Detecting Functionality-Specific Vulnerabilities via Retrieving Individual Functionality-Equivalent APIs in Open-Source Repositories

2025/01/01 by Chen, Tianyu, Wang, Zeyu, Li, Lin +7 · 13 citations
Computer Science · #Advanced Graph Neural Networks #Domain Adaptation and Few-Shot Learning #Machine Learning and ELM

paper · doi:10.4230/lipics.ecoop.2025.6

openalex created_date 2019/07/30 · openalex publication_date 2025/01/01 · openalex updated_date 2026/07/31

Abstract

Functionality-specific vulnerabilities, which mainly occur in Application Programming Interfaces (APIs) with specific functionalities, are crucial for software developers to detect and avoid. When detecting individual functionality-specific vulnerabilities, the existing two categories of approaches are ineffective because they consider only the API bodies and are unable to handle diverse implementations of functionality-equivalent APIs. To effectively detect functionality-specific vulnerabilities, we propose APISS, the first approach to utilize API doc strings and signatures instead of API bodies. APISS first retrieves functionality-equivalent APIs for APIs with existing vulnerabilities and then migrates Proof-of-Concepts (PoCs) of the existing vulnerabilities for newly detected vulnerable APIs. To retrieve functionality-equivalent APIs, we leverage a Large Language Model for API embedding to improve the accuracy and address the effectiveness and scalability issues suffered by the existing approaches. To migrate PoCs of the existing vulnerabilities for newly detected vulnerable APIs, we design a semi-automatic schema to substantially reduce manual costs. We conduct a comprehensive evaluation to empirically compare APISS with four state-of-the-art approaches of detecting vulnerabilities and two state-of-the-art approaches of retrieving functionality-equivalent APIs. The evaluation subjects include 180 widely used Java repositories using 10 existing vulnerabilities, along with their PoCs. The results show that APISS effectively retrieves functionality-equivalent APIs, achieving a Top-1 Accuracy of 0.81 while the best of the baselines under comparison achieves only 0.55. APISS is highly efficient: the manual costs are within 10 minutes per vulnerability and the end-to-end runtime overhead of testing one candidate API is less than 2 hours. APISS detects 179 new vulnerabilities and receives 60 new CVE IDs, bringing high value to security practice.

Cited by

• BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks
• Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
• Motion Guided 3D Pose Estimation from Videos
• Non-Parametric Graph Learning for Bayesian Graph Neural Networks
• Generalizing Graph Neural Networks on Out-Of-Distribution Graphs
• Neural Relational Inference for Interacting Systems
• Graph Convolutional Networks for Hyperspectral Image Classification
• Gauge Equivariant Mesh CNNs: Anisotropic convolutions on geometric\n graphs
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations
• Matrix Encoding Networks for Neural Combinatorial Optimization
• Measuring and Improving the Use of Graph Information in Graph Neural Networks
• Latent Structure Mining With Contrastive Modality Fusion for Multimedia Recommendation
• BRP-NAS: Prediction-based NAS using GCNs
• Incomplete Graph Representation and Learning via Partial Graph Neural Networks
• Pose-based Modular Network for Human-Object Interaction Detection
• Unified Conversational Recommendation Policy Learning via Graph-based Reinforcement Learning
• Hierarchical Graph-RNNs for Action Detection of Multiple Activities
• CoulGAT: An Experiment on Interpretability of Graph Attention Networks
• Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study
• Deep Graph Memory Networks for Forgetting-Robust Knowledge Tracing
• Personalized Route Recommendation With Neural Network Enhanced Search Algorithm
• Hyperbolic Graph Convolutional Neural Networks
• Improving the generalization of protein expression models with mechanistic sequence information
• Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning
• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
• Identify Hidden Spreaders of Pandemic over Contact Tracing Networks
• Grounded and Controllable Image Completion by Incorporating Lexical Semantics
• On Explainability of Graph Neural Networks via Subgraph Explorations
• Belief places and spaces: Mapping cognitive environments
• Simultaneous Inference of Past Demography and Selection from the Ancestral Recombination Graph under the Beta Coalescent
• Graph Neural Networks for Identifying Protein-Reactive Compounds
• Adaptive unified contrastive learning with graph-based feature aggregator for imbalanced medical image classification
• Vessel-guided and graph-based retinal vessel junction detection and classification
• Graph Convolutional Value Decomposition in Multi-Agent Reinforcement Learning
• Deep Hypergraph U-Net for Brain Graph Embedding and Classification
• Graph convolutional networks for learning with few clean and many noisy labels
• Local2Global: Scaling global representation learning on graphs via local training
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications
• Spherical Message Passing for 3D Graph Networks
• Efficient Variational Graph Autoencoders for Unsupervised Cross-domain Prerequisite Chains
• Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
• Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction
• Graph neural networks: A review of methods and applications
• Improving Distant Supervised Relation Extraction by Dynamic Neural Network
• Jointly Attacking Graph Neural Network and its Explanations
• Sequential Recommendation with Graph Neural Networks
• Cognitive Knowledge Graph Reasoning for One-shot Relational Learning
• FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration
• Sequential Graph Convolutional Network for Active Learning
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• Graph Geometry Interaction Learning
• Understanding Structural Vulnerability in Graph Convolutional Networks
• Towards Robust Partially Supervised Multi-Structure Medical Image Segmentation on Small-Scale Data
• Heterogeneous Similarity Graph Neural Network on Electronic Health Records
• Tree Decomposed Graph Neural Network
• Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging
• Hierarchical Generation of Molecular Graphs using Structural Motifs
• Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting
• Classifying Diagrams and Their Parts using Graph Neural Networks: A Comparison of Crowd-Sourced and Expert Annotations
• Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computation
• Graph Normalizing Flows
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• Visual Semantic Reasoning for Image-Text Matching
• mvn2vec: Preservation and Collaboration in Multi-View Network Embedding
• TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks
• Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
• SAWNet: A Spatially Aware Deep Neural Network for 3D Point Cloud Processing
• Are Graph Neural Networks Miscalibrated?
• GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
• Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles
• DNA: Dynamic Social Network Alignment
• Intact-VAE: Estimating Treatment Effects under Unobserved Confounding
• GCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks
• Graph-based Security and Privacy Analytics via Collective Classification with Joint Weight Learning and Propagation
• Semi-Supervised Graph Classification: A Hierarchical Graph Perspective
• SceneFormer: Indoor Scene Generation with Transformers
• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning
• Exploring Deep 3D Spatial Encodings for Large-Scale 3D Scene Understanding
• TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation
• Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme
• Predicting electric vehicle charging demand using a heterogeneous spatio-temporal graph convolutional network
• High-throughput quantum theory of atoms in molecules (QTAIM) for geometric deep learning of molecular and reaction properties
• Measuring research interest similarity with transition probabilities
• Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition
• M2GCNet: Multi-Modal Graph Convolution Network for Precise Brain Tumor Segmentation Across Multiple MRI Sequences
• How Does GAN-based Semi-supervised Learning Work?
• Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach
• Learning Feature Aggregation for Deep 3D Morphable Models
• Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
• Adaptive Universal Generalized PageRank Graph Neural Network
• Deep Graph Contrastive Representation Learning
• Deep Fusion Clustering Network
• RESCUE: Retrieval Augmented Secure Code Generation
• Sheaf Neural Networks
• Graph-based Joint Pandemic Concern and Relation Extraction on Twitter
• AliGraph: A Comprehensive Graph Neural Network Platform
• Relational Pooling for Graph Representations
• PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python
• Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning
• ICE-GAN: Identity-aware and Capsule-Enhanced GAN with Graph-based Reasoning for Micro-Expression Recognition and Synthesis
• Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection
• Composition-based Multi-Relational Graph Convolutional Networks
• Graph Neural Networks: A Review of Methods and Applications
• Convolution, attention and structure embedding
• Density-Ratio Based Personalised Ranking from Implicit Feedback
• Multi-Graph Transformer for Free-Hand Sketch Recognition
• Understanding over-squashing and bottlenecks on graphs via curvature
• Computing Steiner Trees using Graph Neural Networks
• Hierarchical Graph-to-Graph Translation for Molecules
• AnomalyDAE: Dual autoencoder for anomaly detection on attributed networks
• Attributed Network Embedding for Incomplete Attributed Networks
• Label Efficient Semi-Supervised Learning via Graph Filtering
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Self-Training With Noisy Student Improves ImageNet Classification
• TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction
• Graph Neural Network Training with Data Tiering
• Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty
• Hierarchical attention graph learning with LLM enhancement for molecular solubility prediction
• A nonlinear diffusion method for semi-supervised learning on hypergraphs
• Modeling Dynamic Heterogeneous Network for Link Prediction using Hierarchical Attention with Temporal RNN
• Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
• FedGL: Federated Graph Learning Framework with Global Self-Supervision
• Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
• Semantic Conditioned Dynamic Modulation for Temporal Sentence Grounding in Videos
• A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning
• Knowledge Graph-enhanced Sampling for Conversational Recommender System
• Representing Videos as Discriminative Sub-graphs for Action Recognition
• Interpreting graph neural networks with Myerson values for cheminformatics approaches
• A Biased Graph Neural Network Sampler with Near-Optimal Regret
• Locality and compositionality in zero-shot learning
• A Block-based Generative Model for Attributed Networks Embedding
• MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit
• Deep Neural Networks for Relation Extraction
• Predicting Path Failure In Time-Evolving Graphs
• Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering
• Robust Collective Classification against Structural Attacks
• On the Importance of Sampling in Training GCNs: Tighter Analysis and Variance Reduction
• Graph Neural Networks with Local Graph Parameters
• Graph Meta Learning via Local Subgraphs
• SynProtX: a large-scale proteomics-based deep learning model for predicting synergistic anticancer drug combinations
• Parallel mesh reconstruction streams for pose estimation of interacting hands
• Semi-Implicit Graph Variational Auto-Encoders
• An integrative network approach for longitudinal stratification in Parkinson’s disease
• Auto-Encoding Twin-Bottleneck Hashing
• An Experimental Study of Formula Embeddings for Automated Theorem Proving in First-Order Logic
• ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks
• Heterogeneous-Temporal Graph Convolutional Networks: Make the Community Detection Much Better
• 3D Shape Reconstruction from Vision and Touch
• Privileged Knowledge Distillation for Online Action Detection
• Skeleon-Based Typing Style Learning For Person Identification
• Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignment
• Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
• DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability
• Learning Large Neighborhood Search Policy for Integer Programming
• Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks
• End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection
• Graph Residual Flow for Molecular Graph Generation
• Neural message passing for joint paratope-epitope prediction
• On Learning Paradigms for the Travelling Salesman Problem
• Small-footprint Keyword Spotting with Graph Convolutional Network
• Efficient Robustness Certificates for Discrete Data: Sparsity-Aware\n Randomized Smoothing for Graphs, Images and More
• Open-World Class Discovery with Kernel Networks
• Semantic Graph Based Place Recognition for 3D Point Clouds
• Dual Graph Representation Learning
• Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
• Scaling Gaussian Processes with Derivative Information Using Variational Inference
• Hierarchical Fashion Graph Network for Personalized Outfit Recommendation
• Neural Subgraph Isomorphism Counting
• From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
• Explainability Techniques for Graph Convolutional Networks
• CAP: Co-Adversarial Perturbation on Weights and Features for Improving Generalization of Graph Neural Networks
• Space-Time Correspondence as a Contrastive Random Walk
• Bayesian Graph Neural Networks with Adaptive Connection Sampling
• Vision graph convolutional network for underwater image enhancement
• Cross-GCN: Enhancing Graph Convolutional Network with k-Order Feature Interactions
• Learnt Sparsification for Interpretable Graph Neural Networks
• Learning Knowledge Graph-based World Models of Textual Environments
• Domain Adaptation with Auxiliary Target Domain-Oriented Classifier
• An Efficient Neighborhood-based Interaction Model for Recommendation on Heterogeneous Graph
• Communication-Efficient Sampling for Distributed Training of Graph Convolutional Networks
• Neural Design Network: Graphic Layout Generation with Constraints
• SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks
• Simplifying Graph Convolutional Networks
• Automated Relational Meta-learning
• Weisfeiler and Lehman Go Topological: Message Passing Simplicial\n Networks
• DeltaConv
• Multi-Granularity Reasoning for Social Relation Recognition from Images
• EATSA-GNN: Edge-Aware and Two-Stage attention for enhancing graph neural networks based on teacher–student mechanisms for graph node classification
• A Survey on Temporal Sentence Grounding in Videos
• Relation-Aware Graph Attention Network for Visual Question Answering
• Multi-Label Image Recognition with Graph Convolutional Networks
• Graph Denoising with Framelet Regularizer
• Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling
• Adaptive Transfer Learning on Graph Neural Networks
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• How Attentive are Graph Attention Networks?
• Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
• Chemical-Reaction-Aware Molecule Representation Learning
• Track Seeding and Labelling with Embedded-space Graph Neural Networks
• Learning Vertex Representations for Bipartite Networks
• Towards Robust Graph Contrastive Learning
• Stochastic Aggregation in Graph Neural Networks
• Comprehensive Image Captioning via Scene Graph Decomposition
• Heterogeneous Deep Graph Infomax
• Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks
• Label-Aware Graph Convolutional Networks
• On Provable Benefits of Depth in Training Graph Convolutional Networks
• Intelligent Home 3D: Automatic 3D-House Design from Linguistic Descriptions Only
• Contrastive Learning for Recommender System
• Poisson Kernel Avoiding Self-Smoothing in Graph Convolutional Networks
• Node-Level Membership Inference Attacks Against Graph Neural Networks
• MagNet: A Neural Network for Directed Graphs
• LLMCDSR: Enhancing Cross-Domain Sequential Recommendation with Large Language Models
• Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
• Compact Graph Architecture for Speech Emotion Recognition
• GNNExplainer: Generating Explanations for Graph Neural Networks
• GRNet: Gridding Residual Network for Dense Point Cloud Completion
• Graph Convolutional Module for Temporal Action Localization in Videos
• Knowledge-aware Graph Neural Networks with Label Smoothness Regularization for Recommender Systems
• Distributed Scheduling using Graph Neural Networks
• Building Dynamic Knowledge Graphs from Text-based Games
• Tensor Networks for Multi-Modal Non-Euclidean Data
• Towards Accurate and Compact Architectures via Neural Architecture Transformer
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations
• Independent Prototype Propagation for Zero-Shot Compositionality
• Lipschitz Normalization for Self-Attention Layers with Application to Graph Neural Networks
• Graph Generation with Variational Recurrent Neural Network
• Complementary-Label Learning for Arbitrary Losses and Models
• Improving Generative Imagination in Object-Centric World Models
• The expressive power of kth-order invariant graph networks
• Network Representation Learning: From Traditional Feature Learning to Deep Learning
• A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems
• Bayesian Graph Convolutional Neural Networks using Node Copying
• UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation
• Weisfeiler and Lehman Go Cellular: CW Networks
• Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation
• Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
• Adversarial Model Extraction on Graph Neural Networks
• Distinguish Confusion in Legal Judgment Prediction via Revised Relation Knowledge
• Combinatorial Optimization by Graph Pointer Networks and Hierarchical Reinforcement Learning
• Principled Hyperedge Prediction with Structural Spectral Features and Neural Networks
• How Powerful are Graph Neural Networks?
• Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks
• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• Overlapping Community Detection with Graph Neural Networks
• GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs
• Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphs
• Face to purchase: Predicting consumer choices with structured facial and behavioral traits embedding
• ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Inductive Subgraph Embedding for Link Prediction
• Explaining GNN over Evolving Graphs using Information Flow
• MixHop: Higher-Order Graph Convolutional Architectures via Sparsified\n Neighborhood Mixing
• GraphTSNE: A Visualization Technique for Graph-Structured Data
• A Graph Convolutional Network Composition Framework for Semi-supervised\n Classification
• Improving the Expressive Power of Graph Neural Network with Tinhofer Algorithm
• Graph Adversarial Training: Dynamically Regularizing Based on Graph Structure
• Graph Convolutional Gaussian Processes For Link Prediction
• Recent advances and applications of deep learning methods in materials science
• Graph-Based Social Relation Reasoning
• A Structured Model For Action Detection
• Beyond Clicks: Modeling Multi-Relational Item Graph for Session-Based Target Behavior Prediction
• Graph-based, Self-Supervised Program Repair from Diagnostic Feedback
• Decoupling feature propagation from the design of graph auto-encoders
• Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
• Spatio-Temporal Hybrid Graph Convolutional Network for Traffic Forecasting in Telecommunication Networks
• Spatio-temporal Modeling for Large-scale Vehicular Networks Using Graph Convolutional Networks
• Wasserstein Adversarially Regularized Graph Autoencoder
• Graph Neural Networks Inspired by Classical Iterative Algorithms
• Learning Reasoning Paths over Semantic Graphs for Video-grounded Dialogues
• Generalization and Representational Limits of Graph Neural Networks
• An Attention-based Graph Neural Network for Heterogeneous Structural Learning
• Neural Embedding Propagation on Heterogeneous Networks
• Winning an Election: On Emergent Strategic Communication in Multi-Agent Networks
• Causal World Models by Unsupervised Deconfounding of Physical Dynamics
• Graphite: Iterative Generative Modeling of Graphs
• Bridging the Gap between Sample-based and One-shot Neural Architecture Search with BONAS
• Decentralized Structural-RNN for Robot Crowd Navigation with Deep Reinforcement Learning
• Disentangling Interpretable Generative Parameters of Random and\n Real-World Graphs
• Affective Image Content Analysis: Two Decades Review and New Perspectives
• Representation Learning for Words and Entities
• Constant Curvature Graph Convolutional Networks
• Boost then Convolve: Gradient Boosting Meets Graph Neural Networks
• "How do urban incidents affect traffic speed?" A Deep Graph Convolutional Network for Incident-driven Traffic Speed Prediction
• Adversarial Graph Augmentation to Improve Graph Contrastive Learning
• Relationship-Embedded Representation Learning for Grounding Referring Expressions
• Spatio-Temporal Sparsification for General Robust Graph Convolution Networks
• Combination of Unified Embedding Model and Observed Features for Knowledge Graph Completion
• Weakly Supervised Semantic Point Cloud Segmentation:Towards 10X Fewer Labels
• Generating Smooth Pose Sequences for Diverse Human Motion Prediction
• Space-Time-Separable Graph Convolutional Network for Pose Forecasting
• GraphiT: Encoding Graph Structure in Transformers
• Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning
• Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs
• PICK: Processing Key Information Extraction from Documents using Improved Graph Learning-Convolutional Networks
• Using ontology embeddings for structural inductive bias in gene\n expression data analysis
• MGN-Net: a multi-view graph normalizer for integrating heterogeneous\n biological network populations
• A Diffusion Model for POI Recommendation
• Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition
• AppQ: Warm-starting App Recommendation Based on View Graphs
• Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings
• Robust Deep Graph Based Learning for Binary Classification
• Stealing Links from Graph Neural Networks
• SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization
• Non-Recursive Graph Convolutional Networks
• Lets Play Music: Audio-driven Performance Video Generation
• Solving Machine Learning Problems
• Neural Graph Embedding Methods for Natural Language Processing
• Iterative Graph Self-Distillation
• Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences
• 3D Graph Anatomy Geometry-Integrated Network for Pancreatic Mass Segmentation, Diagnosis, and Quantitative Patient Management
• Graph Pooling with Node Proximity for Hierarchical Representation Learning
• AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition
• Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College
• Evaluating Modules in Graph Contrastive Learning
• Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
• Hierarchical Pyramid Representations for Semantic Segmentation
• Interferometric Graph Transform for Community Labeling
• A Graph Neural Network Approach for Scalable Wireless Power Control
• A gentle introduction to deep learning for graphs
• Learning structured approximations of combinatorial optimization problems
• Backdoor Attacks to Graph Neural Networks
• Scaling Up Graph Neural Networks Via Graph Coarsening
• A Framework for Object-Centric Predictive Process Monitoring Using Graph-Based Process Executions
• HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information
• Popularity Prediction on Social Platforms with Coupled Graph Neural Networks
• Accuracy and Scalability of Machine Learning Methods for Genotype-Phenotype Association Data
• Adversarial Robustness for Code
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph\n Link Prediction
• Graph Neighborhood Attentive Pooling
• AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack
• Cascade Image Matting with Deformable Graph Refinement
• Artificial intelligence in the discovery and design of molecular semiconductors: a systematic review
• Toward Edge-Centric Network Embeddings
• Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
• Modeling Sentiment Dependencies with Graph Convolutional Networks for Aspect-level Sentiment Classification
• Using Text to Teach Image Retrieval
• Self-Supervised Regional and Temporal Auxiliary Tasks for Facial Action Unit Recognition
• Graph-Convolutional Deep Learning to Identify Optimized Molecular Configurations
• From #Jobsearch to #Mask: Improving COVID-19 Cascade Prediction with Spillover Effects
• Spatio-temporal Parking Behaviour Forecasting and Analysis Before and During COVID-19
• GNNIE: GNN Inference Engine with Load-balancing and Graph-Specific Caching
• Exploring Global Information for Session-based Recommendation
• Ego-CNN: Distributed, Egocentric Representations of Graphs for Detecting Critical Structures
• Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching
• DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation
• ACNe: Attentive Context Normalization for Robust Permutation-Equivariant Learning
• Multi-task Self-distillation for Graph-based Semi-Supervised Learning
• EEG-Based Emotion Recognition Using Regularized Graph Neural Networks
• GraphSAC: Detecting anomalies in large-scale graphs
• Maintenance planning recommendation of complex industrial equipment based on knowledge graph and graph neural network
• InfoFair: Information-Theoretic Intersectional Fairness
• On Inductive Biases for Machine Learning in Data Constrained Settings
• Prediction of Carbon Nanostructure Mechanical Properties and Role of Defects Using Machine Learning
• Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art
• Latent Network Embedding via Adversarial Auto-encoders
• Explainability-based Backdoor Attacks Against Graph Neural Networks
• Graph Neural Networks with Feature and Structure Aware Random Walk
• When Product Search Meets Collaborative Filtering: A Hierarchical Heterogeneous Graph Neural Network Approach
• Higher-order Weighted Graph Convolutional Networks
• Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition
• Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Tackling Online Abuse: A Survey of Automated Abuse Detection Methods
• Knowledge-aware Zero-Shot Learning: Survey and Perspective
• A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions
• Towards Representation Identical Privacy-Preserving Graph Neural Network via Split Learning
• Automatic design of novel potential 3CL^pro and PL^pro inhibitors
• GCN for HIN via Implicit Utilization of Attention and Meta-paths
• AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange
• Distance-aware Molecule Graph Attention Network for Drug-Target Binding Affinity Prediction
• ECKPN: Explicit Class Knowledge Propagation Network for Transductive Few-shot Learning
• Deep graph convolution neural network with non-negative matrix factorization for community discovery
• How did we get there? AI applications to biological networks and sequences
• Sensitive Information Detection: Recursive Neural Networks for Encoding Context
• HR-RCNN: Hierarchical Relational Reasoning for Object Detection
• Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders
• Adversarial Training Methods for Network Embedding
• Reinforcement Learning based Collective Entity Alignment with Adaptive Features
• Exploiting Contextual Information with Deep Neural Networks
• Blind Omnidirectional Image Quality Assessment with Viewport Oriented Graph Convolutional Networks
• Multi-Stage Network Embedding for Exploring Heterogeneous Edges
• PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
• Subset Node Representation Learning over Large Dynamic Graphs
• Improving Graph Neural Networks with Simple Architecture Design
• Pre-training of Graph Augmented Transformers for Medication Recommendation
• Calibrating and Improving Graph Contrastive Learning
• Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networks
• Deep Graph Memory Networks for Forgetting-Robust Knowledge Tracing
• Network2Vec Learning Node Representation Based on Space Mapping in Networks
• Simplification of Graph Convolutional Networks: A Matrix Factorization-based Perspective
• Unsupervised Joint k-node Graph Representations with Compositional\n Energy-Based Models
• Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals
• Variational Graph Recurrent Neural Networks
• Auto-encoding brain networks with applications to analyzing large-scale brain imaging datasets
• CollaborER: A Self-supervised Entity Resolution Framework Using Multi-features Collaboration
• How Powerful is Graph Convolution for Recommendation?
• Graph Factorization Machines for Cross-Domain Recommendation
• Neural Enhanced Belief Propagation for Cooperative Localization
• Graph-SIM: A Graph-based Spatiotemporal Interaction Modelling for Pedestrian Action Prediction
• Meta Graph Attention on Heterogeneous Graph with Node-Edge Co-evolution
• High-Order Relation Construction and Mining for Graph Matching
• Sewer-ML: A Multi-Label Sewer Defect Classification Dataset and\n Benchmark
• The deep learning and statistical physics applications to the problems of combinatorial optimization
• Deconvolutional Networks on Graph Data
• The Open Force Field Initiative: Open Software and Open Science for Molecular Modeling
• Optimizing Graph Transformer Networks with Graph-based Techniques
• Incorporating Reachability Knowledge into a Multi-Spatial Graph Convolution Based Seq2Seq Model for Traffic Forecasting
• Deep Graph Library Optimizations for Intel(R) x86 Architecture
• Locality Guided Neural Networks for Explainable Artificial Intelligence
• Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing
• Deep Representation Learning For Multimodal Brain Networks
• Mining Implicit Entity Preference from User-Item Interaction Data for Knowledge Graph Completion via Adversarial Learning
• BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
• Exact Recovery of Community Structures Using DeepWalk and Node2vec
• Syntax Role for Neural Semantic Role Labeling
• Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition
• Robust Counterfactual Explanations on Graph Neural Networks
• Hierarchical Graph Networks for 3D Human Pose Estimation
• mathttMedGraph: Structural and Temporal Representation Learning of\n Electronic Medical Records
• Bosonic Random Walk Networks for Graph Learning
• Pre-Training Graph Neural Networks for Cold-Start Users and Items Representation
• CoPhy: Counterfactual Learning of Physical Dynamics
• Meta-path Free Semi-supervised Learning for Heterogeneous Networks
• Graph Structural-topic Neural Network
• Modeling Graph Node Correlations with Neighbor Mixture Models
• Relational Graph Learning for Crowd Navigation
• Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network
• A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis
• Topology-Aware Graph Pooling Networks
• Predicting Critical Nodes in Temporal Networks by Dynamic Graph Convolutional Networks
• Graph Stacked Hourglass Networks for 3D Human Pose Estimation
• H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks
• Uniform Convergence, Adversarial Spheres and a Simple Remedy
• Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep\n Reinforcement Learning
• Answer Them All! Toward Universal Visual Question Answering Models
• A Lagrangian Approach to Information Propagation in Graph Neural Networks
• Temporal Network Embedding with Micro- and Macro-dynamics
• TSAM: Temporal Link Prediction in Directed Networks based on Self-Attention Mechanism
• RWNE: A Scalable Random-Walk-Based Network Embedding Framework with Personalized Higher-Order Proximity Preserved
• Hierarchical Graph Matching Network for Graph Similarity Computation
• SoGCN: Second-Order Graph Convolutional Networks
• Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity
• Parameter Prediction for Unseen Deep Architectures
• Exchange means change: An unsupervised single-temporal change detection framework based on intra- and inter-image patch exchange
• SeanNet: Semantic Understanding Network for Localization Under Object Dynamics
• GraphXCOVID: Explainable Deep Graph Diffusion Pseudo-Labelling for\n Identifying COVID-19 on Chest X-rays
• Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition
• LightCAKE: A Lightweight Framework for Context-Aware Knowledge Graph Embedding
• Contrastive Graph Neural Network Explanation
• Contrastive Neural Architecture Search with Neural Architecture Comparators
• Demand Prediction for Electric Vehicle Sharing
• A Proposal-based Approach for Activity Image-to-Video Retrieval
• Unsupervised Multi-Source Domain Adaptation for Person Re-Identification
• Single-Layer Graph Convolutional Networks For Recommendation
• MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
• GMAN: A Graph Multi-Attention Network for Traffic Prediction
• Reconstruction for Powerful Graph Representations
• Dual-embedding based Neural Collaborative Filtering for Recommender Systems
• Irregular Convolutional Auto-Encoder on Point Clouds
• Discovering Supply Chain Links with Augmented Intelligence
• Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning
• Same Object, Different Grasps: Data and Semantic Knowledge for Task-Oriented Grasping
• Towards Feature-free TSP Solver Selection: A Deep Learning Approach
• Anomaly Detection for Aggregated Data Using Multi-Graph Autoencoder
• A Novel Higher-order Weisfeiler-Lehman Graph Convolution
• Accurate Learning of Graph Representations with Graph Multiset Pooling
• Learning Graph Pooling and Hybrid Convolutional Operations for Text Representations
• Fitting the Search Space of Weight-sharing NAS with Graph Convolutional Networks

Related

• SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis
• Finding Vulnerabilities in Mobile Application APIs: A Modular Programmatic Approach
• Data-Driven Vulnerability Detection and Repair in Java Code
• A Manually-Curated Dataset of Fixes to Vulnerabilities of Open-Source Software
• A Match Made in Heaven? AI-driven Matching of Vulnerabilities and Security Unit Tests