Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

2017/08/25 by Xiao, Han, Rasul, Kashif, Vollgraf, Roland · 340 citations
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1708.07747

Abstract

We present Fashion-MNIST, a new dataset comprising of 28x28 grayscale images of 70,000 fashion products from 10 categories, with 7,000 images per category. The training set has 60,000 images and the test set has 10,000 images. Fashion-MNIST is intended to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits. The dataset is freely available at https://github.com/zalandoresearch/fashion-mnist

Cited by

• Rethinking Expert Training for Model Merging with Prompt Learning
• Image Inpainting via Stochastic Dynamics
• Shunting Inhibition and Dendritic Branching Shape Local Credit Assignment
• Qutrit-Based Neural Quantum Kernels for Classification Tasks
• FILLER: Feature Imputation via Latent Location Exploration and Retrieval
• Automated Numerical Stability Analysis of Deep Learning Operators
• PIcsC: Partitioning-Induced Covariate Shift Correction
• Multiclass Classification without Labels via Posterior Simplex Geometry
• Are Flat Minima an Illusion?
• Online Learning Extreme Learning Machine with Low-Complexity Predictive Plasticity Rule and FPGA Implementation
• Residual Prior Diffusion: A Probabilistic Framework Integrating Coarse Latent Priors with Diffusion Models
• MODE: Multi-Objective Adaptive Coreset Selection
• Programmable Optical Spectrum Shapers as Computing Primitives for Accelerating Convolutional Neural Networks
• Clust-PSI-PFL: A Population Stability Index Approach for Clustered Non-IID Personalized Federated Learning
• Bloom Filter Encoding for Machine Learning
• Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning
• Sprecher Networks: A Parameter-Efficient Kolmogorov-Arnold Architecture
• Practical Quantum-Classical Feature Fusion for complex data Classification
• Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study
• Is Your Conditional Diffusion Model Actually Denoising?
• DeepGuard: Defending Deep Joint Source-Channel Coding Against Eavesdropping at Physical-Layer
• FedOAED: Federated On-Device Autoencoder Denoiser for Heterogeneous Data under Limited Client Availability
• Practical Framework for Privacy-Preserving and Byzantine-robust Federated Learning
• Domain-Aware Quantum Circuit for QML
• How to Square Tensor Networks and Circuits Without Squaring Them
• Semi-Supervised Online Learning on the Edge by Transforming Knowledge from Teacher Models
• Fully Dynamic Algorithms for Chamfer Distance
• Persistent Multiscale Density-based Clustering
• On Improving Deep Active Learning with Formal Verification
• MURIM: Multidimensional Reputation-based Incentive Mechanism for Federated Learning
• DAMA: A Unified Accelerated Approach for Decentralized Nonconvex Minimax Optimization-Part I: Algorithm Development and Results
• Element-wise Modulation of Random Matrices for Efficient Neural Layers
• Dual-Qubit Hierarchical Fuzzy Neural Network for Image Classification: Enabling Relational Learning via Quantum Entanglement
• Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerability
• Federated Learning with Feedback Alignment
• Communication-Efficient Neural Tangent Kernels for Heterogeneous Decentralized Federated Learning
• Uncertainty Quantification for Machine Learning: One Size Does Not Fit All
• DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning
• D2M: A Decentralized, Privacy-Preserving, Incentive-Compatible Data Marketplace for Collaborative Learning
• Simple Yet Effective Selective Imputation for Incomplete Multi-view Clustering
• REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature
• Uncertainty-Preserving QBNNs: Multi-Level Quantization of SVI-Based Bayesian Neural Networks for Image Classification
• Wasserstein-Aligned Hyperbolic Multi-View Clustering
• GS-KAN: Parameter-Efficient Kolmogorov-Arnold Networks via Sprecher-Type Shared Basis Functions
• SSplain: Sparse and Smooth Explainer for Retinopathy of Prematurity Classification
• A Bootstrap Perspective on Stochastic Gradient Descent
• Evaluation Framework for Centralized and Decentralized Aggregation Algorithm in Federated Systems
• Credal and Interval Deep Evidential Classifications
• Neural Variability Enhances Artificial Network Robustness
• BEP: A Binary Error Propagation Algorithm for Binary Neural Networks Training
• Domain Feature Collapse: Implications for Out-of-Distribution Detection and Solutions
• Density-Informed VAE (DiVAE): Reliable Log-Prior Probability via Density Alignment Regularization
• Parameter efficient hybrid spiking-quantum convolutional neural network with surrogate gradient and quantum data-reupload
• Convergence of a class of gradient-free optimisation schemes when the objective function is noisy, irregular, or both
• Multi-Scale Visual Prompting for Lightweight Small-Image Classification
• Probabilistic Foundations of Fuzzy Simplicial Sets for Nonlinear Dimensionality Reduction
• Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation
• Unifying Sign and Magnitude for Optimizing Deep Vision Networks via ThermoLion
• Walking on the Fiber: A Simple Geometric Approximation for Bayesian Neural Networks
• Realistic Handwritten Multi-Digit Writer (MDW) Number Recognition Challenges
• From Coefficients to Directions: Rethinking Model Merging with Directional Alignment
• TIE: A Training-Inversion-Exclusion Framework for Visually Interpretable and Uncertainty-Guided Out-of-Distribution Detection
• Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation
• Escaping Barren Plateaus in Variational Quantum Algorithms Using Negative Learning Rate in Quantum Internet of Things
• An Improved and Generalised Analysis for Spectral Clustering
• The Multiclass Score-Oriented Loss (MultiSOL) on the Simplex
• Multiclass threshold-based classification and model evaluation
• Anomaly Detection with Adaptive and Aggressive Rejection for Contaminated Training Data
• Readout-Side Bypass for Residual Hybrid Quantum-Classical Models
• Flexible Genetic Algorithm for Quantum Support Vector Machines
• Federated style aware transformer aggregation of representations
• Uncertainty of Network Topology with Applications to Out-of-Distribution Detection
• Re-Key-Free, Risky-Free: Adaptable Model Usage Control
• DL-CapsNet: A Deep and Light Capsule Network
• InTAct: Interval-based Task Activation Consolidation for Continual Learning
• Quantum Masked Autoencoders for Vision Learning
• Hard Samples, Bad Labels: Robust Loss Functions That Know When to Back Off
• Scenario-Aware Control of Segmented Ladder Bus: Design and FPGA Implementation
• DecNefSimulator: A Modular, Interpretable Framework for Decoded Neurofeedback Simulation Using Generative Models
• Robust Client-Server Watermarking for Split Federated Learning
• Synthetic Forgetting without Access: A Few-shot Zero-glance Framework for Machine Unlearning
• LAYA: Layer-wise Attention Aggregation for Interpretable Depth-Aware Neural Networks
• On Robustness of Linear Classifiers to Targeted Data Poisoning
• FLClear: Visually Verifiable Multi-Client Watermarking for Federated Learning
• LILogic Net: Compact Logic Gate Networks with Learnable Connectivity for Efficient Hardware Deployment
• CEDL: Centre-Enhanced Discriminative Learning for Anomaly Detection
• Benchmarking Quantum Kernels Across Diverse and Complex Data
• Tight Robustness Certification through the Convex Hull of ℓ₀ Attacks
• On the Detectability of Active Gradient Inversion Attacks in Federated Learning
• ACT as Human: Multimodal Large Language Model Data Annotation with Critical Thinking
• LE-CapsNet: A Light and Enhanced Capsule Network
• FedeCouple: Fine-Grained Balancing of Global-Generalization and Local-Adaptability in Federated Learning
• Parameter-Free Clustering via Self-Supervised Consensus Maximization (Extended Version)
• Iterated Population Based Training with Task-Agnostic Restarts
• Verified SHAP: Provable Bounds for Exact Shapley Values of Neural Networks
• Distributed Zero-Shot Learning for Visual Recognition
• PraxiMLP: A Threshold-based Framework for Efficient Three-Party MLP with Practical Security
• Multivariate Variational Autoencoder
• Runtime Safety Monitoring of Deep Neural Networks for Perception: A Survey
• An Efficient Gradient-Aware Error-Bounded Lossy Compressor for Federated Learning
• Optimizing Classification of Infrequent Labels by Reducing Variability in Label Distribution
• Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network
• Vectorized Computation of Euler Characteristic Functions and Transforms
• Which Similarity-Sensitive Entropy?
• Decentralized Federated Learning with Distributed Aggregation Weight Optimization
• Bayesian Natural Gradient Fine-Tuning of CLIP Models via Kalman Filtering
• Bayesian Coreset Optimization for Personalized Federated Learning
• Trans-defense: Transformer-based Denoiser for Adversarial Defense with Spatial-Frequency Domain Representation
• Higher-Order Regularization Learning on Hypergraphs
• Active Learning with Task-Driven Representations for Messy Pools
• Topology-Aware Active Learning on Graphs
• Evaluation of Wafer-Scale SOT-MRAM for Analog Crossbar Array Applications
• A Framework for Bounding Deterministic Risk with PAC-Bayes: Applications to Majority Votes
• Scaling Adaptive Non-Local Observable Quantum Super-Resolution via Matrix Product States
• How Out-of-Equilibrium Phase Transitions can Seed Pattern Formation in Trained Diffusion Models
• FloDR: An invertible dimensionality reduction method based on a normalising flow
• Calibrated Uncertainty Sampling for Active Learning
• Defending Against Backdoor Attacks via Alignment Checking in Model-Contrastive Federated Learning
• Conformalized Rate-Adaptive Sensing
• Surrogate Assisted Diversity Estimation in Neural Ensemble Search
• SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions
• Real-time Calibration-free Imaging Through Dynamic and Distinct Multimode Fibers via Spatial Harmonic Invariant Nonlinear Encoding (SHINE)
• Cost-Sensitive Unbiased Risk Estimation for Multi-Class Positive-Unlabeled Learning
• An efficient probabilistic hardware architecture for diffusion-like models
• Explaining Robustness to Catastrophic Forgetting Through Incremental Concept Formation
• Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station
• VIKING: Deep variational inference with stochastic projections
• Plugging Weight-tying Nonnegative Neural Network into Proximal Splitting Method: Architecture for Guaranteeing Convergence to Optimal Point
• Amortized Variational Inference for Partial-Label Learning: A Probabilistic Approach to Label Disambiguation
• Towards Straggler-Resilient Split Federated Learning: An Unbalanced Update Approach
• Optimal Graph Clustering without Edge Density Signals
• Optimization of the quantization of dense neural networks from an exact QUBO formulation
• Matrix-Free Least Squares Solvers: Values, Gradients, and What to Do With Them
• Learning from N-Tuple Data with M Positive Instances: Unbiased Risk Estimation and Theoretical Guarantees
• Uncertainty Estimation by Flexible Evidential Deep Learning
• Exploration via Feature Perturbation in Contextual Bandits
• TeamFormer: Shallow Parallel Transformers with Progressive Approximation
• Programmatic Representation Learning with Language Models
• FedPPA: Progressive Parameter Alignment for Personalized Federated Learning
• Hybrid Boson Sampling-Neural Network Architecture for Enhanced Classification
• HattriQ: Designing Integrated Gradients for Feature Attribution in Quantum Machine Learning
• Learning at the Speed of Physics: Equilibrium Propagation on Oscillator Ising Machines
• Iterative Data Curation with Theoretical Guarantees
• Phase-Aware Deep Learning with Complex-Valued CNNs for Audio Signal Applications
• Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning
• Convergence of optimizers implies eigenvalues filtering at equilibrium
• Do We Really Need Permutations? Impact of Width Expansion on Linear Mode Connectivity
• FedLAM: Low-latency Wireless Federated Learning via Layer-wise Adaptive Modulation
• Quick-CapsNet (QCN): A fast alternative to Capsule Networks
• Posterior Collapse as a Phase Transition in Variational Autoencoders
• Quantum-enhanced Computer Vision: Going Beyond Classical Algorithms
• DPMM-CFL: Clustered Federated Learning via Dirichlet Process Mixture Model Nonparametric Clustering
• Angular Constraint Embedding via SpherePair Loss for Constrained Clustering
• Field Free Spin-Orbit Torque Controlled Synapse and Stochastic Neuron Devices for Spintronic Boltzmann Neural Networks
• Out-of-Distribution Detection from Small Training Sets using Bayesian Neural Network Classifiers
• MACS: Measurement-Aware Consistency Sampling for Inverse Problems
• Expand Neurons, Not Parameters
• Busemann Functions in the Wasserstein Space: Existence, Closed-Forms, and Applications to Slicing
• RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts
• Technical note on Fisher Information for Robust Federated Cross-Validation
• Learning Robust Diffusion Models from Imprecise Supervision
• Dale meets Langevin: A Multiplicative Denoising Diffusion Model
• Using Fourier Analysis and Mutant Clustering to Accelerate DNN Mutation Testing
• Provenance Networks: End-to-End Exemplar-Based Explainability
• Random Feature Spiking Neural Networks
• Nonparametric Identification of Latent Concepts
• Uncertainty Quantification for Regression using Proper Scoring Rules
• TAP: Two-Stage Adaptive Personalization of Multi-task and Multi-Modal Foundation Models in Federated Learning
• FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
• From MNIST to ImageNet: Understanding the Scalability Boundaries of Differentiable Logic Gate Networks
• Ascent Fails to Forget
• Neural Hamilton--Jacobi Characteristic Flows for Optimal Transport
• Lightweight and Robust Federated Data Valuation
• One-shot Conditional Sampling: MMD meets Nearest Neighbors
• Enabling Physical AI through Biological Principles
• Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model
• Generalist Multi-Class Anomaly Detection via Distillation to Two Heterogeneous Student Networks
• Learning-Based Testing for Deep Learning: Enhancing Model Robustness with Adversarial Input Prioritization
• Differentiable Sparsity via D-Gating: Simple and Versatile Structured Penalization
• Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning
• Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery
• Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models
• Ringleader ASGD: The First Asynchronous SGD with Optimal Time Complexity under Data Heterogeneity
• Neural Feature Geometry Evolves as Discrete Ricci Flow
• Slicing Wasserstein Over Wasserstein Via Functional Optimal Transport
• The role of fibration symmetries in geometric deep learning
• QuFoundry: Generating Data with Quantum Properties for Quantum Machine Learning Utility
• Contrastive Mutual Information Learning: Toward Robust Representations without Positive-Pair Augmentations
• Explaining Grokking and Information Bottleneck through Neural Collapse Emergence
• LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training
• Null-Space Filtering for Data-Free Continual Model Merging: Preserving Transparency, Promoting Fidelity
• The Unwinnable Arms Race of AI Image Detection
• Simplifying Neural Networks During Training
• Spontaneous symmetry breaking and Goldstone modes for deep information propagation
• dtour: A Steerable Tour de Vis Through High-Dimensional Data
• Training deep physical neural networks with local physical information bottleneck
• Shared-Weights Extender and Gradient Voting for Neural Network Expansion
• On the Edge of Memorization in Diffusion Models
• MER-Inspector: Assessing model extraction risks from an attack-agnostic perspective
• All-magnonic neurons for analog artificial neural networks
• On The Dynamic Ensemble Selection for TinyML-based Systems -- a Preliminary Study
• Confidence-gated training for efficient early-exit neural networks
• An Unlearning Framework for Continual Learning
• Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning
• Enhancing Performance and Calibration in Quantile Hyperparameter Optimization
• Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
• Incorporating Visual Cortical Lateral Connection Properties into CNN: Recurrent Activation and Excitatory-Inhibitory Separation
• FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learning
• Beyond Correlation: Causal Multi-View Unsupervised Feature Selection Learning
• On the Out-of-Distribution Backdoor Attack for Federated Learning
• ReTrack: Data Unlearning in Diffusion Models through Redirecting the Denoising Trajectory
• EByFTVeS: Efficient Byzantine Fault Tolerant-based Verifiable Secret-sharing in Distributed Privacy-preserving Machine Learning
• A biological vision inspired framework for machine perception of abutting grating illusory contours
• Curvature as a tool for evaluating dimensionality reduction and estimating intrinsic dimension
• Exploring Training Data Attribution under Limited Access Constraints
• Learning from Uncertain Similarity and Unlabeled Data
• Neuromorphic Photonic Circuits with Nonlinear Dynamics and Memory for Time Sequence Classification
• Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks
• SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixing
• PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits
• Feature Space Topology Control via Hopkins Loss
• Differentially Private Decentralized Dataset Synthesis Through Randomized Mixing with Correlated Noise
• FedBiF: Communication-Efficient Federated Learning via Bits Freezing
• ZORRO: Zero-Knowledge Robustness and Privacy for Split Learning (Full Version)
• Locality in Image Diffusion Models Emerges from Data Statistics
• MSPCaps: A Multi-Scale Patchify Capsule Network with Cross-Agreement Routing for Visual Recognition
• Diabatic quantum annealing for training energy-based generative models
• Decentralized Stochastic Nonconvex Optimization under the (L₀,L₁)-Smoothness
• Heart Disease Prediction: A Comparative Study of Optimisers Performance in Deep Neural Networks
• Label Smoothing++: Enhanced Label Regularization for Training Neural Networks
• ACE and Diverse Generalization via Selective Disagreement
• Breaking the Conventional Forward-Backward Tie in Neural Networks: Activation Functions
• Imitative Membership Inference Attack
• Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decomposition
• Entanglement and Classical Simulability in Quantum Extreme Learning Machines
• PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization
• Benchmarking Robust Aggregation in Decentralized Gradient Marketplaces
• Universality of physical neural networks with multivariate nonlinearity
• On Evaluating the Poisoning Robustness of Federated Learning under Local Differential Privacy
• The Advantage of Fine-Grained Training
• Dynamical Learning in Deep Asymmetric Recurrent Neural Networks
• On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
• Plug-and-Play Latent Diffusion for Electromagnetic Inverse Scattering with Application to Brain Imaging
• RL's Razor: Why Online Reinforcement Learning Forgets Less
• Rethinking Layer-wise Gaussian Noise Injection: Bridging Implicit Objectives and Privacy Budget Allocation
• Semi-decentralized Federated Time Series Prediction with Client Availability Budgets
• A Service-Oriented Adaptive Hierarchical Incentive Mechanism for Federated Learning
• Stealth by Conformity: Evading Robust Aggregation through Adaptive Poisoning
• RotaTouille: Rotation Equivariant Deep Learning for Contours
• Privacy-Utility Trade-off in Data Publication: A Bilevel Optimization Framework with Curvature-Guided Perturbation
• UMATO: Bridging Local and Global Structures for Reliable Visual Analytics with Dimensionality Reduction
• Preserving Bilinear Weight Spectra with a Signed and Shrunk Quadratic Activation Function
• Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity
• Modeling and benchmarking quantum optical neurons for efficient neural computation
• One-Shot Clustering for Federated Learning Under Clustering-Agnostic Assumption
• SC-GIR: Goal-oriented Semantic Communication via Invariant Representation Learning
• Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats
• FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learning
• Feature Augmentations for High-Dimensional Learning
• Class Incremental Continual Learning with Self-Organizing Maps and Variational Autoencoders Using Synthetic Replay
• Photonic restricted Boltzmann machine for content generation tasks
• Owen Sampling Accelerates Contribution Estimation in Federated Learning
• Cluster and then Embed: A Modular Approach for Visualization
• Saddle Hierarchy in Dense Associative Memory
• Tackling Federated Unlearning as a Parameter Estimation Problem
• GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling
• Federated Learning with Heterogeneous and Private Label Sets
• FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning
• Towards Reliable and Generalizable Differentially Private Machine Learning (Extended Version)
• Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
• AFABench: A Generic Framework for Benchmarking Active Feature Acquisition
• FedUP: Efficient Pruning-based Federated Unlearning for Model Poisoning Attacks
• Multi-view Clustering via Bi-level Decoupling and Consistency Learning
• ASAP: Unsupervised Post-training with Label Distribution Shift Adaptive Learning Rate
• DREAMS: Preserving both Local and Global Structure in Dimensionality Reduction
• Beyond Trade-offs: A Unified Framework for Privacy, Robustness, and Communication Efficiency in Federated Learning
• SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
• Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods
• Robust Federated Learning under Adversarial Attacks via Loss-Based Client Clustering
• Deploying Models to Non-participating Clients in Federated Learning without Fine-tuning: A Hypernetwork-based Approach
• TCUQ: Single-Pass Uncertainty Quantification from Temporal Consistency with Streaming Conformal Calibration for TinyML
• SimQFL: A Quantum Federated Learning Simulator with Real-Time Visualization
• Toward Architecture-Agnostic Local Control of Posterior Collapse in VAEs
• DE-VAE: Revealing Uncertainty in Parametric and Inverse Projections with Variational Autoencoders using Differential Entropy
• Combinations of Fast Activation and Trigonometric Functions in Kolmogorov-Arnold Networks
• PCA- and SVM-Grad-CAM for Convolutional Neural Networks: Closed-form Jacobian Expression
• Adaptive Variance-Penalized Continual Learning with Fisher Regularization
• eMamba: Efficient Acceleration Framework for Mamba Models in Edge Computing
• Detecting Untargeted Attacks and Mitigating Unreliable Updates in Federated Learning for Underground Mining Operations
• Topological Structure Description for Artcode Detection Using the Shape of Orientation Histogram
• FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairness
• Resource-Aware Aggregation and Sparsification in Heterogeneous Ensemble Federated Learning
• Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stability
• Decentralized Relaxed Smooth Optimization with Gradient Descent Methods
• Multi-Hop Privacy Propagation for Differentially Private Federated Learning in Social Networks
• Cognition in Superposition: Quantum Models in AI, Finance, Defence, Gaming and Collective Behaviour
• Fuzzy-Pattern Tsetlin Machine
• A Distributed Asynchronous Generalized Momentum Algorithm Without Delay Bounds
• Enhancing Privacy in Decentralized Min-Max Optimization: A Differentially Private Approach
• Revisiting Data Attribution for Influence Functions
• QuProFS: An Evolutionary Training-free Approach to Efficient Quantum Feature Map Search
• Data-Efficient Neural Training with Dynamic Connectomes
• Watermarking Kolmogorov-Arnold Networks for Emerging Networked Applications via Activation Perturbation
• Local Diffusion Models and Phases of Data Distributions
• Differentially Private Federated Clustering with Random Rebalancing
• Membership Inference Attack with Partial Features
• Task complexity shapes internal representations and robustness in neural networks
• Negative Binomial Variational Autoencoders for Overdispersed Latent Modeling
• Cumulative Learning Rate Adaptation: Revisiting Path-Based Schedules for SGD and Adam
• Learning from Similarity-Confidence and Confidence-Difference
• Learning from Oblivion: Predicting Knowledge Overflowed Weights via Retrodiction of Forgetting
• Compressed Decentralized Momentum Stochastic Gradient Methods for Nonconvex Optimization
• Toward Errorless Training ImageNet-1k
• Gaussian mixture layers for neural networks
• Cloud Model Characteristic Function Auto-Encoder: Integrating Cloud Model Theory with MMD Regularization for Enhanced Generative Modeling
• SelectiveShield: Lightweight Hybrid Defense Against Gradient Leakage in Federated Learning
• Neural Network Training via Stochastic Alternating Minimization with Trainable Step Sizes
• Slice or the Whole Pie? Utility Control for AI Models
• Energy-Efficient Stochastic Computing (SC) Neural Networks for Internet of Things Devices With Layer-Wise Adjustable Sequence Length (ASL)
• Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
• Heterogeneity-Oblivious Robust Federated Learning
• RegMean++: Enhancing Effectiveness and Generalization of Regression Mean for Model Merging
• Pseudo-label Induced Subspace Representation Learning for Robust Out-of-Distribution Detection
• FedAPTA: Federated Multi-task Learning for Heterogeneous Devices with Adaptive Layer-wise Pruning and Task-aware Aggregation
• Model Recycling Framework for Multi-Source Data-Free Supervised Transfer Learning
• Stochastic Encodings for Active Feature Acquisition
• Improving Noise Efficiency in Privacy-preserving Dataset Distillation
• Dynamic Clustering for Personalized Federated Learning on Heterogeneous Edge Devices
• FedGuard: A Diverse-Byzantine-Robust Mechanism for Federated Learning with Major Malicious Clients
• SDSNN: A Single-Timestep Spiking Neural Network with Self-Dropping Neuron and Bayesian Optimization
• Random-Access Ranked Retrieval and Similarity Search
• Towards Heterogeneity-Aware and Energy-Efficient Topology Optimization for Decentralized Federated Learning in Edge Environment
• Evaluating the Dynamics of Membership Privacy in Deep Learning
• FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks
• Graph Lineages and Skeletal Graph Products
• Proto-EVFL: Enhanced Vertical Federated Learning via Dual Prototype with Extremely Unaligned Data
• Density Operator Expectation Maximization
• Supervised Quantum Image Processing
• Cascading and Proxy Membership Inference Attacks
• Embedding-Aware Quantum-Classical SVMs for Scalable Quantum Machine Learning

Related

• Training on test data: Removing near duplicates in Fashion-MNIST
• The iMaterialist Fashion Attribute Dataset
• MMFashion: An Open-Source Toolbox for Visual Fashion Analysis
• Segmentation task for fashion and apparel
• Fashion-Gen: The Generative Fashion Dataset and Challenge