Adaptive Long-term Embedding with Denoising and Augmentation for Recommendation

2025/04/18 by Akhlaghi, Zahra, Chehreghani, Mostafa Haghir · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.2504.13614

Abstract

The rapid growth of the internet has made personalized recommendation systems indispensable. Graph-based sequential recommendation systems, powered by Graph Neural Networks (GNNs), effectively capture complex user-item interactions but often face challenges such as noise and static representations. In this paper, we introduce the Adaptive Long-term Embedding with Denoising and Augmentation for Recommendation (ALDA4Rec) method, a novel model that constructs an item-item graph, filters noise through community detection, and enriches user-item interactions. Graph Convolutional Networks (GCNs) are then employed to learn short-term representations, while averaging, GRUs, and attention mechanisms are utilized to model long-term embeddings. An MLP-based adaptive weighting strategy is further incorporated to dynamically optimize long-term user preferences. Experiments conducted on four real-world datasets demonstrate that ALDA4Rec outperforms state-of-the-art baselines, delivering notable improvements in both accuracy and robustness. The source code is available at https://github.com/zahraakhlaghi/ALDA4Rec.

Citations

• Leveraging hierarchy-aware diffusion model and knowledge-enhanced contrastive learning for recommendation
• PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems
• Disentangling Popularity and Quality: An Edge Classification Approach for Fair Recommendation
• Enhancing robustness in implicit feedback recommender systems with subgraph contrastive learning
• Best of Both Worlds: Advantages of Hybrid Graph Sequence Models
• Transformers need glasses! Information over-squashing in language tasks
• SelfGNN: Self-Supervised Graph Neural Networks for Sequential Recommendation
• Double Correction Framework for Denoising Recommendation
• Heterophily-Aware Fair Recommendation using Graph Convolutional Networks
• Content Augmented Graph Neural Networks
• Fast unfolding of communities in large networks: 15 years later
• Disentangling Long and Short-Term Interests for Recommendation
• Graph Structure Learning with Variational Information Bottleneck
• TEA: A Sequential Recommendation Framework via Temporally Evolving Aggregations
• UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation
• A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• Dynamic Graph Neural Networks for Sequential Recommendation
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• LightGCN
• Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
• Unbiased Recommender Learning from Missing-Not-At-Random Implicit Feedback
• Neural Graph Collaborative Filtering
• BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
• Graph Neural Networks: A Review of Methods and Applications
• Graph neural networks: A review of methods and applications
• Session-Based Recommendation with Graph Neural Networks
• Self-Attentive Sequential Recommendation
• Semi-Supervised Classification with Graph Convolutional Networks
• Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering
• The MovieLens Datasets
• Matrix Factorization Techniques for Recommender Systems
• LLM4DSR: Leveraging Large Language Model for Denoising Sequential Recommendation

Cited by

• Contrastive Matrix Completion with Denoising and Augmented Graph Views for Robust Recommendation

Related

• Recommendation System in Advertising and Streaming Media: Unsupervised Data Enhancement Sequence Suggestions
• Memory Augmented Graph Neural Networks for Sequential Recommendation
• Linear-Time Graph Neural Networks for Scalable Recommendations
• Enhancing Recommendation Systems with GNNs and Addressing Over-Smoothing
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation