Denoising Self-attentive Sequential Recommendation

Abstract

Transformer-based sequential recommenders are very powerful for capturing both short-term and long-term sequential item dependencies. This is mainly attributed to their unique self-attention networks to exploit pairwise item-item interactions within the sequence. However, real-world item sequences are often noisy, which is particularly true for implicit feedback. For example, a large portion of clicks do not align well with user preferences, and many products end up with negative reviews or being returned. As such, the current user action only depends on a subset of items, not on the entire sequences. Many existing Transformer-based models use full attention distributions, which inevitably assign certain credits to irrelevant items. This may lead to sub-optimal performance if Transformers are not regularized properly.

References in corpus (3)

• Session-based Recommendation with Graph Neural Networks
• Denoising Implicit Feedback for Recommendation
• Clicks can be Cheating: Counterfactual Recommendation for Mitigating Clickbait Issue

Cited by in corpus (13)

• Turning Dross Into Gold Loss: is BERT4Rec really better than SASRec?
• Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
• Time to Split: Exploring Data Splitting Strategies for Offline Evaluation of Sequential Recommenders
• Scalable Cross-Entropy Loss for Sequential Recommendations with Large Item Catalogs
• FATA-Trans: Field And Time-Aware Transformer for Sequential Tabular Data
• Towards Lightweight Cross-domain Sequential Recommendation via External Attention-enhanced Graph Convolution Network
• Adversarial Collaborative Filtering for Free
• Enhancing Transformers without Self-supervised Learning: A Loss Landscape Perspective in Sequential Recommendation
• Shapley Value-driven Data Pruning for Recommender Systems
• Multi-task Offline Reinforcement Learning for Online Advertising in Recommender Systems
• Enhancing Recommendation with Denoising Auxiliary Task
• Empowering Denoising Sequential Recommendation with Large Language Model Embeddings