Notes on the latest work from WSDM 2024 in the area of recommender systems

➡️ Only include details of papers that have preprints available online.

1. Defense Against Model Extraction Attacks on Recommender Systems
   Primer:

2. Motif-based Prompt Learning for Universal Cross-domain Recommendation
   Primer:

3. To Copy, or not to Copy; That is a Critical Issue of the Output Softmax Layer in Neural Sequential Recommenders
   Primer:

4. Linear Recurrent Units for Sequential Recommendation
   Primer:

5. User Behavior Enriched Temporal Knowledge Graph for Sequential Recommendation

Primer:

6. CausalMMM: Learning Causal Structure for Marketing Mix Modeling

Primer:

7. Intent Contrastive Learning with Cross Subsequences for Sequential Recommendation

Primer:

8. Budgeted Embedding Table For Recommender Systems

Primer:

9. Pre-trained Recommender Systems: A Causal Debiasing Perspective

Primer:

10. Dynamic Sparse Learning: A Novel Paradigm for Efficient Recommendation

Primer:

11. PEACE: Prototype lEarning Augmented transferable framework for Cross-domain rEcommendation

Primer:

12. Collaboration and Transition: Distilling Item Transitions into Multi-Query Self-Attention for Sequential Recommendation

Primer:

13. Unified Pretraining for Recommendation via Task Hypergraphs

Primer:

14. SSLRec: A Self-Supervised Learning Library for Recommendation

Primer:

15. Multi-Sequence Attentive User Representation Learning for Side-information Integrated Sequential Recommendation

Primer:

16. LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting

Primer:

17. MONET: Modality-Embracing Graph Convolutional Network and Target-Aware Attention for Multimedia Recommendation

Primer:

18. Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure

Primer:

19. Knowledge Graph Diffusion Model for Recommendation

Primer:

20. Large Language Models for Data Aumgnetation in Recommendation - Current preprint title is LLMRec: Large Language Models with Graph Augmentation for Recommendation

Primer:

21. Leveraging Multimodal Features and Item-level User Feedback for Bundle Construction

Primer:

22. Interact with the Explanations: Causal Debiased Explainable Recommendation System

Primer:

23. Global Heterogeneous Graph and Target Interest Denoising for Multi-behavior Sequential Recommendation

Primer:

24. MultiFS: Automated Multi-Scenario Feature Selection in Deep Recommender Systems

Primer:

25. MADM: A Model-agnostic Denoising Module for Graph-based Social Recommendation

Primer:

26. CDRNP: Cross-Domain Recommendation to Cold-Start Users via Neural Process

Primer:

27. Inverse Learning with Extremely Sparse Feedback for Recommendation

Primer:

28. Contextual MAB Oriented Embedding Denoising for Sequential Recommendation

Primer:

29. Mixed Attention Network for Cross-domain Sequential Recommendation

Primer:

30. Knowledge Graph Context-Enhanced Diversified Recommendation

Primer:

31. Exploring Adapter-based Transfer Learning for Recommender Systems: Empirical Studies and Practical Insights

Primer:

32. Diff-MSR: A Diffusion Model Enhanced Paradigm for Cold-Start Multi-Scenario Recommendation

Primer:

33. AutoPooling: Automated Pooling Search for Multi-valued Features in Recommendations

Primer:

34. C^2DR: Robust Cross-Domain Recommendation based on Causal Disentanglement

Primer:

35. RecJPQ: Training Large-Catalogue Sequential Recommenders

Primer:

36. On the Effectiveness of Unlearning in Session-Based Recommendation

Primer:

37. Proxy-based Item Representation for Attribute and Context-aware Recommendation

Primer:

38. IncMSR: An Incremental Learning Approach for Multi-Scenario Recommendation

Primer:

39. Deep Evolutional Instant Interest Network for CTR Prediction in Trigger-Induced Recommendation

Primer:

40. User Consented Federated Recommender System Against Personalized Attribute Inference Attack

Primer:

41. Neural Kalman Filtering for Robust Temporal Recommendation

Primer:

42. ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models

Primer: Addressing the limitations of existing content-based recommender systems, this paper presents the ONCE framework, which leverages both open- and closed-source large language models (LLMs) to significantly enhance recommendation performance. Their findings demonstrate that combining finetuning on open-source LLMs with prompting-based data augmentation on closed-source models yields substantial improvements, with relative gains reaching up to 19.32% compared to state-of-the-art models. These results highlight the immense potential of LLMs in content-based recommendation and hold significant implications for online content platforms. Notably, the ONCE framework extends beyond news and book recommendation, demonstrating its applicability to diverse domains.