Topic
recommendation system
Bid Farewell to Seesaw: New Framework Boosts Long-Tail Recommendation Accuracy Without Sacrificing Diversity
A new research paper from arxiv introduces HID (Hybrid Intent-based Dual Constraint Framework), a plug-and-play solution for session-based recommendation that simultaneously improves recommendation accuracy and long-tail item performance, eliminating the traditional trade-off. The framework uses hybrid intent learning and intent constraint loss to filter session-irrelevant noise.
New Generative Recommendation Model HoloRec Uses Hierarchical Encoding and Interleaved Reasoning to Boost Accuracy
A research paper introduces HoloRec, a generative recommendation model that uses holistic encoding and interleaved reasoning to overcome limitations of existing approaches. The model supports two inference modes — non-thinking for speed and thinking for higher accuracy — and shows significant gains on sparse datasets.
LLM-Encoded Knowledge Guides Federated Graph Recommendation to Improve Accuracy
Researchers propose a federated graph recommendation framework that leverages LLM-encoded semantic knowledge to guide cross-client structural aggregation, addressing the challenge of non-IID client data. The method consistently outperforms existing federated graph baselines on standard benchmarks.