5 papers
ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning
Yunhang He, Cong Xu, Zhangchi Zhu +2
Graph filter design is central to spectral collaborative filtering, yet most existing methods rely on manually tuned hyperparameters rather than fully learnable filters. We show th…
Break the Optimization Barrier of LLM-Enhanced Recommenders: A Theoretical Analysis and Practical Framework
Zhangchi Zhu, Wei Zhang
Large language model (LLM)-enhanced recommendation models inject LLM representations into backbone recommenders to exploit rich item text without inference-time LLM cost. However,…
Rejuvenating Cross-Entropy Loss in Knowledge Distillation for Recommender Systems
Zhangchi Zhu, Wei Zhang
This paper analyzes Cross-Entropy (CE) loss in knowledge distillation (KD) for recommender systems. KD for recommender systems targets at distilling rankings, especially among item…
Exploring Feature-based Knowledge Distillation for Recommender System: A Frequency Perspective
Zhangchi Zhu, Wei Zhang
In this paper, we analyze the feature-based knowledge distillation for recommendation from the frequency perspective. By defining knowledge as different frequency components of the…
Are LLM-based Recommenders Already the Best? Simple Scaled Cross-entropy Unleashes the Potential of Traditional Sequential Recommenders
Cong Xu, Zhangchi Zhu, Mo Yu +3
Large language models (LLMs) have been garnering increasing attention in the recommendation community. Some studies have observed that LLMs, when fine-tuned by the cross-entropy (C…