Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dual-Tree LLM-Enhanced Negative Sampling for Implicit Collaborative Filtering

Jiayi Wu, Zhengyu Wu, Xunkai Li, Rong-Hua Li, Guoren Wang

TL;DR

A text-free and fine-tuning-free Dual-Tree LLM-enhanced Negative Sampling method that combines user-item preference scores with item-item hierarchical similarities from these encodings to mine high-quality hard negatives, thus improving models'discriminative ability.

Abstract

Negative sampling is a pivotal technique in implicit collaborative filtering (CF) recommendation, enabling efficient and effective training by contrasting observed interactions with sampled unobserved ones. Recently, large language models (LLMs) have shown promise in recommender systems; however, research on LLM-empowered negative sampling remains underexplored. Existing methods heavily rely on textual information and task-specific fine-tuning, limiting practical applicability. To address this limitation, we propose a text-free and fine-tuning-free Dual-Tree LLM-enhanced Negative Sampling method (DTL-NS). It consists of two modules: (i) an offline false negative identification module that leverages hierarchical index trees to transform collaborative structural and latent semantic information into structured item-ID encodings for LLM inference, enabling accurate identification of false negatives; and (ii) a multi-view hard negative sampling module that combines user-item preference scores with item-item hierarchical similarities from these encodings to mine high-quality hard negatives, thus improving models' discriminative ability. Extensive experiments demonstrate the effectiveness of DTL-NS. For example, on the Amazon-sports dataset, DTL-NS outperforms the strongest baseline by 10.64% and 19.12% in Recall@20 and NDCG@20, respectively. Moreover, DTL-NS can be integrated into various implicit CF models and negative sampling methods, consistently enhancing their performance.

Dual-Tree LLM-Enhanced Negative Sampling for Implicit Collaborative Filtering

TL;DR

A text-free and fine-tuning-free Dual-Tree LLM-enhanced Negative Sampling method that combines user-item preference scores with item-item hierarchical similarities from these encodings to mine high-quality hard negatives, thus improving models'discriminative ability.

Abstract

Negative sampling is a pivotal technique in implicit collaborative filtering (CF) recommendation, enabling efficient and effective training by contrasting observed interactions with sampled unobserved ones. Recently, large language models (LLMs) have shown promise in recommender systems; however, research on LLM-empowered negative sampling remains underexplored. Existing methods heavily rely on textual information and task-specific fine-tuning, limiting practical applicability. To address this limitation, we propose a text-free and fine-tuning-free Dual-Tree LLM-enhanced Negative Sampling method (DTL-NS). It consists of two modules: (i) an offline false negative identification module that leverages hierarchical index trees to transform collaborative structural and latent semantic information into structured item-ID encodings for LLM inference, enabling accurate identification of false negatives; and (ii) a multi-view hard negative sampling module that combines user-item preference scores with item-item hierarchical similarities from these encodings to mine high-quality hard negatives, thus improving models' discriminative ability. Extensive experiments demonstrate the effectiveness of DTL-NS. For example, on the Amazon-sports dataset, DTL-NS outperforms the strongest baseline by 10.64% and 19.12% in Recall@20 and NDCG@20, respectively. Moreover, DTL-NS can be integrated into various implicit CF models and negative sampling methods, consistently enhancing their performance.
Paper Structure (20 sections, 13 equations, 6 figures, 4 tables, 2 algorithms)

This paper contains 20 sections, 13 equations, 6 figures, 4 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Negative Sampling in Recommendation
  4. LLM-based Recommendation and Negative Sampling
  5. Methodology
  6. Problem Formalization
  7. Dual-Tree LLM-based False Negative Identification (DTL-FNI)
  8. Dual-Tree Guided Multi-View Hard Negative Sampling (DT-MHNS)
  9. Time Complexity
  10. Experiments
  11. Experimental Setup
  12. Datasets
  13. Baselines
  14. Implementation Details
  15. Experiment environment.
  16. ...and 5 more sections

Figures (6)

  • Figure 1: LLM-based false-negative identification accuracy.
  • Figure 2: The DTL-NS framework. We depict a single tree-based item encoding example, since the dual trees use node embeddings from different sources, yet share the same subsequent tree construction and item encoding procedures.
  • Figure 3: Recall@20 vs. wall-clock time (in seconds).
  • Figure 4: The impact of $\alpha_c$ and $\alpha_s$.
  • Figure 5: The impact of different variant methods.
  • ...and 1 more figures