LLMRec: Large Language Models with Graph Augmentation for Recommendation

By Wei Wei, Xubin Ren, Jiabin Tang, Qinyong Wang, Lixin Su, Suqi Cheng, Junfeng Wang, Dawei Yin, Chao Huang. Web Search and Data Mining, 2023

451 citations recorded by the source corpus.

The problem of data sparsity has long been a challenge in recommendation systems, and previous studies have attempted to address this issue by incorporating side information. However, this approach often introduces side effects such as noise, availability issues, and low data quality, which in turn hinder the accurate modeling of user preferences and adversely impact recommendation performance. In light of the recent advancements in large language models (LLMs), which possess extensive knowledge bases and strong reasoning capabilities, we propose a novel framework called LLMRec that enhances recommender systems by employing three simple yet effective LLM-based graph augmentation strategies. Our approach leverages the rich content available within online platforms (e.g., Netflix, MovieLens) to augment the interaction graph in three ways: (i) reinforcing user-item interaction egde, (ii) enhancing the understanding of item node attributes, and (iii) conducting user node profiling, intuitively from the natural language perspective. By employing these strategies, we address the challenges posed by sparse implicit feedback and low-quality side information in recommenders. Besides, to ensure the quality of the augmentation, we develop a denoised data robustification mechanism that includes techniques of noisy implicit feedback pruning and MAE-based feature enhancement that help refine the augmented data and improve its reliability. Furthermore, we provide theoretical analysis to support the effectiveness of LLMRec and clarify the benefits of our method in facilitating model optimization. Experimental results on benchmark datasets demonstrate the superiority of our LLM-based augmentation approach over state-of-the-art techniques. To ensure reproducibility, we have made our code and augmented data publicly available at: https://github.com/HKUDS/LLMRec.git.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/5aa3b1009955ce2c8f896e0d5e94e06155ef1e43

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Wayne Xin Zhao
2. Yupeng Hou
3. Hongyu Lu
4. Ruobing Xie
5. Junjie Zhang
6. Enhong Chen
7. Zihan Lin
8. Qi Liu

In Information Systems

1. Yupeng Hou
2. Wayne Xin Zhao
3. Hongyu Lu
4. Zihan Lin
5. Ruobing Xie
6. Junjie Zhang
7. Enhong Chen
8. Hui Xiong

Citations in the corpus

• Large Language Models are Zero-Shot Rankers for Recommender Systems (2023, background): “As the scaling law shows, the performance of LLMs on various downstream tasks generally increases while scaling up the model size and the amount of training data [24, 15, 28].”
• When large language models meet personalization: perspectives of challenges and opportunities (2023, unknown): “LLMRec [81] adopts LLM-based graph augmentation strategies to enrich the information of items and further designs denoise methods to ensure the augmentation.”
• Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach (2023, unknown): “That is, the LLM is instructed to rerank the retrieved candidate items, enabling more accurate recommendations.”
• How Can Recommender Systems Benefit from Large Language Models: A Survey (2023, unknown): “In UniSRec [ Hou et al. , 2022 ] , the item representations are learned for cross-domain sequential recommendation via a fixed BERT model followed by a lightweight MoE-enhanced network.”
• A survey on large language models for recommendation (2023, background): “These challenges also present valuable research opportunities in the field.”
• GraphGPT: Graph Instruction Tuning for Large Language Models (2023, unknown): “However, effectively integrating large language models with graph learning poses non-trivial challenges.”