Improving Content Recommendation: Knowledge Graph-Based Semantic Contrastive Learning for Diversity and Cold-Start Users (2024.lrec-main)
Copied to clipboard
Yejin Kim, Scott Rome, Kevin Foley, Mayur Nankani, Rimon Melamed, Javier Morales, Abhay K. Yadav, Maria Peifer, Sardar Hamidian, H. Howie Huang
| Challenge: | Current approaches focus on improving ranking performance at the cost of escalating complexity and complicating the task. |
| Approach: | They propose a hybrid multi-task learning approach that trains on user-item and item-i item interactions. |
| Outcome: | The proposed approach improves accuracy, relevance, and diversity of user recommendations even for cold-start users. |
Similar Papers
LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation (2025.findings-emnlp)
Copied to clipboard
Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li
| Challenge: | Traditional contrastive learning methods treat negative feedback as equally hard or easy, ignoring informative semantic difficulty during training. |
| Approach: | They propose a framework leveraging Large Language Models to Activate interactions in Graph Contrastive Learning for Recommendation. |
| Outcome: | The proposed framework outperforms state-of-the-art benchmarks on multiple benchmarks. |
Aligning Large Language Models with Recommendation Knowledge (2024.findings-naacl)
Copied to clipboard
Yuwei Cao, Nikhil Mehta, Xinyang Yi, Raghunandan Hulikal Keshavan, Lukasz Heldt, Lichan Hong, Ed Chi, Maheswaran Sathiamoorthy
| Challenge: | Large language models (LLMs) excel at natural language reasoning, but cannot model complex user-item interactions inherent in recommendation tasks. |
| Approach: | They propose to equip large language models with recommendation-specific knowledge to address this gap by combining Masked Item Modeling and Bayesian Personalized Ranking (BPR) auxiliary task data samples are generated that encode item correlations and user preferences. |
| Outcome: | Experiments on Amazon Toys & Games, Beauty, and Sports & Outdoors show that the proposed method outperforms conventional and LLM-based baselines by significant margins in retrieval. |
Pre-training Multi-task Contrastive Learning Models for Scientific Literature Understanding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models (LMs) have shown effectiveness in literature understanding tasks, especially when tuned via contrastive learning. |
| Approach: | They propose a multi-task contrastive learning framework that enables common knowledge sharing across different scientific literature understanding tasks while preventing task-specific skills from interfering with each other. |
| Outcome: | The proposed framework outperforms state-of-the-art pre-trained language models on a comprehensive dataset. |
Perturbation-driven Dual Auxiliary Contrastive Learning for Collaborative Filtering Recommendation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing contrastive learning-based methods struggle with data sparsity in real-world recommendations . Graph collaborative filtering incorporates contrastive training as an auxiliary task to improve performance . |
| Approach: | They propose a perturbation-driven dual auxiliary contrastive learning task for collaborative filtering . structure perturbation and weight perturbation are used to construct two graphs . |
| Outcome: | The proposed model outperforms benchmark models on multiple public datasets. |
Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integration (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Query-to-Recommendation framework integrates large langucage models into recommendation systems . but it faces training-induced bias and bottlenecks from serialized architecture . |
| Approach: | They propose a parallel recommendation framework that decouples LLMs from candidate pre-selection and direct retrieval over the entire item pool. |
| Outcome: | The proposed framework decouples LLMs from candidate pre-selection and enables direct retrieval over the entire item pool. |
Reviews Meet Graphs: Enhancing User and Item Representations for Recommendation with Hierarchical Attentive Graph Neural Network (D19-1)
Copied to clipboard
| Challenge: | Existing methods to learn user and item representations from review texts do not take into account the user-user and item-item relatedness of the user. |
| Approach: | They propose to use review content and user-item graphs to integrate them as different views. |
| Outcome: | The proposed approach can learn user and item representations from review content and user-item graphs. |
Personalized Neural Embeddings for Collaborative Filtering with Text (N19-1)
Copied to clipboard
| Challenge: | Traditional CF approaches exploit user-item relations only and suffer from data sparsity issues. |
| Approach: | They develop a Personalized Neural Embedding framework to exploit both interactions and words seamlessly. |
| Outcome: | The proposed framework exploits both interactions and words seamlessly and predicts user preferences on items based on these embeddings. |
SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Text-based methods lag behind graph embedding-based approaches for knowledge graph completion (KGC) |
| Approach: | They propose three types of negatives to improve contrastive learning to improve learning efficiency. |
| Outcome: | The proposed model outperforms embedding-based methods on several benchmark datasets. |
Enhancing High-order Interaction Awareness in LLM-based Recommender Model (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to model user-item interactions do not account for high-order interactions. |
| Approach: | They propose to enhance whole-word embeddings to enhance LLMs’ interpretation of graph-constructed interactions for recommendations without requiring graph pre-training. |
| Outcome: | The proposed model outperforms state-of-the-art methods in direct recommendations. |
GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative Filtering (2022.naacl-main)
Copied to clipboard
| Challenge: | Content-based collaborative filtering (CF) predicts user-item interactions based on both items’ interaction history and item content information. |
| Approach: | They propose to combine item encodings with a multi-modality approach to improve training efficiency by 146x . |
| Outcome: | The proposed model improves training efficiency (up to 146x) on five datasets from two task domains of Knowledge Tracing and News Recommendation. |