CCLRec: Consensus-driven Contrastive Learning for LLM-enhanced Graph Recommendation

Ting Guo, Dongyu Pei, Litiao Qiu, Xiaoying Liao, Ke Liang, Peng Song, Pinle Qin
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:38235-38247, 2026.

Abstract

Recommendation systems seek to accurately model user preferences from a large set of candidate items. Graph neural networks (GNNs) have emerged as a dominant approach in this domain due to their ability to capture high-order user–item interactions. Recent efforts have aimed to enhance GNN-based representation learning by incorporating the semantic reasoning capabilities of large language models (LLMs). However, existing methods often process graph structural information and LLM-derived semantic knowledge separately, creating a supervisory gap between structural proximity and semantic relevance. To bridge this gap, we propose CCLRec, a consensus-driven contrastive learning framework for recommendation. CCLRec deeply integrates structural and semantic information by identifying consistent signals. Specifically, we first use an LLM to extract semantic representations of items and to sample candidate positive/negative sets in the semantic space. We then introduce a structural–semantic consensus mining strategy that computes the intersection between a node’s structural neighbors in the graph and its semantically similar items. This allows us to identify high-confidence positive pairs endorsed by both collaborative filtering patterns and LLM-based reasoning. By centering contrastive learning on these consensus pairs and applying a weight-aware reinforcement mechanism during training, CCLRec significantly amplifies the contribution of high-quality consensus features during training. Experiments across multiple public benchmarks show that CCLRec consistently outperforms state-of-the-art methods on key metrics, demonstrating the effectiveness of our consensus-aware design.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-guo26p, title = {{CCLR}ec: Consensus-driven Contrastive Learning for {LLM}-enhanced Graph Recommendation}, author = {Guo, Ting and Pei, Dongyu and Qiu, Litiao and Liao, Xiaoying and Liang, Ke and Song, Peng and Qin, Pinle}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {38235--38247}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/guo26p/guo26p.pdf}, url = {https://proceedings.mlr.press/v306/guo26p.html}, abstract = {Recommendation systems seek to accurately model user preferences from a large set of candidate items. Graph neural networks (GNNs) have emerged as a dominant approach in this domain due to their ability to capture high-order user–item interactions. Recent efforts have aimed to enhance GNN-based representation learning by incorporating the semantic reasoning capabilities of large language models (LLMs). However, existing methods often process graph structural information and LLM-derived semantic knowledge separately, creating a supervisory gap between structural proximity and semantic relevance. To bridge this gap, we propose CCLRec, a consensus-driven contrastive learning framework for recommendation. CCLRec deeply integrates structural and semantic information by identifying consistent signals. Specifically, we first use an LLM to extract semantic representations of items and to sample candidate positive/negative sets in the semantic space. We then introduce a structural–semantic consensus mining strategy that computes the intersection between a node’s structural neighbors in the graph and its semantically similar items. This allows us to identify high-confidence positive pairs endorsed by both collaborative filtering patterns and LLM-based reasoning. By centering contrastive learning on these consensus pairs and applying a weight-aware reinforcement mechanism during training, CCLRec significantly amplifies the contribution of high-quality consensus features during training. Experiments across multiple public benchmarks show that CCLRec consistently outperforms state-of-the-art methods on key metrics, demonstrating the effectiveness of our consensus-aware design.} }
Endnote
%0 Conference Paper %T CCLRec: Consensus-driven Contrastive Learning for LLM-enhanced Graph Recommendation %A Ting Guo %A Dongyu Pei %A Litiao Qiu %A Xiaoying Liao %A Ke Liang %A Peng Song %A Pinle Qin %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-guo26p %I PMLR %P 38235--38247 %U https://proceedings.mlr.press/v306/guo26p.html %V 306 %X Recommendation systems seek to accurately model user preferences from a large set of candidate items. Graph neural networks (GNNs) have emerged as a dominant approach in this domain due to their ability to capture high-order user–item interactions. Recent efforts have aimed to enhance GNN-based representation learning by incorporating the semantic reasoning capabilities of large language models (LLMs). However, existing methods often process graph structural information and LLM-derived semantic knowledge separately, creating a supervisory gap between structural proximity and semantic relevance. To bridge this gap, we propose CCLRec, a consensus-driven contrastive learning framework for recommendation. CCLRec deeply integrates structural and semantic information by identifying consistent signals. Specifically, we first use an LLM to extract semantic representations of items and to sample candidate positive/negative sets in the semantic space. We then introduce a structural–semantic consensus mining strategy that computes the intersection between a node’s structural neighbors in the graph and its semantically similar items. This allows us to identify high-confidence positive pairs endorsed by both collaborative filtering patterns and LLM-based reasoning. By centering contrastive learning on these consensus pairs and applying a weight-aware reinforcement mechanism during training, CCLRec significantly amplifies the contribution of high-quality consensus features during training. Experiments across multiple public benchmarks show that CCLRec consistently outperforms state-of-the-art methods on key metrics, demonstrating the effectiveness of our consensus-aware design.
APA
Guo, T., Pei, D., Qiu, L., Liao, X., Liang, K., Song, P. & Qin, P.. (2026). CCLRec: Consensus-driven Contrastive Learning for LLM-enhanced Graph Recommendation. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:38235-38247 Available from https://proceedings.mlr.press/v306/guo26p.html.

Related Material