Semantic-Structural Cross-Calibration for Multi-Behavior Recommendation
Open Access
- 6 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1187-1197
Abstract
Multi-behavior recommendation (MBR) alleviates target behavior sparsity by leveraging abundant auxiliary behaviors. However, most MBR methods are trapped in a dilemma. Separately aggregating multiple behaviors struggles to fully exploit cross-behavior interaction information, while collectively aggregating different behaviors into a unified graph may cause the target behavior to be submerged among massive auxiliary behaviors. To this end, we propose the Semantic-struCtural crOss-calibRation modEl (SCORE), a structure-conditioned calibration framework for MBR. SCORE adopts a decouple–enhance–calibrate strategy to fully exploit cross-behavior interactions while robustly reconstructing target-related user representations. Specifically, SCORE first decouples target semantics from unified representations through a shared modulation space under joint multi-behavior supervision. It then enhances unified representations through structural refinement on the target-behavior graph, reconstructing target-consistent structural context. Finally, SCORE reconciles semantic and structural references through structure-conditioned gating to obtain calibrated representations. Extensive experiments on three real-world benchmarks demonstrate that SCORE greatly improves over thirteen competitive baselines by up to 61.73% on HR@10 and 46.04% on NDCG@10.Keywords
Funding Information
- National Natural Science Foundation of China (62432003)
- National Natural Science Foundation of China (U25A20431)
This publication has 26 references indexed in Scilit:
- Behavior Merging Graph Convolution Network for Multi-Behavior RecommendationIEEE Transactions on Knowledge and Data Engineering, 2025
- Latent Factor Modeling With Expert Network for Multi-Behavior RecommendationIEEE Transactions on Knowledge and Data Engineering, 2025
- Multi-behavior Recommender Systems: A Survey2025
- VCGAE++: variational collective graph autoEncoder for multi-behavior recommendationKnowledge and Information Systems, 2025
- Multi-Behavior Graph Neural Networks for Recommender SystemIEEE Transactions on Neural Networks and Learning Systems, 2022
- Multi-Behavior Enhanced Recommendation with Cross-Interaction Collaborative Relation Modeling2021
- Multi-behavior Recommendation with Graph Convolutional Networks2020
- LightGCN2020
- Learning to Recommend With Multiple Cascading BehaviorsIEEE Transactions on Knowledge and Data Engineering, 2019
- IR evaluation methods for retrieving highly relevant documents2000