Cooperation of Experts: Fusing Heterogeneous Information with Large Margin

Shuo Wang, Shunyang Huang, Jinghui Yuan, Zhixiang Shen, Zhao Kang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:63169-63185, 2025.

Abstract

Fusing heterogeneous information remains a persistent challenge in modern data analysis. While significant progress has been made, existing approaches often fail to account for the inherent heterogeneity of object patterns across different semantic spaces. To address this limitation, we propose the Cooperation of Experts (CoE) framework, which encodes multi-typed information into unified heterogeneous multiplex networks. By transcending modality and connection differences, CoE provides a powerful and flexible model for capturing the intricate structures of real-world complex data. In our framework, dedicated encoders act as domain-specific experts, each specializing in learning distinct relational patterns in specific semantic spaces. To enhance robustness and extract complementary knowledge, these experts collaborate through a novel large margin mechanism supported by a tailored optimization strategy. Rigorous theoretical analyses guarantee the framework’s feasibility and stability, while extensive experiments across diverse benchmarks demonstrate its superior performance and broad applicability.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-wang25an, title = {Cooperation of Experts: Fusing Heterogeneous Information with Large Margin}, author = {Wang, Shuo and Huang, Shunyang and Yuan, Jinghui and Shen, Zhixiang and Kang, Zhao}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {63169--63185}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/wang25an/wang25an.pdf}, url = {https://proceedings.mlr.press/v267/wang25an.html}, abstract = {Fusing heterogeneous information remains a persistent challenge in modern data analysis. While significant progress has been made, existing approaches often fail to account for the inherent heterogeneity of object patterns across different semantic spaces. To address this limitation, we propose the Cooperation of Experts (CoE) framework, which encodes multi-typed information into unified heterogeneous multiplex networks. By transcending modality and connection differences, CoE provides a powerful and flexible model for capturing the intricate structures of real-world complex data. In our framework, dedicated encoders act as domain-specific experts, each specializing in learning distinct relational patterns in specific semantic spaces. To enhance robustness and extract complementary knowledge, these experts collaborate through a novel large margin mechanism supported by a tailored optimization strategy. Rigorous theoretical analyses guarantee the framework’s feasibility and stability, while extensive experiments across diverse benchmarks demonstrate its superior performance and broad applicability.} }
Endnote
%0 Conference Paper %T Cooperation of Experts: Fusing Heterogeneous Information with Large Margin %A Shuo Wang %A Shunyang Huang %A Jinghui Yuan %A Zhixiang Shen %A Zhao Kang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-wang25an %I PMLR %P 63169--63185 %U https://proceedings.mlr.press/v267/wang25an.html %V 267 %X Fusing heterogeneous information remains a persistent challenge in modern data analysis. While significant progress has been made, existing approaches often fail to account for the inherent heterogeneity of object patterns across different semantic spaces. To address this limitation, we propose the Cooperation of Experts (CoE) framework, which encodes multi-typed information into unified heterogeneous multiplex networks. By transcending modality and connection differences, CoE provides a powerful and flexible model for capturing the intricate structures of real-world complex data. In our framework, dedicated encoders act as domain-specific experts, each specializing in learning distinct relational patterns in specific semantic spaces. To enhance robustness and extract complementary knowledge, these experts collaborate through a novel large margin mechanism supported by a tailored optimization strategy. Rigorous theoretical analyses guarantee the framework’s feasibility and stability, while extensive experiments across diverse benchmarks demonstrate its superior performance and broad applicability.
APA
Wang, S., Huang, S., Yuan, J., Shen, Z. & Kang, Z.. (2025). Cooperation of Experts: Fusing Heterogeneous Information with Large Margin. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:63169-63185 Available from https://proceedings.mlr.press/v267/wang25an.html.

Related Material