Cooperation of Experts: Fusing Heterogeneous Information with Large Margin

TL;DR

The paper introduces the Cooperation of Experts (CoE) framework that fuses heterogeneous information into unified networks, enabling better modeling of complex data through expert collaboration and a large margin mechanism.

Contribution

It proposes a novel CoE framework with domain-specific encoders and a large margin collaboration mechanism, addressing heterogeneity in multi-space data analysis.

Findings

Demonstrates superior performance across multiple benchmarks.

Provides theoretical guarantees for stability and feasibility.

Shows broad applicability to real-world complex data.

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 overcoming 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. Our code is available at https://github.com/strangeAlan/CoE.