通过专家协作机制融合异构数据，提升复杂数据建模能力
Cooperation of Experts: Fusing Heterogeneous Information with Large Margin
- 设计多专家编码器，分别学习不同语义空间的关联模式
- 引入大间距机制增强模型鲁棒性，实现互补知识提取
- 在多个基准上验证性能优越，适合异构数据融合任务
融合异构信息仍是现代数据分析中的持续挑战。尽管已有显著进展，现有方法往往未能充分考虑不同语义空间中对象模式的本质差异。为此，我们提出合作专家（CoE）框架，将多类型信息编码为统一的异质多重网络。通过克服模态与连接差异，CoE 提供了一个强大且灵活的模型，用于捕捉真实世界复杂数据的精细结构。在该框架中，专用编码器作为领域特定专家，各自专注于学习特定语义空间中的独特关系模式。为增强鲁棒性并提取互补知识，这些专家通过一种新颖的大间距机制协同工作，并由定制优化策略支持。严格的理论分析确保了框架的可行性和稳定性，大量跨多样基准的实验验证了其卓越性能与广泛适用性。代码已开源：https://github.com/strangeAlan/CoE。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。