学术报告

Hierarchical Contrastive Learning for Multimodal Data

题目:Hierarchical Contrastive Learning for Multimodal Data

报告人:李惠超

报告人简介:李惠超,中国科学院大学数学科学学院博士研究生,师从张三国教授。于2025-2026年到新加坡国立大学进行为期一年的交流访问,受Doudou Zhou教授指导。目前的研究方向包括深度学习的统计理论研究,多模态学习方法,智能体评测及模型算法研究。

摘要:Multimodal representation learning is commonly built on a shared-private decomposition, treating latent information as either common to all modalities or specific to one. This binary view is often inadequate: many factors are shared by only subsets of modalities, and ignoring such partial sharing can over-align unrelated signals and obscure complementary information. We propose Hierarchical Contrastive Learning (HCL), a framework that learns globally shared, partially shared, and modality-specific representations within a unified model. HCL combines a hierarchical latent-variable formulation with structural sparsity and a structure-aware contrastive objective that aligns only modalities that genuinely share a latent factor. Under uncorrelated latent variables, we prove identifiability of the hierarchical decomposition, establish recovery guarantees for the loading matrices, and derive parameter estimation and excess-risk bounds for downstream prediction. Simulations show accurate recovery of hierarchical structure and effective selection of task-relevant components. On multimodal electronic health records, HCL yields more informative representations and consistently improves predictive performance.

报告时间:2026年7月21日 下午14:00-15:00

报告地点:腾讯会议:988-540-021

邀请人:胡晓楠