Generalizable and Robust Spectral Method for Multi-view Representation Learning

TL;DR

This paper introduces SpecRaGE, a novel multi-view representation learning framework that combines graph Laplacian methods with deep learning, achieving robustness and scalability, especially in noisy or contaminated data scenarios.

Contribution

SpecRaGE innovatively integrates graph Laplacian techniques with neural networks and meta-learning to enhance generalization, robustness, and scalability in multi-view learning.

Findings

Outperforms state-of-the-art methods in noisy data scenarios

Demonstrates robustness against outliers and data contamination

Achieves scalable and generalizable multi-view representations

Abstract

Multi-view representation learning (MvRL) has garnered substantial attention in recent years, driven by the increasing demand for applications that can effectively process and analyze data from multiple sources. In this context, graph Laplacian-based MvRL methods have demonstrated remarkable success in representing multi-view data. However, these methods often struggle with generalization to new data and face challenges with scalability. Moreover, in many practical scenarios, multi-view data is contaminated by noise or outliers. In such cases, modern deep-learning-based MvRL approaches that rely on alignment or contrastive objectives present degraded performance in downstream tasks, as they may impose incorrect consistency between clear and corrupted data sources. We introduce $\textit{SpecRaGE}$, a novel fusion-based framework that integrates the strengths of graph Laplacian methods with the power of deep learning to overcome these challenges. SpecRage uses neural networks to learn parametric mapping that approximates a joint diagonalization of graph Laplacians. This solution bypasses the need for alignment while enabling generalizable and scalable learning of informative and meaningful representations. Moreover, it incorporates a meta-learning fusion module that dynamically adapts to data quality, ensuring robustness against outliers and noisy views. Our extensive experiments demonstrate that SpecRaGE outperforms state-of-the-art methods, particularly in scenarios with data contamination, paving the way for more reliable and efficient multi-view learning.