Task-Augmented Cross-View Imputation Network for Partial Multi-View Incomplete Multi-Label Classification

TL;DR

This paper introduces TACVI-Net, a novel two-stage network that imputes missing multi-view data in incomplete multi-label classification by leveraging task-relevant features and multi-view reconstruction, improving performance on real-world datasets.

Contribution

The paper proposes a task-augmented cross-view imputation network that effectively recovers missing views in incomplete multi-view multi-label learning using a two-stage approach.

Findings

Outperforms state-of-the-art methods on five datasets.

Effectively recovers missing multi-view data.

Enhances classification accuracy in incomplete multi-view scenarios.

Abstract

In real-world scenarios, multi-view multi-label learning often encounters the challenge of incomplete training data due to limitations in data collection and unreliable annotation processes. The absence of multi-view features impairs the comprehensive understanding of samples, omitting crucial details essential for classification. To address this issue, we present a task-augmented cross-view imputation network (TACVI-Net) for the purpose of handling partial multi-view incomplete multi-label classification. Specifically, we employ a two-stage network to derive highly task-relevant features to recover the missing views. In the first stage, we leverage the information bottleneck theory to obtain a discriminative representation of each view by extracting task-relevant information through a view-specific encoder-classifier architecture. In the second stage, an autoencoder based multi-view reconstruction network is utilized to extract high-level semantic representation of the augmented features and recover the missing data, thereby aiding the final classification task. Extensive experiments on five datasets demonstrate that our TACVI-Net outperforms other state-of-the-art methods.