Topological Inductive Bias fosters Multiple Instance Learning in Data-Scarce Scenarios

TL;DR

This paper introduces a topology-preserving inductive bias into multiple instance learning to improve classification performance in data-scarce scenarios, especially for rare disease detection.

Contribution

It proposes Topology Guided MIL (TG-MIL), a novel method that incorporates topological constraints to enhance MIL performance with limited data.

Findings

15.3% average improvement on synthetic datasets

2.8% average improvement on MIL benchmarks

5.5% improvement in rare anemia classification

Abstract

Multiple instance learning (MIL) is a framework for weakly supervised classification, where labels are assigned to sets of instances, i.e., bags, rather than to individual data points. This paradigm has proven effective in tasks where fine-grained annotations are unavailable or costly to obtain. However, the effectiveness of MIL drops sharply when training data are scarce, such as for rare disease classification. To address this challenge, we propose incorporating topological inductive biases into the data representation space within the MIL framework. This bias introduces a topology-preserving constraint that encourages the instance encoder to maintain the topological structure of the instance distribution within each bag when mapping them to MIL latent space. As a result, our Topology Guided MIL (TG-MIL) method enhances the performance and generalizability of MIL classifiers across different aggregation functions, especially under scarce-data regimes. Our evaluations show average performance improvements of 15.3% for synthetic MIL datasets, 2.8% for MIL benchmarks, and 5.5% for rare anemia classification compared to current state-of-the-art MIL models, where only 17-120 samples per class are available. We make our code publicly available.