Synthetic Data Reveals Generalization Gaps in Correlated Multiple Instance Learning

2025-10-29

AI Summary

Conventional multiple-instance learning (MIL) methods in medical image analysis model instances—e.g., patches or slices—independently, neglecting spatial or sequential contextual dependencies, thereby limiting generalization. Method: We construct a class of synthetic classification tasks with analytically tractable optimal solutions that explicitly require models to leverage features from neighboring instances for discrimination. This enables systematic diagnosis of fundamental bottlenecks in context modeling and generalization of existing MIL approaches, including state-of-the-art relational MIL models. Contribution/Results: Through quantitative comparison against the closed-form Bayesian optimal estimator, we provide the first rigorous quantification of the substantial performance gap between mainstream MIL methods and the theoretical optimum. Experiments demonstrate that even under large-scale training, current methods fail to approach the optimal solution, underscoring the necessity of explicit context-aware mechanisms in MIL frameworks.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Multiple instance learning (MIL) is often used in medical imaging to classify high-resolution 2D images by processing patches or classify 3D volumes by processing slices. However, conventional MIL approaches treat instances separately, ignoring contextual relationships such as the appearance of nearby patches or slices that can be essential in real applications. We design a synthetic classification task where accounting for adjacent instance features is crucial for accurate prediction. We demonstrate the limitations of off-the-shelf MIL approaches by quantifying their performance compared to the optimal Bayes estimator for this task, which is available in closed-form. We empirically show that newer correlated MIL methods still struggle to generalize as well as possible when trained from scratch on tens of thousands of instances.

Problem

• MIL ignores contextual relationships between instances
• Synthetic task reveals generalization gaps in MIL
• Correlated MIL methods struggle with optimal generalization

Innovation

• Synthetic data reveals MIL generalization gaps
• Correlated MIL methods struggle with generalization
• Accounting for adjacent instance features is crucial