Structured Contrastive Learning for Interpretable Latent Representations

ICLR 2026 Conference Submission20306 Authors

Keywords: Structured Representation Learning, Contrastive Learning, Neural Network Interpretability, Transformation Invariance, Feature Decoupling

TL;DR: To address neural networks’ brittleness to transformations, we propose Structured Contrastive Learning (SCL), which partitions latent representations into meaningful groups, enabling robust behavior without architectural changes.

Abstract: Neural networks exhibit severe brittleness to semantically irrelevant transformations. A mere 75ms electrocardiogram (ECG) phase shift degrades latent cosine similarity from 1.0 to 0.2, while sensor rotations collapse activity recognition performance with inertial measurement units (IMUs). We identify the root cause as "laissez-faire" representation learning, where latent spaces evolve unconstrained provided task performance is satisfied. We propose Structured Contrastive Learning (SCL), a framework that partitions latent space representations into three semantic groups: invariant features that remain consistent under given transformations (e.g., phase shifts or rotations), variant features that actively differentiate transformations via a novel variant mechanism, and free features that preserve task flexibility. This creates controllable push-pull dynamics where different latent dimensions serve distinct, interpretable purposes. The variant mechanism enhances contrastive learning by encouraging variant features to differentiate within positive pairs, enabling simultaneous robustness and interpretability. Our approach requires no architectural modifications and integrates seamlessly into existing training pipelines. Experiments on ECG phase invariance and IMU rotation robustness demonstrate superior performance: ECG similarity improves from 0.25 to 0.91 under phase shifts, while WISDM activity recognition achieves 86.65% accuracy with 95.38% rotation consistency, consistently outperforming traditional data augmentation. This work represents a paradigm shift from reactive data augmentation to proactive structural learning, transforming neural networks from black boxes into interpretable glass box systems.

Primary Area: learning on time series and dynamical systems

Submission Number: 20306