IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension

Julie Mordacq, Vicky Kalogeiton, Steve Oudot

Self-supervised learning (SSL) has demonstrated remarkable success in learning useful representations from unlabeled data. However, the standard protocol for evaluating these representations, linear probing, is computationally expensive, sensitive to hyperparameters, and provides limited insight into the geometric structure of the representation space. Motivated by connections between neural network generalization and intrinsic dimensionality (ID) we propose IdEst, a method for estimating the ID of SSL representations via the Minimum Spanning Tree dimension estimator ($\mathrm{dim}_\mathrm{MST}$). Across diverse datasets, architectures, and SSL pretraining objectives, we show that IdEst strongly correlates with downstream linear probe performances. Furthermore, we demonstrate that IdEst enables efficient hyperparameter selection, significantly reducing the computational cost compared to supervised alternatives. Our results highlight intrinsic dimensionality as a principled geometric proxy for assessing and optimizing SSL representations, complementing standard supervised probing protocols.

T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning

Julie Mordacq, David Loiseaux, Vicky Kalogeiton, Steve Oudot

Self-supervised learning (SSL) has emerged as a powerful paradigm for learning representations without labeled data, often by enforcing invariance to input transformations such as rotations or blurring. Recent studies have highlighted two pivotal properties for effective representations: (i) avoiding dimensional collapse-where the learned features occupy only a low-dimensional subspace, and (ii) enhancing uniformity of the induced distribution. In this work, we introduce T-REGS, a simple regularization framework for SSL based on the length of the Minimum Spanning Tree over the learned representation.

ADAPT: Multimodal Learning for Detecting Physiological Changes under Missing Modalities

Julie Mordacq, Leo Milecki, Maria Vakalopoulou, Steve Oudot, Vicky Kalogeiton

Multimodality has recently gained attention in the medical domain, where imaging or video modalities may be integrated with biomedical signals or health records. Yet, two challenges remain: balancing the contributions of modalities, especially in cases with a limited amount of data available, and tackling missing modalities. To address both issues, in this paper, we introduce the AnchoreD multimodAl Physiological Transformer (ADAPT), a multimodal, scalable framework with two key components: (i) aligning all modalities in the space of the strongest, richest modality (called anchor) to learn a joint embedding space, and (ii) a Masked Multimodal Transformer, leveraging both inter- and intra-modality correlations while handling missing modalities.