PLATONT: Learning a Platonic Representation for Unified Network Tomography

TL;DR

PLATONT introduces a unified framework for network tomography that models various network indicators as projections of a shared latent state, improving generalization and robustness across multiple network inference tasks.

Contribution

It proposes a novel shared latent space model guided by the Platonic Representation Hypothesis, enabling multi-task learning and better interpretability in network tomography.

Findings

Outperforms existing methods in link estimation, topology inference, and traffic prediction.

Achieves higher accuracy and robustness on synthetic and real-world datasets.

Effectively models multiple network indicators within a unified latent space.

Abstract

Network tomography aims to infer hidden network states, such as link performance, traffic load, and topology, from external observations. Most existing methods solve these problems separately and depend on limited task-specific signals, which limits generalization and interpretability. We present PLATONT, a unified framework that models different network indicators (e.g., delay, loss, bandwidth) as projections of a shared latent network state. Guided by the Platonic Representation Hypothesis, PLATONT learns this latent state through multimodal alignment and contrastive learning. By training multiple tomography tasks within a shared latent space, it builds compact and structured representations that improve cross-task generalization. Experiments on synthetic and real-world datasets show that PLATONT consistently outperforms existing methods in link estimation, topology inference, and traffic prediction, achieving higher accuracy and stronger robustness under varying network conditions.