PLATONT: Learning a Platonic Representation for Unified Network Tomography
This work addresses network tomography for improved network management and monitoring, offering a novel unified approach that enhances cross-task generalization.
The paper tackles the problem of inferring hidden network states like link performance and topology from external observations by proposing PLATONT, a unified framework that models different network indicators as projections of a shared latent state, resulting in higher accuracy and stronger robustness in experiments on synthetic and real-world datasets.
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.