PLATONT: Learning a Platonic Representation for Unified Network Tomography
By: Chengze Du , Heng Xu , Zhiwei Yu and more
Potential Business Impact:
Finds hidden internet problems using many clues.
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.
Similar Papers
Cross-View Topology-Aware Graph Representation Learning
Machine Learning (CS)
Helps computers understand complex data patterns better.
Quantum Noise Tomography with Physics-Informed Neural Networks
Quantum Physics
Makes quantum computers work better by understanding noise.
Network of Theseus (like the ship)
Machine Learning (CS)
Changes computer brains without losing their smarts.