# PLATONT: Learning a Platonic Representation for Unified Network Tomography

arXiv: https://arxiv.org/abs/2511.15251 · HTML: https://mlsanity.com/paper/2511.15251/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 78 references that are in the map.
- First posted on arXiv 19 Nov 2025.

## Builds on (most cited first, 22 of 22)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Which Tasks Should Be Learned Together in Multi-task Learning?](https://mlsanity.com/paper/1905.07553/) (2019)
- [Characterizing and Avoiding Negative Transfer](https://mlsanity.com/paper/1811.09751/) (2018)
- [You Only Learn One Representation: Unified Network for Multiple Tasks](https://mlsanity.com/paper/2105.04206/) (2021)
- [Improving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization](https://mlsanity.com/paper/2202.00232/) (2022)
- [Towards a Unified Framework of Contrastive Learning for Disentangled Representations](https://mlsanity.com/paper/2311.04774/) (2023)
- [Estimating Traffic and Anomaly Maps via Network Tomography](https://mlsanity.com/paper/1407.1660/) (2014)
- [A spectral method for multi-view subspace learning using the product of projections](https://mlsanity.com/paper/2410.19125/) (2024)
- [Learning Based Methods for Traffic Matrix Estimation from Link Measurements](https://mlsanity.com/paper/2008.00905/) (2020)
- [Asymptotic generalization error of a single-layer graph convolutional network](https://mlsanity.com/paper/2402.03818/) (2024)
- [On Fundamental Bounds of Failure Identifiability by Boolean Network Tomography](https://mlsanity.com/paper/1903.10636/) (2019)
- [PixelBytes: Catching Unified Representation for Multimodal Generation](https://mlsanity.com/paper/2410.01820/) (2024)
- [Unlocking Diversity of Fast-Switched Optical Data Center Networks with Unified Routing](https://mlsanity.com/paper/2412.00266/) (2024)
- [Self-Supervised Contrastive Learning for Videos using Differentiable Local Alignment](https://mlsanity.com/paper/2409.04607/) (2024)
- [SecureNT: Smart Topology Obfuscation for Privacy-Aware Network Monitoring](https://mlsanity.com/paper/2412.08177/) (2024)
- [Identification of Path Congestion Status for Network Performance Tomography using Deep Spatial-Temporal Learning](https://mlsanity.com/paper/2412.10762/) (2024)
- [Network Tomography with Path-Centric Graph Neural Network](https://mlsanity.com/paper/2502.16430/) (2025)
- [RoTO: Robust Topology Obfuscation Against Tomography Inference Attacks](https://mlsanity.com/paper/2508.12852/) (2025)

## Abstract (arXiv)

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.