Metraipolis › archive › dc_224a64fecc60
Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphs — arXiv:2610.02990
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.02990
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-05T23:10:02.254Z
- SHA-256 of the archived text
84f63cee666e4e30f7296d435fbd194bb291056cd7172d6e28e3c0b1e9494729- Stable URL of this page
https://metraipolis.com/documento/dc_224a64fecc60
How to cite
Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphs — arXiv:2610.02990 — arXiv, https://arxiv.org/abs/2610.02990 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_224a64fecc60 (Metraipolis archive dc_224a64fecc60, sha256 84f63cee666e4e30f7296d435fbd194bb291056cd7172d6e28e3c0b1e9494729)
BibTeX
@misc{dc224a64fecc60,
title = {Differentiable Koopman Operator for Contrastive Learning on Dynamic Graphs — arXiv:2610.02990},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.02990},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_224a64fecc60; sha256 84f63cee666e4e30f7296d435fbd194bb291056cd7172d6e28e3c0b1e9494729},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.02990. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Real-world interaction networks are inherently dynamic: edges form and dissolve as node behavior shifts over time. Most snapshot-based contrastive methods encode temporal dependencies implicitly in encoder weights, without an explicit model of how node representations evolve, making them brittle under distribution shifts. We propose KAIROS (Koopman-Aligned Invariant Representations for Open Dynamic Systems), a self-supervised framework that embeds a differentiable Koopman operator within a dynamic graph contrastive learning loop to linearize temporal evolution in the learned embedding space. A dual-view encoder pairs raw node features with a graph-diffused structural view and is optimized with multi-granularity contrastive objectives across temporal windows. For anomaly detection, KAIROS uses the Koopman prediction residual together with temporal inconsistency and local neighborhood deviation to separate irregular behavior from predictable graph evolution. Evaluated on nine dynamic graph benchmarks, KAIROS achieves state-of-the-art anomaly detection results on all nine datasets, with gains of up to 23.15 ROC-AUC points over prior work, while remaining competitive for unsupervised node classification. These results show that explicit dynamics modeling provides a scalable and effective inductive bias for temporal graph representation learning. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.02990 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-05T23:01:38.658Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).