Metraipolis › archive › dc_a3e8158cf3fe

Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs — arXiv:2608.27948

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.27948
License (as archived)
CC0-1.0
Archived
2026-10-17T11:06:29.485Z
SHA-256 of the archived text
38adfc183e8b1504df8822fc45dbb1f0669bba2ce4adc0dcc2e0d88319f4ccc3
Stable URL of this page
https://metraipolis.com/documento/dc_a3e8158cf3fe

How to cite

Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs — arXiv:2608.27948 — arXiv (en), https://arxiv.org/abs/2608.27948 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3e8158cf3fe (Metraipolis archive dc_a3e8158cf3fe, sha256 38adfc183e8b1504df8822fc45dbb1f0669bba2ce4adc0dcc2e0d88319f4ccc3)
BibTeX
@misc{dca3e8158cf3fe,
  title = {Temporal Memory-Aware Online Test-Time Adaptation on Dynamic Graphs — arXiv:2608.27948},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.27948},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3e8158cf3fe; sha256 38adfc183e8b1504df8822fc45dbb1f0669bba2ce4adc0dcc2e0d88319f4ccc3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.27948. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which involves potential distribution shifts that may harm model generalization and test-time inference. While recent efforts have investigated TTA on static graphs, there is still a research gap on dynamic graphs learned with dynamic GNN (DGNN) models, where both structural connectivity and node semantics evolve continuously over time. This makes adapting a DGNN model for reliable test-time performance substantially challenging. To fill this gap, in this work, we propose a novel framework of temporal memory-aware Online Test-Time Adaptation on Dynamic Graphs, named DGOTTA, to effectively adapt well-trained DGNNs during test time. Specifically, the proposed DGOTTA contains three modules: (1) temporal-aware augmentation, to extend the diversity of test dynamic graphs for addressing complex temporal and spatial shifts; (2) memory-aware model prediction, to alleviate catastrophic forgetting; (3) consistency-guided online adaptation, to enforce temporal alignment and memory smoothness. Extensive experiments on three real-world datasets and four DGNN backbones demonstrate that DGOTTA significantly improves generalization under diverse distribution shifts and multiple model architectures.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-31 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.27948 — 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 2026-10-17T10:50:25.786Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).