Metraipolis › archive › dc_beed8939525d

AnchorRM: Parallel Intra-Batch State Reconstruction with Anchor-Based Residual Memory for Temporal Graph Neural Networks — arXiv:2610.27558

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27558
License (as archived)
CC0-1.0
Archived
2026-10-21T07:07:51.462Z
SHA-256 of the archived text
f527d0b1a9aabd5e8d8e1d52bcae7ef5d9e49c82e77eea7aa1314cc9f9b2f153
Stable URL of this page
https://metraipolis.com/documento/dc_beed8939525d

How to cite

AnchorRM: Parallel Intra-Batch State Reconstruction with Anchor-Based Residual Memory for Temporal Graph Neural Networks — arXiv:2610.27558 — arXiv (en), https://arxiv.org/abs/2610.27558 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_beed8939525d (Metraipolis archive dc_beed8939525d, sha256 f527d0b1a9aabd5e8d8e1d52bcae7ef5d9e49c82e77eea7aa1314cc9f9b2f153)
BibTeX
@misc{dcbeed8939525d,
  title = {AnchorRM: Parallel Intra-Batch State Reconstruction with Anchor-Based Residual Memory for Temporal Graph Neural Networks — arXiv:2610.27558},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27558},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_beed8939525d; sha256 f527d0b1a9aabd5e8d8e1d52bcae7ef5d9e49c82e77eea7aa1314cc9f9b2f153},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27558. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Memory-based temporal graph neural networks (TGN) rely on recurrent node memories to capture evolving interaction histories. However, temporal mini-batching introduces a trade-off between computational efficiency and temporal fidelity: when a node appears multiple times within the same batch, later interactions are evaluated using stale pre-batch memory because the intermediate memory updates have not yet been committed. This problem becomes more severe as temporal batch size increases. To overcome this challenge, we propose AnchorRM, an anchor-based residual memory mechanism that reconstructs event-specific intra-batch node states without executing sequential recurrent updates. AnchorRM treats the last committed node memory at the beginning of each batch as a pre-batch fixed anchor and uses causally preceding same-batch interactions to infer the missing state evolution relative to that anchor. The learned residual then calibrates the anchor to reconstruct an event-specific node memory for each interaction. Because each event-specific residual is predicted directly from the fixed anchor and its causal history, reconstructed states do not depend on previously reconstructed states and can therefore be computed in parallel within the batch while preserving temporal causality. Experiments across four temporal graph datasets and three memory-based backbones demonstrate that AnchorRM achieves an average 6.16x training speedup (up to 10.05x) and 28.67x batch scaling (up to 40x). These results demonstrate that AnchorRM substantially improves the scalability and training efficiency of memory-based temporal graph learning while maintaining competitive predictive performance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.27558 — 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 2026-10-21T07:05:43.572Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).