Metraipolis › archive › dc_e216753fcfa8
EdgeReMIND: A Scalable, Top-Ranked Memorization Baseline for Temporal Multi-Relational Link Prediction — arXiv:2609.17916
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.17916
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T15:04:30.363Z
- SHA-256 of the archived text
e339f34d5f01edb3fbeb0f1fdc91e09827801a4674269ac0a2181a45226ffa6c- Stable URL of this page
https://metraipolis.com/documento/dc_e216753fcfa8
How to cite
EdgeReMIND: A Scalable, Top-Ranked Memorization Baseline for Temporal Multi-Relational Link Prediction — arXiv:2609.17916 — arXiv (en), https://arxiv.org/abs/2609.17916 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e216753fcfa8 (Metraipolis archive dc_e216753fcfa8, sha256 e339f34d5f01edb3fbeb0f1fdc91e09827801a4674269ac0a2181a45226ffa6c)
BibTeX
@misc{dce216753fcfa8,
title = {EdgeReMIND: A Scalable, Top-Ranked Memorization Baseline for Temporal Multi-Relational Link Prediction — arXiv:2609.17916},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.17916},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e216753fcfa8; sha256 e339f34d5f01edb3fbeb0f1fdc91e09827801a4674269ac0a2181a45226ffa6c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.17916. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Temporal link prediction on the Temporal Graph Benchmark 2.0 (TGB 2.0) faces a scalability ceiling: on the benchmark's three largest datasets, every existing embedding method runs out of memory or exceeds the time budget. These large-scale graphs are the ones nearest real deployment scale, so failing on them is a real production limitation. EdgeReMIND sets the highest reported test mean reciprocal rank (MRR) on six of eight TGB 2.0 datasets and is the only relation-aware method that runs on all of them. This linear memorization model, with learned per-relation weights over data-calibrated features, is therefore not merely a fallback where embeddings fail but a practical state-of-the-art baseline across the benchmark. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.17916 — 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 2026-10-15T14:08:19.084Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).