analiza aiqbench
EdgeReMIND addresses a critical scalability bottleneck in temporal graph learning by offering the first relation-aware method capable of running on the largest TGB 2.0 datasets without memory or time budget failures. Its linear memorization architecture achieves state-of-the-art performance on six of eight benchmark datasets, establishing a new practical baseline for production-scale link prediction tasks.
EdgeReMIND: A Scalable, Top-Ranked Memorization Baseline for Temporal Multi-Relational Link Prediction
arXiv:2609.17916v1 Announce Type: new Abstract: 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.
Abstract: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.
22 pages, 6 figures, 13 tables. Accepted at the Fifth Learning on Graphs Conference (LoG 2026), Proceedings Track. Code: this https URL
Machine Learning (cs.LG)
arXiv:2609.17916 [cs.LG]
(or arXiv:2609.17916v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.17916 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 226 cuvinte
Subiecte conexe
Scalable Multi-GPU Simulation of 3D Multicellular Growth with RNN-Based Workload Balancing
arXiv · 27 aug. 2026
Differentiable latent structure discovery for interpretable forecasting in clinical time series
arXiv · 21 iul. 2026
[AINews] The Future of Latent Space
Latent Space · 25 sept. 2026
[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · 13 oct. 2026