AI Paper Atlas

Research map / Learning theory and algorithms / Optimal transport

AvAtar: Learning to Align via Active Optimal Transport

Qi Yu, Ruizhong Qiu, Zhichen Zeng, My T. Thai, huan liu, Hanghang Tong

ICML 2026 · Learning theory and algorithms › Optimal transport · approach: Neural optimal transport · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
weight each pair's query impact by the transport plan row as a posterior (ablation)AvAtar-L2 · Douban (PARROT)MRR: 0.669 -> 0.837Improved
weight each pair's query impact by the transport plan row as a posterior (ablation)AvAtar-Consist · Phone-Email (PARROT)MRR: 0.506 -> 0.630Improved
use sparse matrix operations in conjugate gradient instead of dense (ablation)AvAtar-L2 · Douban (PARROT)MRR: 0.839 -> 0.837No clear effect
use sparse matrix operations in conjugate gradient instead of dense (ablation)AvAtar-Consist · ACM-DBLP-A (PARROT)query time (s): 1010 -> 118Improved
use gradient-propagated entropy utility instead of applying entropy directly to Tactive query for GOT · image-text retrieval and groundingRecall@1: up to 2.6% in Recall@1Improved
use AvAtar-L2/Consist instead of best baseline query strategiesOT-based network alignment · Phone-Email, ACM-DBLP-P, Douban, ACM-DBLP-AMRR: up to 2.8% in MRRImproved
use network-specific GibbsMatchings/TopMatchings instead of generic EntropyOT-based network alignment · Network alignment with PARROT and JOENAMRR: JOENA Phone-Email round 10: 0.778 -> 0.661 (GibbsMatchings)Hurt
use consistency utility instead of L2 utilityAvAtar · plain networks (Phone-Email, ACM-DBLP-P)MRR: up to 0.6% improvement on plain networks; L2 better on attributedMixed
use entropy utility instead of L2 utilityAvAtar · image-text retrieval and groundingRecall@1: ImageNet-C GOT-W round 10: 0.505 -> 0.509Mixed
vary query batch size nb (ablation)AvAtar-L2 · Phone-Email and Douban (PARROT)MRRNo clear effect
increase query budget k (ablation)AvAtar · all tasksMRR / Recall@1: Phone-Email PARROT: 0.539 -> 0.629 (round 5 -> 10)Improved
use AvAtar instead of TopMatchings/GibbsMatchings for efficiencyactive network alignment · Phone-Email and Douban (PARROT)query time and MRR: up to 25x speed-up; up to 8.1% MRRImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy