# AvAtar: Learning to Align via Active Optimal Transport

arXiv: https://arxiv.org/abs/2605.24395 · HTML: https://mlsanity.com/paper/2605.24395/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 65 references that are in the map.
- First posted on arXiv 23 May 2026.

## Builds on (most cited first, 30 of 40)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [A Survey of Deep Active Learning](https://mlsanity.com/paper/2009.00236/) (2020)
- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration](https://mlsanity.com/paper/2110.14076/) (2021)
- [Neural Optimal Transport](https://mlsanity.com/paper/2201.12220/) (2022)
- [Vision-Language Pre-training: Basics, Recent Advances, and Future Trends](https://mlsanity.com/paper/2210.09263/) (2022)
- [Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions](https://mlsanity.com/paper/2209.03430/) (2022)
- [Graph Optimal Transport for Cross-Domain Alignment](https://mlsanity.com/paper/2006.14744/) (2020)
- [GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer](https://mlsanity.com/paper/2308.03768/) (2023)
- [Discrete-state Continuous-time Diffusion for Graph Generation](https://mlsanity.com/paper/2405.11416/) (2024)
- [Rotation-Invariant Transformer for Point Cloud Matching](https://mlsanity.com/paper/2303.08231/) (2023)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders](https://mlsanity.com/paper/2305.18612/) (2023)
- [Class-Imbalanced Graph Learning without Class Rebalancing](https://mlsanity.com/paper/2308.14181/) (2023)
- [In Defense of Core-set: A Density-aware Core-set Selection for Active Learning](https://mlsanity.com/paper/2206.04838/) (2022)
- [Ensuring User-side Fairness in Dynamic Recommender Systems](https://mlsanity.com/paper/2308.15651/) (2023)
- [Hierarchical Multi-Marginal Optimal Transport for Network Alignment](https://mlsanity.com/paper/2310.04470/) (2023)
- [Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics](https://mlsanity.com/paper/2505.12709/) (2025)
- [Graph4MM: Weaving Multimodal Learning with Structural Information](https://mlsanity.com/paper/2510.16990/) (2025)
- [Robust Attributed Graph Alignment via Joint Structure Learning and Optimal Transport](https://mlsanity.com/paper/2301.12721/) (2023)
- [Gradient Compressed Sensing: A Query-Efficient Gradient Estimator for High-Dimensional Zeroth-Order Optimization](https://mlsanity.com/paper/2405.16805/) (2024)
- [WAPITI: A Watermark for Finetuned Open-Source LLMs](https://mlsanity.com/paper/2410.06467/) (2024)
- [TUCKET: A Tensor Time Series Data Structure for Efficient and Accurate Factor Analysis over Time Ranges](https://mlsanity.com/paper/2501.06647/) (2025)
- [Joint Optimal Transport and Embedding for Network Alignment](https://mlsanity.com/paper/2502.19334/) (2025)
- [PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment](https://mlsanity.com/paper/2505.21366/) (2025)
- [Hierarchical LoRA MoE for Efficient CTR Model Scaling](https://mlsanity.com/paper/2510.10432/) (2025)

## Built on by (most cited first, 1 of 1)

- [Scalable Optimal Transport Algorithm for Network Alignment](https://mlsanity.com/paper/2607.11952/) (2026)

## Abstract (arXiv)

Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration. Recent works increasingly leverage optimal transport (OT) for distributional alignment, whose effectiveness largely depends on sparse supervision that is hard or costly to obtain in practice. Existing works, however, largely overlook how to actively acquire high-quality supervision to improve their alignment performance under OT frameworks. In this paper, we propose a principled active alignment framework for optimal transport alignment called AvAtar. We quantify the informativeness of a candidate by measuring its gradient-based impact on the global alignment result, computed as the gradient propagation from the global alignment result to all possible supervisions of the candidate through the entropy-regularized OT formulation. While differentiating through OT is challenging given its constrained nature, we leverage the adjoint-state method to reformulate the computation to a linear system solvable by the conjugate gradient method with linear complexity and guaranteed convergence. By encoding the global alignment result via effective utility functions, AvAtar is applicable to general alignment problems under the OT framework. Extensive experiments on three representative alignment tasks demonstrate the effectiveness, scalability, and generalizability of the proposed AvAtar.