Optimal Transport (OT) has recently emerged as a central tool in data sciences to compare
in a geometrically faithful way point clouds and more generally probability distributions. The …

This paper proposes a simple self-supervised approach for learning a representation for
visual correspondence from raw video. We cast correspondence as prediction of links in a …

Optimal transport has recently been reintroduced to the machine learning community thanks
in part to novel efficient optimization procedures allowing for medium to large scale …

Deep generative models have achieved conspicuous progress in realistic image synthesis
with multifarious conditional inputs, while generating diverse yet high-fidelity images …

Cross-domain alignment between two sets of entities (eg, objects in an image, words in a
sentence) is fundamental to both computer vision and natural language processing. Existing …

This work presents a two-stage neural architecture for learning and refining structural
correspondences between graphs. First, we use localized node embeddings computed by a …

With the increasing attention to large vision-language models such as CLIP, there has been
a significant amount of effort dedicated to building efficient prompts. Unlike conventional …

Most graph kernels are an instance of the class of R-Convolution kernels, which measure
the similarity of objects by comparing their substructures. Despite their empirical success …

Disparate impact has raised serious concerns in machine learning applications and its
societal impacts. In response to the need of mitigating discrimination, fairness has been …

We propose a scalable Gromov-Wasserstein learning (S-GWL) method and establish a
novel and theoretically-supported paradigm for large-scale graph analysis. The proposed …