Timezone: »

 
Poster
Graph Optimal Transport for Cross-Domain Alignment
Liqun Chen · Zhe Gan · Yu Cheng · Linjie Li · Lawrence Carin · Jingjing Liu

Thu Jul 16 07:00 AM -- 07:45 AM & Thu Jul 16 06:00 PM -- 06:45 PM (PDT) @
in Poster Session 42 »

Cross-domain alignment between two sets of entities (e.g., objects in an image, words in a sentence) is fundamental to both computer vision and natural language processing. Existing methods mainly focus on designing advanced attention mechanisms to simulate soft alignment, where no training signals are provided to explicitly encourage alignment. Plus, the learned attention matrices are often dense and difficult to interpret. We propose Graph Optimal Transport (GOT), a principled framework that builds upon recent advances in Optimal Transport (OT). In GOT, cross-domain alignment is formulated as a graph matching problem, by representing entities as a dynamically-constructed graph. Two types of OT distances are considered: (i) Wasserstein distance (WD) for node (entity) matching; and (ii) Gromov-Wasserstein distance (GWD) for edge (structure) matching. Both WD and GWD can be incorporated into existing neural network models, effectively acting as a drop-in regularizer.
The inferred transport plan also yields sparse and self-normalized alignment, enhancing the interpretability of the learned model. Experiments show consistent outperformance of GOT over baselines across a wide range of tasks, including image-text retrieval, visual question answering, image captioning, machine translation, and text summarization.

Keywords: Algorithms · Deep Learning - Algorithms

Author Information

Liqun Chen (Duke University)
Zhe Gan (Microsoft)
Yu Cheng (Microsoft)
Linjie Li (Microsoft)
Lawrence Carin (Duke)
Jingjing Liu (Microsoft)

More from the Same Authors