Hypergraph Transformer: Weakly-Supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering

Yu-Jung Heo, Eun-Sol Kim, Woo Suk Choi, Byoung-Tak Zhang


Abstract
Knowledge-based visual question answering (QA) aims to answer a question which requires visually-grounded external knowledge beyond image content itself. Answering complex questions that require multi-hop reasoning under weak supervision is considered as a challenging problem since i) no supervision is given to the reasoning process and ii) high-order semantics of multi-hop knowledge facts need to be captured. In this paper, we introduce a concept of hypergraph to encode high-level semantics of a question and a knowledge base, and to learn high-order associations between them. The proposed model, Hypergraph Transformer, constructs a question hypergraph and a query-aware knowledge hypergraph, and infers an answer by encoding inter-associations between two hypergraphs and intra-associations in both hypergraph itself. Extensive experiments on two knowledge-based visual QA and two knowledge-based textual QA demonstrate the effectiveness of our method, especially for multi-hop reasoning problem. Our source code is available at https://github.com/yujungheo/kbvqa-public.
Anthology ID:
2022.acl-long.29
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
373–390
Language:
URL:
https://aclanthology.org/2022.acl-long.29
DOI:
10.18653/v1/2022.acl-long.29
Bibkey:
Cite (ACL):
Yu-Jung Heo, Eun-Sol Kim, Woo Suk Choi, and Byoung-Tak Zhang. 2022. Hypergraph Transformer: Weakly-Supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 373–390, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Hypergraph Transformer: Weakly-Supervised Multi-hop Reasoning for Knowledge-based Visual Question Answering (Heo et al., ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.29.pdf
Software:
 2022.acl-long.29.software.zip
Code
 yujungheo/kbvqa-public
Data
DBpediaVisual Question Answering