Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answering

Pascal Tilli, Ngoc Thang Vu


Abstract
Explainable artificial intelligence (XAI) aims to make machine learning models more transparent. While many approaches focus on generating explanations post-hoc, interpretable approaches, which generate the explanations intrinsically alongside the predictions, are relatively rare. In this work, we integrate different discrete subset sampling methods into a graph-based visual question answering system to compare their effectiveness in generating interpretable explanatory subgraphs intrinsically. We evaluate the methods on the dataset and show that the integrated methods effectively mitigate the performance trade-off between interpretability and answer accuracy, while also achieving strong co-occurrences between answer and question tokens. Furthermore, we conduct a human evaluation to assess the interpretability of the generated subgraphs using a comparative setting with the extended Bradley-Terry model, showing that the answer and question token co-occurrence metrics strongly correlate with human preferences. Our source code is publicly available.
Anthology ID:
2025.coling-main.167
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2445–2455
Language:
URL:
https://aclanthology.org/2025.coling-main.167/
DOI:
Bibkey:
Cite (ACL):
Pascal Tilli and Ngoc Thang Vu. 2025. Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answering. In Proceedings of the 31st International Conference on Computational Linguistics, pages 2445–2455, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Discrete Subgraph Sampling for Interpretable Graph based Visual Question Answering (Tilli & Vu, COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.167.pdf