{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dialgraph-sparse-graph-learning-networks-for","title":"Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer","arxiv_id":"2004.06698","date":"2020-04-14","proceeding":"Findings (EMNLP) 2021 11","authors":["Gi-Cheon Kang","Junseok Park","Hwaran Lee","Byoung-Tak Zhang","Jin-Hwa Kim"],"abstract":"Visual dialog is a task of answering a sequence of questions grounded in an image using the previous dialog history as context. In this paper, we study how to address two fundamental challenges for this task: (1) reasoning over underlying semantic structures among dialog rounds and (2) identifying several appropriate answers to the given question. To address these challenges, we propose a Sparse Graph Learning (SGL) method to formulate visual dialog as a graph structure learning task. SGL infers inherently sparse dialog structures by incorporating binary and score edges and leveraging a new structural loss function. Next, we introduce a Knowledge Transfer (KT) method that extracts the answer predictions from the teacher model and uses them as pseudo labels. We propose KT to remedy the shortcomings of single ground-truth labels, which severely limit the ability of a model to obtain multiple reasonable answers. As a result, our proposed model significantly improves reasoning capability compared to baseline methods and outperforms the state-of-the-art approaches on the VisDial v1.0 dataset. The source code is available at https://github.com/gicheonkang/SGLKT-VisDial.","url_abs":"https://arxiv.org/abs/2004.06698v2","url_pdf":"https://arxiv.org/pdf/2004.06698v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dialgraph-sparse-graph-learning-networks-for","repo_url":"https://github.com/gicheonkang/sglkt-visdial","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"graph-learning","task_name":"Graph Learning"},{"task_slug":"graph-structure-learning","task_name":"Graph structure learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"visual-dialogue","task_name":"Visual Dialog"}],"methods":[{"method_slug":"interpretability","method_name":"Interpretability"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2004.06698","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}