# Reasoning Visual Dialog with Sparse Graph Learning and Knowledge Transfer

arXiv: https://arxiv.org/abs/2004.06698 · HTML: https://mlsanity.com/paper/2004.06698/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2020.

## Built on by (most cited first, 6 of 6)

- [The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training](https://mlsanity.com/paper/2205.12502/) (2022)
- [Unified Multimodal Model with Unlikelihood Training for Visual Dialog](https://mlsanity.com/paper/2211.13235/) (2022)
- [mathbbVD-mathbbGR: Boosting mathbbVisual mathbbDialog with Cascaded Spatial-Temporal Multi-Modal mathbbGRaphs](https://mlsanity.com/paper/2310.16590/) (2023)
- [Enabling Harmonious Human-Machine Interaction with Visual-Context Augmented Dialogue System: A Review](https://mlsanity.com/paper/2207.00782/) (2022)
- [IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selection](https://mlsanity.com/paper/2212.00482/) (2022)
- [Adversarial Robustness of Visual Dialog](https://mlsanity.com/paper/2207.02639/) (2022)

## Abstract (arXiv)

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.