---
title: "Cause-Effect Driven Optimization for Robust Medical Visual Question Answering with Language Biases"
authors:
  - "Huanjia Zhu"
  - "Yishu Liu"
  - "Xiaozhao Fang"
  - "Guangming Lu"
  - "Bingzhi Chen"
doi: "10.24963/ijcai.2025/280"
url: "https://ijcai.org/proceedings/2025/280"
pdf: "https://ijcai.org/proceedings/2025/0280.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "2512-2520"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Biomedical image analysis"
  - "Computer Vision: CV: Multimodal learning"
  - "Computer Vision: CV: Vision, language and reasoning"
---

# Cause-Effect Driven Optimization for Robust Medical Visual Question Answering with Language Biases

Huanjia Zhu, Yishu Liu, Xiaozhao Fang, Guangming Lu, Bingzhi Chen

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 2512-2520. DOI: [10.24963/ijcai.2025/280](https://doi.org/10.24963/ijcai.2025/280)

## Abstract

Existing Medical Visual Question Answering (Med-VQA) models often suffer from language biases, where spurious correlations between question types and answer categories are inadvertently established.
To address these issues, we propose a novel Cause-Effect Driven Optimization framework called CEDO, that incorporates three well-established mechanisms, i.e., Modality-driven Heterogeneous Optimization (MHO), Gradient-guided Modality Synergy (GMS), and Distribution-adapted Loss Rescaling (DLR), for comprehensively mitigating language biases from both causal and effectual perspectives.
Specifically, MHO employs adaptive learning rates for specific modalities to achieve heterogeneous optimization, thus enhancing robust reasoning capabilities. 
Additionally, GMS leverages the Pareto optimization method to foster synergistic interactions between modalities and enforce gradient orthogonality to eliminate bias updates, thereby mitigating language biases from the effect side, i.e., shortcut bias. Furthermore, DLR is designed to assign adaptive weights to individual losses to ensure balanced learning across all answer categories, effectively alleviating language biases from the cause side, i.e., imbalance biases within datasets. Extensive experiments on multiple traditional and bias-sensitive benchmarks consistently demonstrate the robustness of CEDO over state-of-the-art competitors.