AI 服務暫時不可用，以下為來源正文，待恢復後補全翻譯。
[Submitted on 10 Sep 2026] Title:USPLIT-VQA: U-Shaped Split Learning for Visual Question Answering with Contribution-Aware Weighted Aggregation View a PDF of the paper titled USPLIT-VQA: U-Shaped Split Learning for Visual Question Answering with Contribution-Aware Weighted Aggregation, by Md Khalid Syfullah and Alvi Ataur Khalil View PDF HTML (experimental) Abstract:Visual Question Answering (VQA) systems, jointly interpreting images and natural language queries, hold significant promise across many domains, yet the privacy-sensitive nature of user data creates a fundamental barrier. Centralized training requires access to all data, while federated learning requires each client to host the full model. We propose USPLIT-VQA, a U-shaped split learning framework for privacy-preserving VQA in which each client retains the initial layers and the classification head while the server hosts the computationally heavy intermediate layers, keeping raw inputs and labels on the client device. We further introduce Contribution-Aware Weighted Aggregation (CAWA), a gradientsimilarity-based client scoring mechanism designed to reduce the influence of malicious updates. Experiments on four VQA datasets (VQA-RAD, SLAKE, PathVQA, and VizWiz) with two backbones show accuracy gains over Federated Learning for the Custom model and reduced accuracy for BiomedCLIP under the evaluated fixed split, alongside client memory reductions of up to 5.8X and communication reductions of up to 10.8X. With one malicious client, CAWA reduces the attacker's influence by over 98%, while experiments at higher corruption levels identify its limitations. Reconstruction experiments further show lower inversion quality under the evaluated attacks. Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) Cite as: arXiv:2609.12168 [cs.CV] (or arXiv:2609.12168v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2609.12168 arXiv-issued DOI via DataCite (pending registration) Submission history From: Alvi Ataur Khalil [view email] [v1] Thu, 10 Sep 2026 19:56:27 UTC (299 KB) Full-text links: Access Paper: View a PDF of the paper titled USPLIT-VQA: U-Shaped Split Learning for Visual Question Answering with Contribution-Aware Weighted Aggregation, by Md Khalid Syfullah and Alvi Ataur Khalil View PDF HTML (experimental) TeX Source view license Current browse context: cs.CV new | recent | 2026-09 Change to browse by: cs cs.AI References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)