Towards Counterfactual Fairness-aware Domain Generalization in Changing Environments Publication Date: 8/9/2024 Event: #IJCAI2024 – The 33rd International Joint Conference on Artificial Intelligence, Jeju, South Korea @STAIWorkshop Reference: pp. 4560-4568, 2024 Authors: Yujie Lin, @TianjinUniv1895; Chen Zhao, @Baylor University; Minglai Shao, Tianjin University; @XujiangZhao, NEC Laboratories America, Inc.; Baoluo Meng, @GEResearch; Haifeng Chen, NEC Laboratories America, Inc. Abstract: Recognizing domain generalization as a commonplace challenge in machine learning, data distribution might progressively evolve across a continuum of sequential domains in practical scenarios. While current methodologies primarily concentrate on bolstering model effectiveness within these new domains, they tend to neglect issues of fairness throughout the learning process. In response, we propose an innovative framework known as Disentanglement for Counterfactual Fairness-aware Domain Generalization (DCFDG). This approach adeptly removes domain-specific information and sensitive information from the embedded representation of classification features. To scrutinize the intricate interplay between semantic information, domain-specific information, and sensitive attributes, we systematically partition the exogenous factors into four latent variables. By incorporating fairness regularization, we utilize semantic information exclusively for classification purposes. Empirical validation on synthetic and authentic datasets substantiates the efficacy of our approach, demonstrating elevated accuracy levels while ensuring the preservation of fairness amidst the evolving landscape of continuous domains. Learn more: nec-labs.com/blog/towards-co…

Congratulations

My first student has won the 🏆Best Paper Award with his very first paper! 🎉 Congratulations Han Sanghyeon @Rowhan1029, and a huge thanks to @STAIWorkshop for hosting such an exceptional event in #AIforSustainability at @IJCAIconf

#Highlights from 3rd day official opening, @IJCAIconf: @STAIWorkshop, W29: Sustainable Transition with AI. Technical papers, posters, panel, keynote talks on #sustainability, #accountability, #greenwashing, #ClimateCrisis, #actionable & #ResponsibleAI. #AI #IJCAI2024 #IJCAi #STAI

Keep sharing with #IJCAI2024 💪

#workshop full house at the #W29 Sustainable Transition with AI (STAI): Empowering Global and Local Sustainability @STAIWorkshop stai.jeju.ai/ #IJCAI2024 #AIforGood

Buy Verified Binance Account just Contact/24 Hours Reply Skype: UsaSeoOnline Telegram: @Usaseoonline WhatsApp: 1 (734) 210-1509 usaseoonline.com/product/buy… #buyverifiedbinanceaccount @StanfordAILab #IJCAI_STAI2024 #IJCAI2024 @STAIWorkshop

🌟 We’re featuring a Best Paper Award at the STAI Workshop at IJCAI 2024! 📅 Submission Deadline: May 21, 11:59 PM 🔔 Submit here: lnkd.in/g95r-t3G 🔔 More info: stai.jeju.ai #IJCAI2024 #STAIWorkshop #AIResearch #Innovation

🌍 IJCAI 2024 STAI Workshop - Call for Papers Extended! 🚀 🗓️ Deadline: May 21, 2024 Contribute to sustainability in AI! Submit your innovative papers & join us in shaping the future. 🌱 🔗 Details [stai.jeju.ai] #IJCAI2024 #STAIworkshop #AIforGood

🌟 Join us at #IJCAI2024 STAI Workshop! 📅 Don’t miss the Best Paper Awards – a chance to shine among peers! Submit by May 7, 11:59 PM. Engage with top experts. 🏆 #STAIWorkshop #BestPaperAward #AIResearch