Dear Colleagues, We are delighted to invite you to participate in "Explainable Deep Neural Networks for Responsible AI: Post-Hoc and Self-Explaining Approaches (DeepXplain 2025)," a special session at IJCNN 2025 dedicated to innovative methodologies for improving the interpretability of Deep Neural Networks (DNNs) while maintaining high predictive accuracy.
Website: https://deepxplain.github.io/ Contributions This special session aims to foster interdisciplinary collaboration, promote the ethical design of AI systems, and encourage the development of benchmarks and datasets for explainability research. Our goal is to advance both post-hoc and intrinsic interpretability approaches, bridging the gap between the high performance of deep neural networks and their transparency. By doing so, we seek to enhance human trust in these models and mitigate the risks of negative social impacts. Topics of interest include, but are not limited to: - Theoretical advancements in post-hoc explanation methods (e.g., LIME, SHAP, Grad-CAM) for DNNs. - Development of inherently interpretable architectures using self-explaining mechanisms, such as attention-based or saliency-based models, prototype networks, and SENNs (Self-Explaining Neural Networks). - Post-hoc and self-explaining methods for Large Language Models (LLMs). - Application-driven explainability insights, particularly in Natural Language Processing and Computer Vision. - Ethical evaluations of DNN-based AI models with a focus on reducing bias and social impact. - Methods, metrics, and methodologies for improving interpretability and fairness in DNNs. - Ethical discussions about the social impact of non-transparent AI models. - Datasets and benchmarking tools for explainability. - Explainable AI in critical applications: healthcare, governance, misinformation, hate speech, etc. Submission Information We welcome submissions of academic papers (both long and short) across the spectrum of theoretical and practical work, including research ideas, methods, tools, simulations, applications or demonstrations, practical evaluations, position papers, and surveys. Submissions must be written in English, adhere to the IJCNN-2025 formatting guidelines, and be submitted as a single PDF file. Important Dates: - Submission link: https://cmt3.research.microsoft.com/IJCNN2025/ - Submission deadline: January 15, 2025 - Notification date: March 15, 2025 - Camera-ready submission: May 1, 2025 Organizers - Francielle Vargas <https://franciellevargas.github.io/>, University of São Paulo, Brazil - Roseli Romero <https://sites.icmc.usp.br/rafrance/>, University of São Paulo, Brazil - Jackson Trager <https://www.jacksonptrager.com/>, University of Southern California, USA - Edson Prestes <https://www.inf.ufrgs.br/~prestes/site/Welcome.html>, Federal University of Rio Grande do Sul, Brazil [], *Francielle Vargas* PhD in Computer Science University of São Paulo https://franciellevargas.github.io
_______________________________________________ Corpora mailing list -- [email protected] https://list.elra.info/mailman3/postorius/lists/corpora.list.elra.info/ To unsubscribe send an email to [email protected]
