Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions: 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9–12, 2025, Proceedings, Part V

Cham : Springer, 2025.

Academic editor: W. Senn, M. Sanguineti, A. Saudargiene, I. Tetko, A. P. Villa, V. Jirsa, Y. Bengio

This book constitutes the refereed proceedings of 34th International Workshops which were held in conjunction with the 34th International Conference on Artificial Neural Networks and Machine Learning, ICANN 2025, held in Kaunas, Lithuania, September 9–12, 2025.
 
The 20 full papers and 8 abstracts included in this workshop volume were carefully reviewed and selected from 42 submissions. They were organized in the following sections: 2nd AI in Drug Discovery (AIDD) Workshop; Special Session: Neural Networks for Graphs and Beyond; Special Session: Neurorobotics;  3rd International Workshop on Reservoir Computing. 

Chapters

Dimension-Augmented Anisotropy in Graph Neural Diffusion

Sycheva T., Beketov M., Smolyar I., , in: Artificial Neural Networks and Machine Learning. ICANN 2025 International Workshops and Special Sessions: 34th International Conference on Artificial Neural Networks, Kaunas, Lithuania, September 9–12, 2025, Proceedings, Part V.: Cham: Springer, 2025. Ch. 4 P. 29–33.

We consider Graph Anisotropic Diffusion (GAD), a recently proposed model of graph neural networks, that can be trained to predict desired properties of the graph by performing learnable diffusion of node features on it. In contrast with similar methods, GAD introduces anisotropy of said diffusion by incorporating filters built from the graph’s Fiedler vector. In ...

Added: September 29, 2025

Keywords: neural networks, reinforcement learning, robotics, deep learning, generative models, graph neural networks, image processing, spiking neural networks, large language models, artificial intelligence, Reservoir computing, machine learning