🎉 We are proud to congratulate relAI PhD student Nil Ayday and her supervisor, relAI Fellow Debarghya Ghoshdastidar! Their paper, “Gaussian Process Limit Reveals Structural Benefits of Graph Transformers,” received the Best Paper – Honorable Mention Award at the 42nd Conference on Uncertainty in Artificial Intelligence (UAI 2026)!
In this work, the authors derive the neural network Gaussian process (NNGP) limits of graph transformers, demonstrating the structural advantages of attention mechanisms compared to standard graph convolutions.
More information: https://lnkd.in/p/dnhkmydr
