MA4a.3

MrsFormer: Transformer with Multiresolution-head Attention

Session:
MA4a: Generative AI for Graphs Lecture
Track:
Adaptive Systems, Machine Learning, and Data Analytics
Location:
Room 4
Presentation Time:
Mon, 26 Oct, 09:05 - 09:30 PT (UTC -7)
Session Co-Chairs:
Santiago Segarra, Rice University, United States and Nicolas Zilberstein, Rice University, United States
Presentation
Discussion
Resources
No resources available.
Session MA4a
MA4a.1: Nonlinear Laplacians Improve Signed-Directed Graph Learning
Ali Parviz, Gal Mishne, Alex Cloninger, UC San Diego, United States; Yuichi Yoshida, National Institute of Informatics, Japan
MA4a.2: Learn to Explore: Meta NAS via Bayesian Optimization Guided Graph Generation
Zijun Sun, Yanning Shen, University of California, Irvine, United States
MA4a.3: MrsFormer: Transformer with Multiresolution-head Attention
MA4a.4: DAG-PnP: Plug-and-Play Causal Discovery with Diffusion Priors
Nicolas Zilberstein, Ali Azizpour, Rice University, United States; Gonzalo Mateos, University of Rochester, United States; Santiago Segarra, Rice University, United States
Contacts