Search Results for author:
Found 3 papers, 1 papers with code
Simulation of Graph Algorithms with Looped Transformers
The architecture we use is a looped transformer with extra attention heads that interact with the graph.
Local Graph Clustering with Noisy Labels
We provide sufficient conditions on the label noise under which, with high probability, using diffusion in the weighted graph yields a more accurate recovery of the target cluster.
Mitigating Data Heterogeneity in Federated Learning with Data Augmentation
Federated Learning (FL) is a prominent framework that enables training a centralized model while securing user privacy by fusing local, decentralized models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
