Showing 2023Show all
2 papers · 1 filter
cs.LG2023
Entropy Aware Training for Fast and Accurate Distributed GNN
Dhruv Deshmukh, Gagan Raj Gupta, Manisha Chawla +2
Several distributed frameworks have been developed to scale Graph Neural Networks (GNNs) on billion-size graphs. On several benchmarks, we observe that the graph partitions generat…
cs.LG2023
PFSL: Personalized & Fair Split Learning with Data & Label Privacy for thin clients
Manas Wadhwa, Gagan Raj Gupta, Ashutosh Sahu +2
The traditional framework of federated learning (FL) requires each client to re-train their models in every iteration, making it infeasible for resource-constrained mobile devices…