Asia
FederatedTransformer: Multi-PartyVertical FederatedLearningonPracticalFuzzilyLinkedData
Federated Learning (FL) is an evolving paradigm that enables multiple parties to collaboratively train models without sharing raw data.
Quadrature-based features for kernel approximation
Marina Munkhoeva, Yermek Kapushev, Evgeny Burnaev, Ivan Oseledets
Neural Information Processing Systems http://nips.cc/
Learning Attractor Dynamics for Generative Memory
Yan Wu, Gregory Wayne, Karol Gregor, Timothy Lillicrap
These mechanisms typically retrieve items in a single step and are fixed after training.
A Graph Theoretic Additive Approximation of Optimal Transport
Nathaniel Lahn, Deepika Mulchandani, Sharath Raghvendra
Neural Information Processing Systems http://nips.cc/
Paraphrasing Complex Network: Network Compression via Factor Transfer
Jangho Kim, Seonguk Park, Nojun Kwak
Among themodel compression methods, a method calledknowledge transferis to train a student network with a stronger teacher network.