Machine Learning

SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification

We propose a novel algorithm that focuses on the less studied relationship between the unlabeled data. Our algorithm achieves state-of-the-art performance on standard benchmarks

Learning with Less Labeling (LwLL)

We propose a novel algorithm for semi-supervised classification that achieves state-of-the-art performance on standard benchmarks and outperform previous works on transfer setting by a large margin.

PyTorch: Exponential Moving Average (EMA) Example

This tutorial shows how to correctly implement EMA for PyTorch

Trust in Multi-Party Human-Robot Interaction

We designed and evaluated a novel framework for robot mediation of a support group

Decentralized Federated Multi-Task Learning and System Design

We designed a decentralized multi-task learning framework and a novel optimization algorithm to collaboratively train models over distributed devices by only sharing their gradient periodically