activity
20162022
most citedA critical look at the current train/test split in machine learning

43 citations · 51 across the 4 of their papers we have counts for

collaborators

7 papers

eess.SP20227 cited

Benchmarking Domain Generalization on EEG-based Emotion Recognition

Yan Li, Hao Chen, Jake Zhao +2

Electroencephalography (EEG) based emotion recognition has demonstrated tremendous improvement in recent years. Specifically, numerous domain adaptation (DA) algorithms have been e…

cs.LG2021

Joining datasets via data augmentation in the label space for neural networks

Jake Zhao, Mingfeng Ou, Linji Xue +3

Most, if not all, modern deep learning systems restrict themselves to a single dataset for neural network training and inference. In this article, we are interested in systematic w…

cs.LG202143 cited

A critical look at the current train/test split in machine learning

Jimin Tan, Jianan Yang, Sai Wu +2

The randomized or cross-validated split of training and testing sets has been adopted as the gold standard of machine learning for decades. The establishment of these split protoco…

cs.HC20201 cited

Interactive Rainbow Score: A Visual-centered Multimodal Flute Tutoring System

Daniel Chin, Yian Zhang, Tianyu Zhang +2

Learning to play an instrument is intrinsically multimodal, and we have seen a trend of applying visual and haptic feedback in music games and computer-aided music tutoring systems…

cs.CL2019

Levenshtein Transformer

Jiatao Gu, Changhan Wang, Jake Zhao

Modern neural sequence generation models are built to either generate tokens step-by-step from scratch or (iteratively) modify a sequence of tokens bounded by a fixed length. In th…

cs.LG2018

Retrieval-Augmented Convolutional Neural Networks for Improved Robustness against Adversarial Examples

Jake Zhao, Kyunghyun Cho

We propose a retrieval-augmented convolutional network and propose to train it with local mixup, a novel variant of the recently proposed mixup algorithm. The proposed hybrid archi…