Sotabase

Career

· Assistant Professor, Dartmouth College2022–
· Postdoctoral Researcher, UC Berkeley Electrical Engineering & Computer Sciences (EECS)2019–2022
· PhD in Electrical and Computer Engineering, Carnegie Mellon University2013–2019
· B.S. in Electrical Engineering, Tsinghua University2009–2013

Publications (62)

FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
1,325
cited
Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2017
520
cited
Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
Industrial Conference on Data Mining · 2021
295
cited
Neurotoxin: Durable Backdoors in Federated Learning
International Conference on Machine Learning · 2022
187
cited
Improving Semi-supervised Federated Learning by Reducing the Gradient Diversity of Models
2021 IEEE International Conference on Big Data (Big Data) · 2021
104
cited
Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering
IEEE Transactions on Image Processing · 2019
82
cited
FoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds
arXiv.org · 2017
80
cited
Coded Distributed Computing for Inverse Problems
Neural Information Processing Systems · 2017
68
cited
Computing Linear Transformations With Unreliable Components
IEEE Transactions on Information Theory · 2015
61
cited
Augmentations in Graph Contrastive Learning: Current Methodological Flaws & Towards Better Practices
The Web Conference · 2021
58
cited
Proactive Caching for Vehicular Multi-View 3D Video Streaming via Deep Reinforcement Learning
IEEE Transactions on Wireless Communications · 2019
52
cited
Boundary thickness and robustness in learning models
Neural Information Processing Systems · 2020
47
cited
Taxonomizing local versus global structure in neural network loss landscapes
Neural Information Processing Systems · 2021
43
cited
An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation
2018 IEEE International Conference on Big Data (Big Data) · 2018
39
cited
Benchmarking Semi-supervised Federated Learning
arXiv.org · 2020
39
cited
Coded Elastic Computing
International Symposium on Information Theory · 2018
33
cited
Neighbors Do Help: Deeply Exploiting Local Structures of Point Clouds
arXiv.org · 2017
33
cited
Test Accuracy vs. Generalization Gap: Model Selection in NLP without Accessing Training or Testing Data
Knowledge Discovery and Data Mining · 2023
29
cited
When are ensembles really effective?
Neural Information Processing Systems · 2023
24
cited
Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data
arXiv.org · 2022
20
cited
Sotabase
Yaoqing Yang | Researcher Profile | Sotabase | Sotabase