4 papers
Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
Abhinav Nippani, Dongyue Li, Haotian Ju +2
We consider the problem of traffic accident analysis on a road network based on road network connections and traffic volume. Previous works have designed various deep-learning meth…
Scalable Multitask Learning Using Gradient-based Estimation of Task Affinity
Dongyue Li, Aneesh Sharma, Hongyang R. Zhang
Multitask learning is a widely used paradigm for training models on diverse tasks, with applications ranging from graph neural networks to language model fine-tuning. Since tasks m…
Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach
Hongyang R. Zhang, Dongyue Li, Haotian Ju
The training of over-parameterized neural networks has received much study in recent literature. An important consideration is the regularization of over-parameterized networks due…
Learning Tree-Structured Composition of Data Augmentation
Dongyue Li, Kailai Chen, Predrag Radivojac +1
Data augmentation is widely used for training a neural network given little labeled data. A common practice of augmentation training is applying a composition of multiple transform…