Search Results for author:
Found 14 papers, 9 papers with code
Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis
This paper constructs a large-scale, unified dataset of traffic accident records from official reports of various states in the US, totaling 9 million records, accompanied by road networks and traffic volume reports.
Boosting Multitask Learning on Graphs through Higher-Order Task Affinities
Lastly, we provide a theoretical analysis to show that under a planted block model of tasks on graphs, our affinity scores can provably separate tasks into groups.
Noise Stability Optimization for Flat Minima with Tight Rates
It leads to a 17. 7% (and 12. 8%) reduction in the trace (and largest eigenvalue) of the Hessian matrix of the loss surface.
Identification of Negative Transfers in Multitask Learning Using Surrogate Models
This problem is computationally challenging since the number of subsets grows exponentially with the number of source tasks; efficient heuristics for subset selection do not always capture the relationship between task subsets and multitask learning performances.
Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusion
Graph neural networks are widely used tools for graph prediction tasks.
Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees
We study the generalization properties of fine-tuning to understand the problem of overfitting, which has often been observed (e. g., when the target dataset is small or when the training labels are noisy).
Improved Group Robustness via Classifier Retraining on Independent Splits
Given a limited amount of group labels at training time, Just Train Twice (Liu et al., 2021), or JTT in short, is a two-stage method that infers a pseudo group label for every unlabeled example first, then applies group DRO based on the inferred group labels.
Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations
As ERM models can be good spurious attribute predictors, CNC works by (1) using a trained ERM model's outputs to identify samples with the same class but dissimilar spurious features, and (2) training a robust model with contrastive learning to learn similar representations for same-class samples.
Improved Regularization and Robustness for Fine-tuning in Neural Networks
We present a PAC-Bayes generalization bound that depends on the distance traveled in each layer during fine-tuning and the noise stability of the fine-tuned model.
Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers
Intuitively, the transfer effect from one task to another task depends on dataset shifts such as sample sizes and covariance matrices.
Learning Over-Parametrized Two-Layer ReLU Neural Networks beyond NTK
We consider the dynamic of gradient descent for learning a two-layer neural network.
Understanding and Improving Information Transfer in Multi-Task Learning
We investigate multi-task learning approaches that use a shared feature representation for all tasks.
On the Generalization Effects of Linear Transformations in Data Augmentation
We validate our proposed scheme on image and text datasets.
Recovery Guarantees for Quadratic Tensors with Sparse Observations
We consider the tensor completion problem of predicting the missing entries of a tensor.
