paper-with-me

홈 › Papers

HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks

2021-02-04 · YuanYuan Chen, Boyang Li, Han Yu, Pengcheng Wu, Chunyan Miao

The behaviors of deep neural networks (DNNs) are notoriously resistant to human interpretations. In this paper, we propose Hypergradient Data Relevance Analysis, or HYDRA, which interprets the predictions made by DNNs as effects of their training data. Existing approaches generally estimate data contributions around the final model parameters and ignore how the training data shape the optimization trajectory. By unrolling the hypergradient of test loss w.r.t. the weights of training data, HYDRA assesses the contribution of training data toward test data points throughout the training trajectory. In order to accelerate computation, we remove the Hessian from the calculation and prove that, under moderate conditions, the approximation error is bounded. Corroborating this theoretical claim, empirical results indicate the error is indeed small. In addition, we quantitatively demonstrate that HYDRA outperforms influence functions in accurately estimating data contribution and detecting noisy data labels. The source code is available at https://github.com/cyyever/aaai_hydra_8686.

📄 PDF Abstract BibTeX arXiv:2102.02515

Code (1)

cyyever/aaai_hydra 공식 구현 pytorch

Tasks

Rolling Shutter Correction

Similar Papers 제목 키워드 기반

Understanding the Generalization of Bilevel Programming in Hyperparameter Optimization: A Tale of Bias-Variance Decomposition

2026-02-20 · Yubo Zhou, Jun Shu, Junmin Liu, Deyu Meng arxiv

Gradient-based hyperparameter optimization (HPO) have emerged recently, leveraging bilevel programming techniques to optimize hyperparameter by estimating hypergradient w.r.t. validation loss. Nevertheless, previous theo…

Hyperparameter OptimizationFew-Shot Learning

Glocal Hypergradient Estimation with Koopman Operator

2024-02-05 · Ryuichiro Hataya, Yoshinobu Kawahara

Gradient-based hyperparameter optimization methods update hyperparameters using hypergradients, gradients of a meta criterion with respect to hyperparameters. Previous research used two distinct update strategies: optimi…

Hyperparameter Optimization

Convergence Properties of Stochastic Hypergradients

2020-11-13 · Riccardo Grazzi, Massimiliano Pontil, Saverio Salzo

Bilevel optimization problems are receiving increasing attention in machine learning as they provide a natural framework for hyperparameter optimization and meta-learning. A key step to tackle these problems is the effic…

Bilevel OptimizationHyperparameter OptimizationMeta-Learning

GlycoNMR: Dataset and benchmarks for NMR chemical shift prediction of carbohydrates with graph neural networks

2023-11-28 · Zizhang Chen, Ryan Paul Badman, Lachele Foley, Robert Woods 외

Molecular representation learning (MRL) is a powerful tool for bridging the gap between machine learning and chemical sciences, as it converts molecules into numerical representations while preserving their chemical feat…

Drug Designmolecular representationProperty PredictionRepresentation Learning

Differentiable Self-Adaptive Learning Rate

2022-10-19 · Bozhou Chen, Hongzhi Wang, Chenmin Ba

Learning rate adaptation is a popular topic in machine learning. Gradient Descent trains neural nerwork with a fixed learning rate. Learning rate adaptation is proposed to accelerate the training process through adjustin…