Bridging OOD Detection and Generalization: A Graph-Theoretic View

Authors: Han Wang, Sharon Li

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results showcase competitive performance in comparison to existing methods, thereby validating our theoretical underpinnings.
Researcher Affiliation Academia Han Wang Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign hanw14@illinois.edu Yixuan Li Department of Computer Sciences University of Wisconsin-Madison sharonli@cs.wisc.edu
Pseudocode No The paper describes algorithms and methods through text and mathematical equations but does not present a clearly labeled 'Pseudocode' or 'Algorithm' block.
Open Source Code Yes Code is publicly available at https://github.com/deeplearning-wisc/graph-spectral-ood.
Open Datasets Yes Following the setup of [5], we employ CIFAR-10 [14] as Pin and CIFAR-10-C [15] with Gaussian additive noise as the Pcovariate out . For Psemantic out , we leverage SVHN [16], LSUN [17], Places365 [18], Textures [19].
Dataset Splits Yes For splitting training/validation, we use 30% for validation and the remaining for training.
Hardware Specification Yes We conduct all the experiments in Pytorch, using NVIDIA GeForce RTX 2080Ti.
Software Dependencies No The paper mentions 'Pytorch' but does not specify a version number for it or any other software dependencies, which is required for a reproducible description.
Experiment Setup Yes We use stochastic gradient descent with Nesterov momentum [22], with weight decay 0.0005 and momentum 0.09. We train the network with the loss function in Eq. 6 for 1000 epochs. The learning rate is 0.03 and the batch size is 512. We fine-tune for 20 epochs with a learning rate of 0.005 and batch size of 512.