Representer Point Selection for Explaining Deep Neural Networks

Authors: Chih-Kuan Yeh, Joon Kim, Ian En-Hsu Yen, Pradeep K. Ravikumar

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We perform a number of experiments with multiple datasets and evaluate our method s performance and compare with that of the influence functions.
Researcher Affiliation Academia Chih-Kuan Yeh Joon Sik Kim Ian E.H. Yen Pradeep Ravikumar Machine Learning Department Carnegie Mellon University Pittsburgh, PA 15213 {cjyeh, joonsikk, eyan, pradeepr}@cs.cmu.edu
Pseudocode No The paper describes the steps of the algorithm in prose, but does not provide a formal pseudocode block or algorithm listing.
Open Source Code Yes Source code available at github.com/chihkuanyeh/Representer_Point_Selection.
Open Datasets Yes We perform a number of experiments with multiple datasets and evaluate our method s performance... on CIFAR-10 dataset [15]... in Animals with Attributes (Aw A) dataset [18].
Dataset Splits No The paper mentions training data and test data, but does not explicitly provide details about a separate validation split, such as percentages or counts, or cross-validation setup.
Hardware Specification No The paper does not specify any particular hardware components like CPU models, GPU models, or memory specifications used for the experiments.
Software Dependencies No The paper mentions using specific models like VGG-16 and Resnet-50, and optimization methods like SGD and LBFGS, but does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes The L2 weight decay is set to 1e-2 for all methods for fair comparison. We first solve (4) with loss Lsoftmax(Φ(xi, Θ), Φ(xi, Θgiven)) for λ = 0.001, and then calculate Φ(xt, Θ ) = Pn i=1 k(xt, xi, αi) as in (2) for all train and test points.