English
Related papers

Related papers: Baseline Computation for Attribution Methods Based…

200 papers

Current methods for the interpretability of discriminative deep neural networks commonly rely on the model's input-gradients, i.e., the gradients of the output logits w.r.t. the inputs. The common assumption is that these input-gradients…

Machine Learning · Computer Science 2021-03-04 Suraj Srinivas , Francois Fleuret

The black-box nature of Deep Neural Networks (DNNs) severely hinders its performance improvement and application in specific scenes. In recent years, class activation mapping-based method has been widely used to interpret the internal…

Computer Vision and Pattern Recognition · Computer Science 2022-07-11 Chunyan Zeng , Kang Yan , Zhifeng Wang , Yan Yu , Shiyan Xia , Nan Zhao

This paper introduces a generic method which enables to use conventional deep neural networks as end-to-end one-class classifiers. The method is based on splitting given data from one class into two subsets. In one-class classification,…

Machine Learning · Computer Science 2019-09-17 Patrick Schlachter , Yiwen Liao , Bin Yang

The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the…

Machine Learning · Computer Science 2022-11-15 Tomasz Korbak , Hady Elsahar , Germán Kruszewski , Marc Dymetman

The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the previous tokens. These probabilities encode the distributional structure that the model…

Computation and Language · Computer Science 2026-05-22 Shilpika Shilpika , Carlo Graziani , Bethany Lusch , Venkatram Vishwanath , Michael E. Papka

The rapid development in data collecting devices and computation platforms produces an emerging number of agents, each equipped with a unique data modality over a particular population of subjects. While the predictive performance of an…

Machine Learning · Computer Science 2020-10-22 Jiaying Zhou , Xun Xian , Na Li , Jie Ding

The Numerical Recipes series of books are a useful resource, but all the algorithms they contain cannot be used within open-source projects. In this paper we develop drop-in alternatives to the two algorithms they present for cubic spline…

Mathematical Software · Computer Science 2020-01-28 Haysn Hornbeck

Feature attribution methods aim to improve the transparency of deep neural networks by identifying the input features that influence a model's decision. Pixel-based heatmaps have become the standard for attributing features to…

Machine Learning · Statistics 2025-06-06 Gabriel Kasmi , Amandine Brunetto , Thomas Fel , Jayneel Parekh

In this paper we address imbalanced binary classification (IBC) tasks. Applying resampling strategies to balance the class distribution of training instances is a common approach to tackle these problems. Many state-of-the-art methods find…

Machine Learning · Computer Science 2022-05-31 Vitor Cerqueira , Luis Torgo , Paula Branco , Colin Bellinger

Despite a sea of interpretability methods that can produce plausible explanations, the field has also empirically seen many failure cases of such methods. In light of these results, it remains unclear for practitioners how to use these…

Machine Learning · Computer Science 2024-01-09 Blair Bilodeau , Natasha Jaques , Pang Wei Koh , Been Kim

We introduce a general and simple structural design called Multiplicative Integration (MI) to improve recurrent neural networks (RNNs). MI changes the way in which information from difference sources flows and is integrated in the…

Machine Learning · Computer Science 2016-11-15 Yuhuai Wu , Saizheng Zhang , Ying Zhang , Yoshua Bengio , Ruslan Salakhutdinov

Deep neural networks for image classification only learn to map in-distribution inputs to their corresponding ground truth labels in training without differentiating out-of-distribution samples from in-distribution ones. This results from…

Machine Learning · Computer Science 2023-08-29 Zhilin Zhao , Longbing Cao , Kun-Yu Lin

Generative artificial intelligence offers a promising avenue for materials discovery, yet its advantages over traditional methods remain unclear. In this work, we introduce and benchmark two baseline approaches - random enumeration of…

Materials Science · Physics 2025-07-02 Nathan J. Szymanski , Christopher J. Bartel

Integrated Gradients (IG) is a commonly used feature attribution method for deep neural networks. While IG has many desirable properties, the method often produces spurious/noisy pixel attributions in regions that are not related to the…

Computer Vision and Pattern Recognition · Computer Science 2021-06-21 Andrei Kapishnikov , Subhashini Venugopalan , Besim Avci , Ben Wedin , Michael Terry , Tolga Bolukbasi

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of tasks, but their deployment is often constrained by substantial memory footprints and computational costs. While prior work has achieved…

Machine Learning · Computer Science 2026-02-04 Jiangyong Yu , Xiaomeng Han , Xing Hu , Chen Xu , Zhe Jiang , Dawei Yang

Conventional deep models predict a test sample with a single forward propagation, which, however, may not be sufficient for predicting hard-classified samples. On the contrary, we human beings may need to carefully check the sample many…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Shuaicheng Niu , Jiaxiang Wu , Yifan Zhang , Guanghui Xu , Haokun Li , Peilin Zhao , Junzhou Huang , Yaowei Wang , Mingkui Tan

Given a set of snapshots from a temporal network we develop, analyze, and experimentally validate a so-called network interpolation scheme. Our method allows us to build a plausible, albeit random, sequence of graphs that transition between…

Social and Information Networks · Computer Science 2021-02-22 Thomas Reeves , Anil Damle , Austin R. Benson

Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but it…

Machine Learning · Computer Science 2026-01-29 Kurt Butler , Guanchao Feng , Petar Djuric

With the aim of matching a pair of instances from two different modalities, cross modality mapping has attracted growing attention in the computer vision community. Existing methods usually formulate the mapping function as the similarity…

Computer Vision and Pattern Recognition · Computer Science 2021-03-01 Zun Li , Congyan Lang , Liqian Liang , Tao Wang , Songhe Feng , Jun Wu , Yidong Li

This paper provides a theoretical framework on the solution of feedforward ReLU networks for interpolations, in terms of what is called an interpolation matrix, which is the summary, extension and generalization of our three preceding…

Machine Learning · Computer Science 2022-12-13 Changcun Huang