中文
相关论文

相关论文: On the Robustness of Removal-Based Feature Attribu…

200 篇论文

The use of algorithm-agnostic approaches is an emerging area of research for explaining the contribution of individual features towards the predicted outcome. Whilst there is a focus on explaining the prediction itself, a little has been…

机器学习 · 计算机科学 2022-11-07 Guilherme Dean Pelegrina , Sajid Siraj

Feature attribution analysis is critical for interpreting machine learning models and supporting reliable data-driven decisions. However, feature attribution measures often exhibit stochastic variation: different train--test splits, random…

机器学习 · 统计学 2026-05-15 Lanxin Xiang , Liang Shi , Youhui Ye , Boyu Jiang , Dawei Zhou , Feng Guo

With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted approaches for model interpretability is feature-based…

计算与语言 · 计算机科学 2021-06-10 Muhammad Bilal Zafar , Michele Donini , Dylan Slack , Cédric Archambeau , Sanjiv Das , Krishnaram Kenthapadi

Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…

计算机视觉与模式识别 · 计算机科学 2023-06-27 Levente Halmosi , Mark Jelasity

Adversarial robustness refers to a model's ability to resist perturbation of inputs, while distribution robustness evaluates the performance of the model under data shifts. Although both aim to ensure reliable performance, prior work has…

机器学习 · 计算机科学 2026-01-26 Yipei Wang , Zhaoying Pan , Xiaoqian Wang

Feature attribution methods are popular in interpretable machine learning. These methods compute the attribution of each input feature to represent its importance, but there is no consensus on the definition of "attribution", leading to…

机器学习 · 计算机科学 2021-12-16 Yilun Zhou , Serena Booth , Marco Tulio Ribeiro , Julie Shah

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that…

图像与视频处理 · 电气工程与系统科学 2021-06-14 Mohammad Zalbagi Darestani , Akshay S. Chaudhari , Reinhard Heckel

Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss…

机器学习 · 计算机科学 2023-03-23 Hao Wang , Chen Li , Jinzhe Jiang , Xin Zhang , Yaqian Zhao , Weifeng Gong

Explanation methods for machine learning models tend not to provide any formal guarantees and may not reflect the underlying decision-making process. In this work, we analyze stability as a property for reliable feature attribution methods.…

机器学习 · 计算机科学 2023-10-30 Anton Xue , Rajeev Alur , Eric Wong

Attribution methods can provide powerful insights into the reasons for a classifier's decision. We argue that a key desideratum of an explanation method is its robustness to input hyperparameters which are often randomly set or empirically…

计算机视觉与模式识别 · 计算机科学 2020-04-14 Naman Bansal , Chirag Agarwal , Anh Nguyen

Machine learning methods have significantly improved in their predictive capabilities, but at the same time they are becoming more complex and less transparent. As a result, explainers are often relied on to provide interpretability to…

机器学习 · 计算机科学 2024-04-17 Zulqarnain Khan , Davin Hill , Aria Masoomi , Joshua Bone , Jennifer Dy

As machine learning models become increasingly prevalent in critical decision-making models and systems in fields like finance, healthcare, etc., ensuring their robustness against adversarial attacks and changes in the input data is…

机器学习 · 统计学 2024-08-05 Arun Prakash R , Anwesha Bhattacharyya , Joel Vaughan , Vijayan N. Nair

In recent years, neural networks have demonstrated their remarkable ability to discern intricate patterns and relationships from raw data. However, understanding the inner workings of these black box models remains challenging, yet crucial…

机器学习 · 统计学 2024-04-18 Niklas Koenen , Marvin N. Wright

Predictors are learned using past training data which may contain features that are unavailable at the time of prediction. We develop an approach that is robust against outlying missing features, based on the optimality properties of an…

信号处理 · 电气工程与系统科学 2020-07-15 Xiuming Liu , Dave Zachariah , Petre Stoica

This work tackles an intriguing and fundamental open challenge in representation learning: Given a well-trained deep learning model, can it be reprogrammed to enhance its robustness against adversarial or noisy input perturbations without…

机器学习 · 计算机科学 2024-10-08 Zhichao Hou , MohamadAli Torkamani , Hamid Krim , Xiaorui Liu

Attribution maps are popular tools for explaining neural networks predictions. By assigning an importance value to each input dimension that represents its impact towards the outcome, they give an intuitive explanation of the decision…

机器学习 · 计算机科学 2022-03-09 Adam Ivankay , Ivan Girardi , Chiara Marchiori , Pascal Frossard

Although machine learning models typically experience a drop in performance on out-of-distribution data, accuracies on in- versus out-of-distribution data are widely observed to follow a single linear trend when evaluated across a testbed…

机器学习 · 计算机科学 2021-07-01 Anders Andreassen , Yasaman Bahri , Behnam Neyshabur , Rebecca Roelofs

The accuracies for many pattern recognition tasks have increased rapidly year by year, achieving or even outperforming human performance. From the perspective of accuracy, pattern recognition seems to be a nearly-solved problem. However,…

计算机视觉与模式识别 · 计算机科学 2020-06-15 Xu-Yao Zhang , Cheng-Lin Liu , Ching Y. Suen

The effectiveness of supervised learning techniques has made them ubiquitous in research and practice. In high-dimensional settings, supervised learning commonly relies on dimensionality reduction to improve performance and identify the…

机器学习 · 计算机科学 2016-08-11 Chang Liu , Bo Li , Yevgeniy Vorobeychik , Alina Oprea

Reward models have become a staple in modern NLP, serving as not only a scalable text evaluator, but also an indispensable component in many alignment recipes and inference-time algorithms. However, while recent reward models increase…

计算与语言 · 计算机科学 2025-09-22 Zhaofeng Wu , Michihiro Yasunaga , Andrew Cohen , Yoon Kim , Asli Celikyilmaz , Marjan Ghazvininejad