paper-with-me

홈 › Papers

Influence-Directed Explanations for Deep Convolutional Networks

2018-02-11 · ICLR 2018 1 · Klas Leino, Shayak Sen, Anupam Datta, Matt Fredrikson, Linyi Li

We study the problem of explaining a rich class of behavioral properties of deep neural networks. Distinctively, our influence-directed explanations approach this problem by peering inside the network to identify neurons with high influence on a quantity and distribution of interest, using an axiomatically-justified influence measure, and then providing an interpretation for the concepts these neurons represent. We evaluate our approach by demonstrating a number of its unique capabilities on convolutional neural networks trained on ImageNet. Our evaluation demonstrates that influence-directed explanations (1) identify influential concepts that generalize across instances, (2) can be used to extract the "essence" of what the network learned about a class, and (3) isolate individual features the network uses to make decisions and distinguish related classes.

📄 PDF Abstract BibTeX arXiv:1802.03788

Code (2)

cmu-transparency/lib-attribution tf
pytorch/captum pytorch

Similar Papers 제목 키워드 기반

HoloNets: Spectral Convolutions do extend to Directed Graphs

2023-10-03 · Christian Koke, Daniel Cremers

Within the graph learning community, conventional wisdom dictates that spectral convolutional networks may only be deployed on undirected graphs: Only there could the existence of a well-defined graph Fourier transform b…

Graph LearningNode Classification

Explaining the Reasoning of Large Language Models Using Attribution Graphs

2025-12-17 · Chase Walker, Rickard Ewetz arxiv

Large language models (LLMs) exhibit remarkable capabilities, yet their reasoning remains opaque, raising safety and trust concerns. Attribution methods, which assign credit to input features, have proven effective for e…

Decision Making

From Graphs to Gradients: Physics-Inspired Structural Attribution for Cyber-Physical IoT Systems and Beyond

2026-07-06 · Spyridon Evangelatos, Christos Diou, Georgios Th. Papadopoulos, Evangelos Markakis 외 arxiv

Interpretable explanation methods in Artificial Intelligence aim to uncover the underlying causes and their effects, enabling a deeper understanding of why a system behaves in a certain way under different inputs. Unlike…

Clustering Edges in Directed Graphs

2022-02-23 · Manohar Murthi, Kamal Premaratne

How do vertices exert influence in graph data? We develop a framework for edge clustering, a new method for exploratory data analysis that reveals how both vertices and edges collaboratively accomplish directed influence…

Clustering

The Costs and Benefits of Goal-Directed Attention in Deep Convolutional Neural Networks

2020-02-06 · Xiaoliang Luo, Brett D. Roads, Bradley C. Love

People deploy top-down, goal-directed attention to accomplish tasks, such as finding lost keys. By tuning the visual system to relevant information sources, object recognition can become more efficient (a benefit) and mo…

Object RecognitionTransfer Learning