paper-with-me

Papers

One-way Explainability Isn't The Message

2022-05-05 · Ashwin Srinivasan, Michael Bain, Enrico Coiera

Recent engineering developments in specialised computational hardware, data-acquisition and storage technology have seen the emergence of Machine Learning (ML) as a powerful form of data analysis with widespread applicability beyond its historical roots in the design of autonomous agents. However -- possibly because of its origins in the development of agents capable of self-discovery -- relatively little attention has been paid to the interaction between people and ML. In this paper we are concerned with the use of ML in automated or semi-automated tools that assist one or more human decision makers. We argue that requirements on both human and machine in this context are significantly different to the use of ML either as part of autonomous agents for self-discovery or as part statistical data analysis. Our principal position is that the design of such human-machine systems should be driven by repeated, two-way intelligibility of information rather than one-way explainability of the ML-system's recommendations. Iterated rounds of intelligible information exchange, we think, will characterise the kinds of collaboration that will be needed to understand complex phenomena for which neither man or machine have complete answers. We propose operational principles -- we call them Intelligibility Axioms -- to guide the design of a collaborative decision-support system. The principles are concerned with: (a) what it means for information provided by the human to be intelligible to the ML system; and (b) what it means for an explanation provided by an ML system to be intelligible to a human. Using examples from the literature on the use of ML for drug-design and in medicine, we demonstrate cases where the conditions of the axioms are met. We describe some additional requirements needed for the design of a truly collaborative decision-support system.

📄 PDF Abstract BibTeX arXiv:2205.08954

Code (0)

등록된 구현이 없습니다.

Tasks

Drug Design

Similar Papers 제목 키워드 기반

FlowX: Towards Explainable Graph Neural Networks via Message Flows

2022-06-26 · Shurui Gui, Hao Yuan, Jie Wang, Qicheng Lao 외

We investigate the explainability of graph neural networks (GNNs) as a step toward elucidating their working mechanisms. While most current methods focus on explaining graph nodes, edges, or features, we argue that, as t…

Philosophy

Multi-resolution Interpretation and Diagnostics Tool for Natural Language Classifiers

2023-03-06 · Peyman Jalali, Nengfeng Zhou, Yufei Yu

Developing explainability methods for Natural Language Processing (NLP) models is a challenging task, for two main reasons. First, the high dimensionality of the data (large number of tokens) results in low coverage and …

DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

2022-05-26 · Peter Müller, Lukas Faber, Karolis Martinkus, Roger Wattenhofer

We propose the fully explainable Decision Tree Graph Neural Network (DT+GNN) architecture. In contrast to existing black-box GNNs and post-hoc explanation methods, the reasoning of DT+GNN can be inspected at every step. …

Decision MakingGraph Neural Network

Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks

2023-10-03 · Xu Zheng, Farhad Shirani, Tianchun Wang, Wei Cheng 외

Graph Neural Networks (GNNs) are neural models that leverage the dependency structure in graphical data via message passing among the graph nodes. GNNs have emerged as pivotal architectures in analyzing graph-structured …

Decision Making

FSX: Message Flow Sensitivity Enhanced Structural Explainer for Graph Neural Networks

2026-01-21 · Bizu Feng, Zhimu Yang, Shaode Yu, Zixin Hu arxiv

Despite the widespread success of Graph Neural Networks (GNNs), understanding the reasons behind their specific predictions remains challenging. Existing explainability methods face a trade-off that gradient-based approa…

Feature Importance