English
Related papers

Related papers: String Diagrams for Layered Explanations

200 papers

String diagrams are a powerful tool for reasoning about composite structures in symmetric monoidal categories. By representing string diagrams as graphs, equational reasoning can be done automatically by double-pushout rewriting. !-graphs…

Logic in Computer Science · Computer Science 2016-02-22 Aleks Kissinger , Vladimir Zamdzhiev

In this work, we present a new approach for constructing models for correlation matrices with a user-defined graphical structure. The graphical structure makes correlation matrices interpretable and avoids the quadratic increase of…

The original idea of proof nets can be formulated by means of interaction nets syntax. Additional machinery as switching, jumps and graph connectivity is needed in order to ensure correspondence between a proof structure and a correct proof…

Logic in Computer Science · Computer Science 2017-01-19 Matteo Acclavio

Recent commonsense-reasoning tasks are typically discriminative in nature, where a model answers a multiple-choice question for a certain context. Discriminative tasks are limiting because they fail to adequately evaluate the model's…

Computation and Language · Computer Science 2021-10-19 Swarnadeep Saha , Prateek Yadav , Lisa Bauer , Mohit Bansal

The use of symbolic knowledge representation and reasoning as a way to resolve the lack of transparency of machine learning classifiers is a research area that lately attracts many researchers. In this work, we use knowledge graphs as the…

Artificial Intelligence · Computer Science 2022-02-09 Edmund Dervakos , Orfeas Menis-Mastromichalakis , Alexandros Chortaras , Giorgos Stamou

Counterfactual explanations promote explainability in machine learning models by answering the question "how should an input instance be perturbed to obtain a desired predicted label?". The comparison of this instance before and after…

Machine Learning · Computer Science 2022-11-09 Jing Ma , Ruocheng Guo , Saumitra Mishra , Aidong Zhang , Jundong Li

Modern machine learning models are opaque, and as a result there is a burgeoning academic subfield on methods that explain these models' behavior. However, what is the precise goal of providing such explanations, and how can we demonstrate…

Machine Learning · Computer Science 2022-12-01 Patrick Fernandes , Marcos Treviso , Danish Pruthi , André F. T. Martins , Graham Neubig

We present a form of algebraic reasoning for computational objects which are expressed as graphs. Edges describe the flow of data between primitive operations which are represented by vertices. These graphs have an interface made of…

Logic in Computer Science · Computer Science 2010-07-23 Lucas Dixon , Ross Duncan , Aleks Kissinger

It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the problem. One peculiar observation is that these explanations…

Machine Learning · Computer Science 2022-03-07 Ashkan Khakzar , Pedram Khorsandi , Rozhin Nobahari , Nassir Navab

Explanations of model behavior are commonly evaluated via proxy properties weakly tied to the purposes explanations serve in practice. We contribute a decision theoretic framework that treats explanations as information signals valued by…

Artificial Intelligence · Computer Science 2026-02-24 Ziyang Guo , Berk Ustun , Jessica Hullman

This work establishes a robust mathematical foundation for compositional System Dynamics modeling, leveraging category theory to formalize and enhance the representation, analysis, and composition of system models. Here, System Dynamics…

Systems and Control · Electrical Eng. & Systems 2025-09-24 Xiaoyan Li , Evan Patterson , Patricia L. Mabry , Nathaniel D. Osgood

Mechanistic Interpretability (MI) aims to understand neural networks through causal explanations. Though MI has many explanation-generating methods, progress has been limited by the lack of a universal approach to evaluating explanations.…

Machine Learning · Computer Science 2025-05-05 Kola Ayonrinde , Louis Jaburi

Calculi of string diagrams are increasingly used to present the syntax and algebraic structure of various families of circuits, including signal flow graphs, electrical circuits and quantum processes. In many such approaches, the semantic…

Logic in Computer Science · Computer Science 2017-05-30 Brendan Fong , Fabio Zanasi

With recent advances in natural language processing, rationalization becomes an essential self-explaining diagram to disentangle the black box by selecting a subset of input texts to account for the major variation in prediction. Yet,…

Machine Learning · Computer Science 2023-09-12 Wenbo Zhang , Tong Wu , Yunlong Wang , Yong Cai , Hengrui Cai

A framework is presented for a computational theory of probabilistic argument. The Probabilistic Reasoning Environment encodes knowledge at three levels. At the deepest level are a set of schemata encoding the system's domain knowledge.…

Artificial Intelligence · Computer Science 2013-04-05 Kathryn Blackmond Laskey

Representing and exploiting multivariate signals requires capturing relations between variables, which we can represent by graphs. Graph dictionaries allow to describe complex relational information as a sparse sum of simpler structures,…

Machine Learning · Computer Science 2026-01-09 William Cappelletti , Pascal Frossard

Building explainable systems is a critical problem in the field of Natural Language Processing (NLP), since most machine learning models provide no explanations for the predictions. Existing approaches for explainable machine learning…

Computation and Language · Computer Science 2019-06-12 Hui Liu , Qingyu Yin , William Yang Wang

Justification theory is a unifying framework for semantics of non-monotonic logics. It is built on the notion of a justification, which intuitively is a graph that explains the truth value of certain facts in a structure. Knowledge…

Logic in Computer Science · Computer Science 2019-05-16 Simon Marynissen

We show that an interesting class of feed-forward neural networks can be understood as quantitative argumentation frameworks. This connection creates a bridge between research in Formal Argumentation and Machine Learning. We generalize the…

Neural and Evolutionary Computing · Computer Science 2020-12-11 Nico Potyka

Statistical modeling is a powerful tool for developing and testing theories by way of causal explanation, prediction, and description. In many disciplines there is near-exclusive use of statistical modeling for causal explanation and the…

Methodology · Statistics 2011-01-06 Galit Shmueli