Computing Rule-Based Explanations of Machine Learning Classifiers using Knowledge Graphs

• URL: http://arxiv.org/abs/2202.03971v1
• Date: Tue, 8 Feb 2022 16:21:49 GMT
• Title: Computing Rule-Based Explanations of Machine Learning Classifiers using Knowledge Graphs
• Authors: Edmund Dervakos, Orfeas Menis-Mastromichalakis, Alexandros Chortaras, Giorgos Stamou
• Abstract summary: We use knowledge graphs as the underlying framework providing the terminology for representing explanations for the operation of a machine learning classifier. In particular, we introduce a novel method for extracting and representing black-box explanations of its operation, in the form of first-order logic rules expressed in the terminology of the knowledge graph.
• Score: 62.997667081978825
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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 underlying framework providing the terminology for representing explanations for the operation of a machine learning classifier. In particular, given a description of the application domain of the classifier in the form of a knowledge graph, we introduce a novel method for extracting and representing black-box explanations of its operation, in the form of first-order logic rules expressed in the terminology of the knowledge graph.

Related papers

• Streamlining models with explanations in the learning loop [0.0]
  Several explainable AI methods allow a Machine Learning user to get insights on the classification process of a black-box model. We exploit this information to design a feature engineering phase, where we combine explanations with feature values.
  arXiv  Detail & Related papers  (2023-02-15T16:08:32Z)
• The Shape of Explanations: A Topological Account of Rule-Based Explanations in Machine Learning [0.0]
  We introduce a framework for rule-based explanation methods and provide a characterization of explainability. We argue that the preferred scheme depends on how much the user knows about the domain and the probability measure over the feature space.
  arXiv  Detail & Related papers  (2023-01-22T02:58:00Z)
• Conditional Attention Networks for Distilling Knowledge Graphs in Recommendation [74.14009444678031]
  We propose Knowledge-aware Conditional Attention Networks (KCAN) to incorporate knowledge graph into a recommender system. We use a knowledge-aware attention propagation manner to obtain the node representation first, which captures the global semantic similarity on the user-item network and the knowledge graph. Then, by applying a conditional attention aggregation on the subgraph, we refine the knowledge graph to obtain target-specific node representations.
  arXiv  Detail & Related papers  (2021-11-03T09:40:43Z)
• This is not the Texture you are looking for! Introducing Novel Counterfactual Explanations for Non-Experts using Generative Adversarial Learning [59.17685450892182]
  counterfactual explanation systems try to enable a counterfactual reasoning by modifying the input image. We present a novel approach to generate such counterfactual image explanations based on adversarial image-to-image translation techniques. Our results show that our approach leads to significantly better results regarding mental models, explanation satisfaction, trust, emotions, and self-efficacy than two state-of-the art systems.
  arXiv  Detail & Related papers  (2020-12-22T10:08:05Z)
• Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization [87.96102461221415]
  We develop an algorithm that provides per-class explainability. In an extensive battery of experiments, we demonstrate the ability of our methods to class-specific visualization.
  arXiv  Detail & Related papers  (2020-12-03T18:48:39Z)
• Information Theoretic Meta Learning with Gaussian Processes [74.54485310507336]
  We formulate meta learning using information theoretic concepts; namely, mutual information and the information bottleneck. By making use of variational approximations to the mutual information, we derive a general and tractable framework for meta learning.
  arXiv  Detail & Related papers  (2020-09-07T16:47:30Z)
• Knowledge Graph semantic enhancement of input data for improving AI [0.0]
  Intelligent systems designed using machine learning algorithms require a large number of labeled data. Background knowledge provides complementary, real world factual information that can augment the limited labeled data to train a machine learning algorithm. The Knowledge Graph (KG) is in vogue as for many practical applications, it is convenient and useful to organize this background knowledge in the form of a graph.
  arXiv  Detail & Related papers  (2020-05-10T17:37:38Z)
• Knowledge Graph Embeddings and Explainable AI [29.205234615756822]
  We introduce the concept of knowledge graph embeddings by explaining what they are, how they can be generated and how they can be evaluated. We summarize the state-of-the-art in this field by describing the approaches that have been introduced to represent knowledge in the vector space. In relation to knowledge representation, we consider the problem of explainability, and discuss models and methods for explaining predictions obtained via knowledge graph embeddings.
  arXiv  Detail & Related papers  (2020-04-30T14:55:09Z)
• Exploiting Structured Knowledge in Text via Graph-Guided Representation Learning [73.0598186896953]
  We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models, our first contribution is an entity masking scheme. In contrast to existing paradigms, our approach uses knowledge graphs implicitly, only during pre-training.
  arXiv  Detail & Related papers  (2020-04-29T14:22:42Z)
• Common-Knowledge Concept Recognition for SEVA [15.124939896007472]
  We build a common-knowledge concept recognition system for a Systems Engineer's Virtual Assistant (SEVA) The problem is formulated as a token classification task similar to named entity extraction. We construct a dataset annotated at the word-level by carefully defining a labelling scheme to train a sequence model to recognize systems engineering concepts.
  arXiv  Detail & Related papers  (2020-03-26T00:30:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.