Bias in ontologies -- a preliminary assessment

• URL: http://arxiv.org/abs/2101.08035v1
• Date: Wed, 20 Jan 2021 09:28:08 GMT
• Title: Bias in ontologies -- a preliminary assessment
• Authors: C. Maria Keet
• Abstract summary: Algorithmic bias is a well-known notion, but what does bias mean in the context of that provide a mechanism for an algorithm's input? This characterisation aims contribute a sensitisation of ethical aspects of representation of information and knowledge.
• Score: 2.360534864805446
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Logical theories in the form of ontologies and similar artefacts in computing and IT are used for structuring, annotating, and querying data, among others, and therewith influence data analytics regarding what is fed into the algorithms. Algorithmic bias is a well-known notion, but what does bias mean in the context of ontologies that provide a structuring mechanism for an algorithm's input? What are the sources of bias there and how would they manifest themselves in ontologies? We examine and enumerate types of bias relevant for ontologies, and whether they are explicit or implicit. These eight types are illustrated with examples from extant production-level ontologies and samples from the literature. We then assessed three concurrently developed COVID-19 ontologies on bias and detected different subsets of types of bias in each one, to a greater or lesser extent. This first characterisation aims contribute to a sensitisation of ethical aspects of ontologies primarily regarding representation of information and knowledge.

Related papers

• Ontology Embedding: A Survey of Methods, Applications and Resources [54.3453925775069]
  Ontologies are widely used for representing domain knowledge and meta data. One straightforward solution is to integrate statistical analysis and machine learning. Numerous papers have been published on embedding, but a lack of systematic reviews hinders researchers from gaining a comprehensive understanding of this field.
  arXiv  Detail & Related papers  (2024-06-16T14:49:19Z)
• Dissecting Causal Biases [0.0]
  This paper focuses on a class of bias originating in the way training data is generated and/or collected. Four sources of bias are considered, namely, confounding, selection, measurement, and interaction.
  arXiv  Detail & Related papers  (2023-10-20T09:12:10Z)
• Anatomizing Bias in Facial Analysis [86.79402670904338]
  Existing facial analysis systems have been shown to yield biased results against certain demographic subgroups. It has become imperative to ensure that these systems do not discriminate based on gender, identity, or skin tone of individuals. This has led to research in the identification and mitigation of bias in AI systems.
  arXiv  Detail & Related papers  (2021-12-13T09:51:13Z)
• A Typology of Data Anomalies [0.0]
  Anomalies are cases that are in some way unusual and do not appear to fit the general patterns present in the dataset. This paper introduces a general typology of anomalies that offers a clear and tangible definition of the different types of anomalies in datasets.
  arXiv  Detail & Related papers  (2021-07-04T13:12:24Z)
• Towards Measuring Bias in Image Classification [61.802949761385]
  Convolutional Neural Networks (CNN) have become state-of-the-art for the main computer vision tasks. However, due to the complex structure their decisions are hard to understand which limits their use in some context of the industrial world. We present a systematic approach to uncover data bias by means of attribution maps.
  arXiv  Detail & Related papers  (2021-07-01T10:50:39Z)
• LOGAN: Local Group Bias Detection by Clustering [86.38331353310114]
  We argue that evaluating bias at the corpus level is not enough for understanding how biases are embedded in a model. We propose LOGAN, a new bias detection technique based on clustering. Experiments on toxicity classification and object classification tasks show that LOGAN identifies bias in a local region.
  arXiv  Detail & Related papers  (2020-10-06T16:42:51Z)
• On the Nature and Types of Anomalies: A Review of Deviations in Data [0.0]
  This study offers the first theoretically principled and domain-independent typology of data anomalies. To concretely define the concept of the anomaly and its different manifestations, the typology employs five dimensions. These fundamental and data-centric dimensions naturally yield 3 broad groups, 9 basic types, and 63 subtypes of anomalies.
  arXiv  Detail & Related papers  (2020-07-30T17:55:11Z)
• Towards causal benchmarking of bias in face analysis algorithms [54.19499274513654]
  We develop an experimental method for measuring algorithmic bias of face analysis algorithms. Our proposed method is based on generating synthetic transects'' of matched sample images. We validate our method by comparing it to a study that employs the traditional observational method for analyzing bias in gender classification algorithms.
  arXiv  Detail & Related papers  (2020-07-13T17:10:34Z)
• Learning from Failure: Training Debiased Classifier from Biased Classifier [76.52804102765931]
  We show that neural networks learn to rely on spurious correlation only when it is "easier" to learn than the desired knowledge. We propose a failure-based debiasing scheme by training a pair of neural networks simultaneously. Our method significantly improves the training of the network against various types of biases in both synthetic and real-world datasets.
  arXiv  Detail & Related papers  (2020-07-06T07:20:29Z)
• Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias [45.956112337250275]
  We propose a methodology grounded in the theory of causal mediation analysis for interpreting which parts of a model are causally implicated in its behavior. We apply this methodology to analyze gender bias in pre-trained Transformer language models. Our mediation analysis reveals that gender bias effects are (i) sparse, concentrated in a small part of the network; (ii) synergistic, amplified or repressed by different components; and (iii) decomposable into effects flowing directly from the input and indirectly through the mediators.
  arXiv  Detail & Related papers  (2020-04-26T01:53:03Z)

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.