Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
ORANGE: Opposite-label soRting for tANGent Explanations in heterogeneous spaces
Stockholms universitet, Samhällsvetenskapliga fakulteten, Institutionen för data- och systemvetenskap.ORCID-id: 0000-0002-5460-2491
Stockholms universitet, Samhällsvetenskapliga fakulteten, Institutionen för data- och systemvetenskap.
Stockholms universitet, Samhällsvetenskapliga fakulteten, Institutionen för data- och systemvetenskap.ORCID-id: 0000-0002-1357-1967
Stockholms universitet, Samhällsvetenskapliga fakulteten, Institutionen för data- och systemvetenskap.ORCID-id: 0000-0001-7713-1381
Visa övriga samt affilieringar
2023 (Engelska)Ingår i: 2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA), IEEE conference proceedings, 2023, s. 1-10Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Most real-world datasets have a heterogeneous feature space composed of binary, categorical, ordinal, and continuous features. However, the currently available local surrogate explainability algorithms do not consider this aspect, generating infeasible neighborhood centers which may provide erroneous explanations. To overcome this issue, we propose ORANGE, a local surrogate explainability algorithm that generates highaccuracy and high-fidelity explanations in heterogeneous spaces. ORANGE has three main components: (1) it searches for the closest feasible counterfactual point to a given instance of interest by considering feasible values in the features to ensure that the explanation is built around the closest feasible instance and not any, potentially non-existent instance in space; (2) it generates a set of neighboring points around this close feasible point based on the correlations among features to ensure that the relationship among features is preserved inside the neighborhood; and (3) the generated instances are weighted, firstly based on their distance to the decision boundary, and secondly based on the disagreement between the predicted labels of the global model and a surrogate model trained on the neighborhood. Our extensive experiments on synthetic and public datasets show that the performance achieved by ORANGE is best-in-class in both explanation accuracy and fidelity.

Ort, förlag, år, upplaga, sidor
IEEE conference proceedings, 2023. s. 1-10
Nyckelord [en]
Correlation, Predictive models, Data science, Sorting
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
data- och systemvetenskap
Identifikatorer
URN: urn:nbn:se:su:diva-224013DOI: 10.1109/DSAA60987.2023.10302474Scopus ID: 2-s2.0-85178999467ISBN: 979-8-3503-4503-2 (digital)OAI: oai:DiVA.org:su-224013DiVA, id: diva2:1814155
Konferens
International Conference on Data Science and Advanced Analytics (DSAA), Thessaloniki, Greece, October 9-13, 2023
Tillgänglig från: 2023-11-23 Skapad: 2023-11-23 Senast uppdaterad: 2024-10-16Bibliografiskt granskad
Ingår i avhandling
1. Orange Juice: Enhancing Machine Learning Interpretability
Öppna denna publikation i ny flik eller fönster >>Orange Juice: Enhancing Machine Learning Interpretability
2024 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

In the current state of AI development, it is reasonable to think that AI will continue to expand and be increasingly utilized across different fields, highly impacting every aspect of humanity's welfare and livelihood. However, different AI researchers and institutions agree that AI has the potential to be extremely beneficial but also may pose existential threats to humanity. It is therefore necessary to develop tools to open the so-called black-box AI algorithms and increase their understandability and trustworthiness, in order to avoid conceivably harmful future scenarios.

The lack of interpretability of AI is a challenge to its own development: it is an obstacle equivalent to those that triggered previous AI winters, such as hardware or technological constraints or public over-expectation. In other words, research in interpretability and model understanding, both from theoretical and pragmatic perspectives, will help avoid a third AI winter, which could be devastating for the current world economy.

Specifically, from the theoretical perspective, the subfields of local explainability and algorithmic fairness require some improvements in order to enhance the explanation output. Local explainability refers to the algorithms that attempt to extract useful explanations for the output of machine learning models for individual instances, while algorithmic fairness refers to the study of biases or fairness issues among different groups of people, whenever the datasets refer to humans. Providing a higher level of explanation accuracy, explanation fidelity and explanation support for the observations of each dataset would help improve the overall level of trustworthiness and the understandability of the explanations. The explainability methods should also be applied to practical scenarios. In the area of autonomous driving, for example, providing confidence intervals on the positioning estimates and positioning errors is important for vehicle operations, and machine learning models coupled with conformal prediction may provide a solution that focuses on the confidence of these estimates, prioritizing safety.  

This thesis contributes to research in the field of AI interpretability, focusing mainly on the algorithms related to local explainability, algorithmic fairness and conformal prediction. Specifically, the thesis targets the improvement of counterfactual and local surrogate explanation algorithms. These explainability methods may also reveal the existence of biases, and therefore the study of algorithmic fairness is a relevant part of interpretability. This thesis focuses on the topic of machine learning fairness assessment through the use of local explainability methods, proposing two novel elements: a single accuracy-based and counterfactual-based bias detection measure and a counterfactual generation method for groups intended for bias detection and fair recommendations across groups. Finally, the idea behind interpretability is to be able to eventually implement such methods in real-world applications. This thesis presents an application of the conformal prediction framework to a regression problem related to autonomous vehicle localization systems. In this application, the framework is able to output the predicted positioning error of a vehicle and its confidence interval with some level of significance.

Ort, förlag, år, upplaga, sidor
Stockholm: Department of Computer and Systems Sciences, Stockholm University, 2024. s. 72
Serie
Report Series / Department of Computer & Systems Sciences, ISSN 1101-8526 ; 24-013
Nyckelord
artificial intelligence, machine learning, interpretability, explainability, counterfactual, fairness
Nationell ämneskategori
Datorsystem
Forskningsämne
data- och systemvetenskap
Identifikatorer
urn:nbn:se:su:diva-233360 (URN)978-91-8014-929-7 (ISBN)978-91-8014-930-3 (ISBN)
Disputation
2024-11-14, L30, NOD-huset, Borgarfjordsgatan 12, Kista, 09:00 (Engelska)
Opponent
Handledare
Tillgänglig från: 2024-10-22 Skapad: 2024-09-10 Senast uppdaterad: 2024-10-08Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Kuratomi Hernandez, AlejandroLee, ZedMiliou, IoannaLindgren, TonyPapapetrou, Panagiotis

Sök vidare i DiVA

Av författaren/redaktören
Kuratomi Hernandez, AlejandroLee, ZedMiliou, IoannaLindgren, TonyPapapetrou, Panagiotis
Av organisationen
Institutionen för data- och systemvetenskap
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 314 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf