检索结果-内蒙古大学图书馆

On the Impact of Explanations on Understanding of Algorithmic Decision-Making

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Schmude, Timothée Koesten, Laura Möller, Torsten Tschiatschek, Sebastian University of Vienna Faculty of Computer Science Research Network Data Science UniVie Doctoral School Computer Science DoCS Austria University of Vienna Faculty of Computer Science Research Group Visualization and Data Analysis Austria University of Vienna Faculty of Computer Science Research Network Data Science Research Group Visualization and Data Analysis Austria University of Vienna Faculty of Computer Science Research Network Data Science Research Group Data Mining and Machine Learning Austria

Ethical principles for algorithms are gaining importance as more and more stakeholders are affected by "high-risk" algorithmic decision-making (ADM) systems. Understanding how these systems work enables stakeholders to make informed decisions and to assess the systems’ adherence to ethical values. Explanations are a promising way to create understanding, but current explainable artificial intelligence (XAI) research does not always consider existent theories on how understanding is formed and evaluated. In this work, we aim to contribute to a better understanding of understanding by conducting a qualitative task-based study with 30 participants, including users and affected stakeholders. We use three explanation modalities (textual, dialogue, and interactive) to explain a "high-risk" ADM system to participants and analyse their responses both inductively and deductively, using the "six facets of understanding" framework by Wiggins & McTighe [63]. Our findings indicate that the "six facets" framework is a promising approach to analyse participants’ thought processes in understanding, providing categories for both rational and emotional understanding. We further introduce the "dialogue" modality as a valid explanation approach to increase participant engagement and interaction with the "explainer", allowing for more insight into their understanding in the process. Our analysis further suggests that individuality in understanding affects participants’ perceptions of algorithmic fairness, demonstrating the interdependence between understanding and ADM assessment that previous studies have outlined. We posit that drawing from theories on learning and understanding like the "six facets" and leveraging explanation modalities can guide XAI research to better suit explanations to learning processes of individuals and consequently enable their assessment of ethical values of ADM systems. © 2023, CC BY.

关键词： Decision making

Deliberative XAI: How Explanations Impact Understanding and Decision-Making of AI Novices in Collective and Individual Settings

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Schmude, Timothée Koesten, Laura Möller, Torsten Tschiatschek, Sebastian University of Vienna Faculty of Computer Science Research Network Data Science Doctoral School Computer Science Austria University of Vienna Faculty of Computer Science Research Group Visualization and Data Analysis Austria University of Vienna Faculty of Computer Science Research Group Visualization and Data Analysis Research Network Data Science Austria University of Vienna Faculty of Computer Science Research Network Data Science Research Group Data Mining and Machine Learning Austria

XAI research often focuses on settings where people learn about and assess algorithmic systems individually. However, as more public AI systems are deployed, it becomes essential for XAI to facilitate collective understanding and deliberation. We conducted a task-based interview study involving 8 focus groups and 12 individual interviews to explore how explanations can support AI novices in understanding and forming opinions about AI systems. Participants received a collection of explanations organized into four information categories to solve tasks and decide about a system’s deployment. These explanations improved or calibrated participants’ self-reported understanding and decision confidence and facilitated group discussions. Participants valued both technical and contextual information and the self-directed and modular explanation structure. Our contributions include an explanation approach that facilitates both individual and collaborative interaction and explanation design recommendations, including active and controllable exploration, different levels of information detail and breadth, and adaptations to the needs of decision subjects. Copyright © 2024, The Authors. All rights reserved.

关键词：

Applying Interdisciplinary Frameworks to Understand Algorithmic Decision-Making

学校读者我要写书评

暂无评论

arXiv 2023年

We argue that explanations for "algorithmic decision-making" (ADM) systems can profit by adopting practices that are already used in the learning sciences. We shortly introduce the importance of explaining ADM systems, give a brief overview of approaches drawing from other disciplines to improve explanations, and present the results of our qualitative task-based study incorporating the "six facets of understanding" [24] framework. We close with questions guiding the discussion of how future studies can leverage an interdisciplinary approach. © 2023, CC BY.

关键词： Decision making

So3krates: equivariant attention for interactions on arbitrary length-scales in molecular systems 22

学校读者我要写书评

暂无评论

So3krates: equivariant attention for interactions on arbitra...

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： J. Thorben Frank Oliver T. Unke Klaus-Robert Müller Machine Learning Group TU Berlin Berlin Germany and BIFOLD Berlin Institute for the Foundations of Learning and Data Germany Machine Learning Group TU Berlin Berlin Germany and BIFOLD Berlin Institute for the Foundations of Learning and Data Germany and Google Research Brain team Berlin Machine Learning Group TU Berlin Berlin Germany and BIFOLD Berlin Institute for the Foundations of Learning and Data Germany and Google Research Brain team Berlin and Department of Artificial Intelligence Korea University Seoul Korea and Max Planck Institut für Informatik Saarbrücken Germany

ISBN: (纸本)9781713871088

The application of machine learning methods in quantum chemistry has enabled the study of numerous chemical phenomena, which are computationally intractable with traditional ab-initio methods. However, some quantum mechanical properties of molecules and materials depend on non-local electronic effects, which are often neglected due to the difficulty of modeling them efficiently. This work proposes a modified attention mechanism adapted to the underlying physics, which allows to recover the relevant non-local effects. Namely, we introduce spherical harmonic coordinates (SPHCs) to reflect higher-order geometric information for each atom in a molecule, enabling a non-local formulation of attention in the SPHC space. Our proposed model So3KRATES- a self-attention based message passing neural network - uncouples geometric information from atomic features, making them independently amenable to attention mechanisms. Thereby we construct spherical filters, which extend the concept of continuous filters in Euclidean space to SPHC space and serve as foundation for a spherical self-attention mechanism. We show that in contrast to other published methods, So3krates is able to describe nonlocal quantum mechanical effects over arbitrary length scales. Further, we find evidence that the inclusion of higher-order geometric correlations increases data efficiency and improves generalization. So3krates matches or exceeds state- of-the-art performance on popular benchmarks, notably, requiring a significantly lower number of parameters (0.25-0.4x) while at the same time giving a substantial speedup (6-14x for training and 2-11x for inference) compared to other models.

关键词：

Towards Enhancing Deep Active learning with Weak Supervision and Constrained Clustering

学校读者我要写书评

暂无评论

Towards Enhancing Deep Active Learning with Weak Supervision...

2023 Workshop on Interactive Adaptive learning, IAL@ECML-PKDD 2023

作者： Aßenmacher, Matthias Rauch, Lukas Goschenhofer, Jann Stephan, Andreas Bischl, Bernd Roth, Benjamin Sick, Bernhard Department of Statistics LMU Munich Ludwigstr. 33 MunichD-80539 Germany LMU Munich Germany University of Kassel Wilhelmshöher Allee 73 KasselD-34121 Germany Fraunhofer IIS Erlangen Germany Research Group Data Mining and Machine Learning University of Vienna Kolingasse 14-16 ViennaA-1090 Austria UniVie Doctoral School Computer Science Vienna Austria

Three fields revolving around the question of how to cope with limited amounts of labeled data are Deep Active learning (DAL), deep Constrained Clustering (CC), and Weakly Supervised learning (WSL). DAL tackles the problem by adaptively posing the question of which data samples to annotate next in order to achieve the best incremental learning improvement, although it suffers from several limitations that hinder its deployment in practical settings. We point out how CC algorithms and WSL could be employed to overcome these limitations and increase the practical applicability of DAL research. Specifically, we discuss the opportunities to use the class discovery capabilities of CC and the possibility of further reducing human annotation efforts by utilizing WSL. We argue that the practical applicability of DAL algorithms will benefit from employing CC and WSL methods for the learning and labeling process. We inspect the overlaps between the three research areas and identify relevant and exciting research questions at the intersection of these areas. © 2023 Copyright for this paper by its authors.

关键词： Deep learning

Fighting spam with statistics

学校读者我要写书评

暂无评论

Significance 2004年第2期1卷 69-72页

作者： Goodman, Joshua Heckerman, David Joshua Goodman is a Researcher in the Machine Learning and Applied Statistics Group at Microsoft Research. He has been on loan to Microsoft's Anti-Spam product team since its inception. His previous work was on language modelling (predicting word sequences) and fast algorithms for logistic regression. David Heckerman is founder and manager of the Machine Learning and Applied Statistics Group at Microsoft Research. Since 1992 he has been a Senior Researcher at Microsoft where he has created applications including junk mail filters data mining tools handwriting recognition for the Tablet PC troubleshooters in Windows and the Answer Wizard in Office. His work includes Bayesian methods for learning probabilistic graphical models from data. David received his doctorate from Stanford University in 1990 and is a Fellow of the American Association for Artificial Intelligence.

Spam-unsolicited commercial e-mail-is a complex and growing problem, and threatens to derail the internet revolution. Joshua Goodman and David Heckerman of Microsoft research describe some statistics-based methods for blocking spam, first by distinguishing it from wanted mail, and then by constructing puzzles they propose to use to challenge suspected spammers. © 2004 The Royal Statistical Society.

关键词：

Finding latent causes in causal networks: an efficient approach based on Markov blankets 08

学校读者我要写书评

暂无评论

Finding latent causes in causal networks: an efficient appro...

Proceedings of the 22nd International Conference on Neural Information Processing Systems

作者： Jean-Philippe Pellet André Elisseeff Pattern Recognition and Machine Learning Group Swiss Federal Institute of Technology Zurich Zurich Switzerland and Data Analytics Group IBM Research GmbH Rüschlikon Switzerland Data Analytics Group IBM Research GmbH Rüschlikon Switzerland

ISBN: (纸本)9781605609492

Causal structure-discovery techniques usually assume that all causes of more than one variable are observed. This is the so-called causal sufficiency assumption. In practice, it is untestable, and often violated. In this paper, we present an efficient causal structure-learning algorithm, suited for causally insufficient data. Similar to algorithms such as IC* and FCI, the proposed approach drops the causal sufficiency assumption and learns a structure that indicates (potential) latent causes for pairs of observed variables. Assuming a constant local density of the data-generating graph, our algorithm makes a quadratic number of conditional-independence tests w.r.t. the number of variables. We show with experiments that our algorithm is comparable to the state-of-the-art FCI algorithm in accuracy, while being several orders of magnitude faster on large problems. We conclude that MBCS* makes a new range of causally insufficient problems computationally tractable.

关键词： causal inference

Cloud-Based Event-Processing Architecture for Opinion mining

学校读者我要写书评

暂无评论

Cloud-Based Event-Processing Architecture for Opinion Mining

IEEE World Congress on Services (SERVICES)

作者： Stella Gatziu Grivas Marc Schaaf Michael Kaschesky Guillaume Bouchard Information and Knowledge Management Unit University of Applied Science Switzerland E-Government Unit Bern University of Applied Sciences Switzerland Data Mining and Machine Learning Group Xerox Research Centre Europe Grenoble France

The viability of cloud computing for information-intensive tasks arising in real-time opinion mining and sentiment analysis of large online text streams is described. We show how a smart distributed architecture enables an efficient and scalable design for opinion mining on internet-based content that answers key challenges, such as integrating heterogeneous data sources and adapting to events through dynamic system configuration. In particular, we present a novel approach of semantic complex event processing in a cloud environment capturing different levels of information, such as event data (e.g. content from various heterogeneous, distributed sources) as well as associations identified during the opinion mining and sentiment analysis process (e.g. dynamic co-reference resolution).

关键词：

SepLL: Separating Latent Class Labels from Weak Supervision Noise

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Stephan, Andreas Kougia, Vasiliki Roth, Benjamin Research Group Data Mining and Machine Learning Faculty of Computer Science University of Vienna Vienna Austria UniVie Doctoral School Computer Science Vienna Austria Faculty of Philological and Cultural Studies University of Vienna Vienna Austria

In the weakly supervised learning paradigm, labeling functions automatically assign heuristic, often noisy, labels to data samples. In this work, we provide a method for learning from weak labels by separating two types of complementary information associated with the labeling functions: information related to the target label and information specific to one labeling function only. Both types of information are reflected to different degrees by all labeled instances. In contrast to previous works that aimed at correcting or removing wrongly labeled instances, we learn a branched deep model that uses all data as-is, but splits the labeling function information in the latent space. Specifically, we propose the end-to-end model SepLL which extends a transformer classifier by introducing a latent space for labeling function specific and task-specific information. The learning signal is only given by the labeling functions matches, no pre-processing or label model is required for our method. Notably, the task prediction is made from the latent layer without any direct task signal. Experiments on Wrench text classification tasks show that our model is competitive with the state-of-the-art, and yields a new best average performance. © 2022, CC BY.

关键词： Classification (of information)