检索结果-内蒙古大学图书馆

FORMAL CONCEPTUAL VIEWS IN NEURAL NETWORKS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hirth, Johannes Hanika, Tom Knowledge and Data Engineering Group University of Kassel Kassel Germany

Explaining neural network models is a challenging task that remains unsolved in its entirety to this day. This is especially true for high dimensional and complex data. With the present work, we introduce two notions for conceptual views of a neural network, specifically a many-valued and a symbolic view. Both provide novel analysis methods to enable a human AI analyst to grasp deeper insights into the knowledge that is captured by the neurons of a network. We test the conceptual expressivity of our novel views through different experiments on the ImageNet and Fruit-360 data sets. Furthermore, we show to which extent the views allow to quantify the conceptual similarity of different learning architectures. Finally, we demonstrate how conceptual views can be applied for abductive learning of human comprehensible rules from neurons. In summary, with our work, we contribute to the most relevant task of globally explaining neural networks *** Codes 68T07 68T30 03G10 Copyright © 2022, The Authors. All rights reserved.

关键词： Neural network models

Greedy Discovery of Ordinal Factors

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dürrschnabel, Dominik Stumme, Gerd Knowledge and Data Engineering Group Interdisciplinary Research Center for Information System Design University of Kassel Kassel Germany

In large datasets, it is hard to discover and analyze structure. It is thus common to introduce tags or keywords for the items. In applications, such datasets are then filtered based on these tags. Still, even medium-sized datasets with a few tags result in complex and for humans hard-to-navigate systems. In this work, we adopt the method of ordinal factor analysis to address this problem. An ordinal factor arranges a subset of the tags in a linear order based on their underlying structure. A complete ordinal factorization, which consists of such ordinal factors, precisely represents the original dataset. Based on such an ordinal factorization, we provide a way to discover and explain relationships between different items and attributes in the dataset. However, computing even just one ordinal factor of high cardinality is computationally complex. We thus propose the greedy algorithm ORDIFIND in this work. This algorithm extracts ordinal factors using already existing fast algorithms developed in formal concept analysis. Then, we leverage ORDIFIND to propose a comprehensive way to discover relationships in the dataset. We furthermore introduce a distance measure based on the representation emerging from the ordinal factorization to discover similar items. To evaluate the method, we conduct a case study on different *** Codes 68T30, 03G10 Copyright © 2023, The Authors. All rights reserved.

关键词： Factorization

HaWANet: Road Scene Understanding with Multi-modal Sensor data Using Height-Width-Driven Attention Network 23rd

学校读者我要写书评

暂无评论

HaWANet: Road Scene Understanding with Multi-modal Sensor D...

23rd International Conference of the Italian Association for Artificial Intelligence, AIxIA 2024

作者： Chatterjee, Soumick Xu, Jiahua Kuzhipathalil, Adarsh Nürnberger, Andreas Faculty of Computer Science Otto von Guericke University Magdeburg Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Magdeburg Germany Genomics Research Centre Human Technopole Milan Italy Hertie Institute for Clinical Brain Research Tuebingen Germany XenomatiX NV Leuven Belgium

ISBN: (纸本)9783031806063

In recent years, the field of autonomous vehicles and driverless technology has seen remarkable advancements, driven by contributions from mainstream automotive manufacturers and open-source projects. This research aims to develop a pipeline for road scene understanding through semantic segmentation. The proposed pipeline utilises a multi-modal segmentation model, incorporating greyscale images and point cloud data from Xenolidar, specifically designed to capture the structural priors of highway road scenes. The fusion of input modalities and the design of an encoder-decoder architecture with a novel attention scheme called HaWANet is introduced, which focuses on the height and width contextual information to improve the accuracy of road segmentation, are the primary aspects explored for the proposed model. The output of the encoder is a two-dimensional point cloud, which effectively represents the road’s planar nature, and is crucial for improving the accuracy of road segmentation, particularly in edge cases, addressing current challenges in autonomous driving research. This research, aimed at addressing the segmentation problem for multimodal sensor data, has presented significant performance improvement over single-modal approaches. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

Maximal Ordinal Two-Factorizations

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dürrschnabel, Dominik Stumme, Gerd Knowledge & Data Engineering Group University of Kassel Kassel Germany Interdisciplinary Research Center for Information System Design Kassel Germany

Given a formal context, an ordinal factor is a subset of its incidence relation that forms a chain in the concept lattice, i.e., a part of the dataset that corresponds to a linear order. To visualize the data in a formal context, Ganter and Glodeanu proposed a biplot based on two ordinal factors. For the biplot to be useful, it is important that these factors comprise as much data points as possible, i.e., that they cover a large part of the incidence relation. In this work, we investigate such ordinal two-factorizations. First, we investigate for formal contexts that omit ordinal two-factorizations the disjointness of the two factors. Then, we show that deciding on the existence of two-factorizations of a given size is an NP-complete problem which makes computing maximal factorizations computationally expensive. Finally, we provide the algorithm Ord2Factor that allows us to compute large ordinal *** Codes 06-08, 03G10, 90C27, 68R10, 06A07 Copyright © 2023, The Authors. All rights reserved.

关键词： Factorization

Generative-Contrastive Graph Learning for Recommendation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Yonghui Wu, Zhengwei Wu, Le Zhang, Kun Hong, Richang Zhang, Zhiqiang Zhou, Jun Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China Ant Group China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

By treating users’ interactions as a user-item graph, graph learning models have been widely deployed in Collaborative Filtering (CF) based recommendation. Recently, researchers have introduced Graph Contrastive Learning (GCL) techniques into CF to alleviate the sparse supervision issue, which first constructs contrastive views by data augmentations and then provides self-supervised signals by maximizing the mutual information between contrastive views. Despite the effectiveness, we argue that current GCL-based recommendation models are still limited as current data augmentation techniques, either structure augmentation or feature augmentation. First, structure augmentation randomly dropout nodes or edges, which is easy to destroy the intrinsic nature of the user-item graph. Second, feature augmentation imposes the same scale noise augmentation on each node, which neglects the unique characteristics of nodes on the graph. To tackle the above limitations, we propose a novel Variational Graph Generative-Contrastive Learning (VGCL) framework for recommendation. Specifically, we leverage variational graph reconstruction to estimate a Gaussian distribution of each node, then generate multiple contrastive views through multiple samplings from the estimated distributions, which builds a bridge between generative and contrastive learning. The generated contrastive views can well reconstruct the input graph without information distortion. Besides, the estimated variances are tailored to each node, which regulates the scale of contrastive loss for each node on optimization. Considering the similarity of the estimated distributions, we propose a cluster-aware twofold contrastive learning, a node-level to encourage consistency of a node’s contrastive views and a cluster-level to encourage consistency of nodes in a cluster. Finally, extensive experimental results on three public datasets clearly demonstrate the effectiveness of the proposed model. Copyright © 2023, The Authors.

关键词： Collaborative filtering

Conceptual Views on Tree Ensemble Classifiers

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hanika, Tom Hirth, Johannes Knowledge & Data Engineering Group University of Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Germany

Random Forests and related tree-based methods are popular for supervised learning from table based data. Apart from their ease of parallelization, their classification performance is also superior. However, this performance, especially parallelizability, is offset by the loss of explainability. Statistical methods are often used to compensate for this disadvantage. Yet, their ability for local explanations, and in particular for global explanations, is limited. In the present work we propose an algebraic method, rooted in lattice theory, for the (global) explanation of tree ensembles. In detail, we introduce two novel conceptual views on tree ensemble classifiers and demonstrate their explanatory capabilities on Random Forests that were trained with standard *** Codes 68T30 03G10 68T27 06A15 97R40 Copyright © 2023, The Authors. All rights reserved.

关键词： Formal concept analysis

Combining Monte-Carlo Tree Search with Proof-Number Search

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Doe, Elliot Winands, Mark H.M. Soemers, Dennis J.N.J. Browne, Cameron Games Group Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

Proof-Number Search (PNS) and Monte-Carlo Tree Search (MCTS) have been successfully applied for decision making in a range of games. This paper proposes a new approach called PN-MCTS that combines these two tree-search methods by incorporating the concept of proof and disproof numbers into the UCT formula of MCTS. Experimental results demonstrate that PN-MCTS outperforms basic MCTS in several games including Lines of Action, MiniShogi, Knightthrough, and Awari, achieving win rates up to 94.0%. Copyright © 2022, The Authors. All rights reserved.

关键词： Decision making

Research Topic Flows in Co-Authorship Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Schäfermeier, Bastian Hirth, Johannes Hanika, Tom Knowledge and Data Engineering Group University of Kassel Wilhelmshoeher Allee 73 Kassel Germany

In scientometrics, scientific collaboration is often analyzed by means of co-authorships. An aspect which is often overlooked and more difficult to quantify is the flow of expertise between authors from different research topics, which is an important part of scientific progress. With the Topic Flow Network (TFN) we propose a graph structure for the analysis of research topic flows between scientific authors and their respective research fields. Based on a multi-graph and a topic model, our proposed network structure accounts for intratopic as well as intertopic flows. Our method requires for the construction of a TFN solely a corpus of publications (i.e., author and abstract information). From this, research topics are discovered automatically through non-negative matrix factorization. The thereof derived TFN allows for the application of social network analysis techniques, such as common metrics and community detection. Most importantly, it allows for the analysis of intertopic flows on a large, macroscopic scale, i.e., between research topic, as well as on a microscopic scale, i.e., between certain sets of authors. We demonstrate the utility of TFNs by applying our method to two comprehensive corpora of altogether 20 Mio. publications spanning more than 60 years of research in the fields computer science and mathematics. Our results give evidence that Topic Flow Networks are suitable, e.g., for the analysis of topical communities, the discovery of important authors in different fields, and, most notably, the analysis of intertopic flows, i.e., the transfer of topical expertise. Besides that, our method opens new directions for future research, such as the investigation of influence relationships between research *** Codes 68T50 68U35 68V35 01A90 00A15 Copyright © 2022, The Authors. All rights reserved.

关键词： Flow graphs

Exploring Scale-Measures of data Sets 16th

学校读者我要写书评

暂无评论

Exploring Scale-Measures of Data Sets

16th International Conference on Formal Concept Analysis, ICFCA 2021

作者： Hanika, Tom Hirth, Johannes Knowledge and Data Engineering Group University of Kassel Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Kassel Germany

ISBN: (纸本)9783030778668

Measurement is a fundamental building block of numerous scientific models and their creation in data driven science. Due to the high complexity and size of modern data sets, it is necessary to develop understandable and efficient scaling methods. A profound theory for scaling data is scale-measures from formal concept analysis. Recent developments indicate that the set of all scale-measures for a given data set constitutes a lattice. In this work we study the properties of said lattice and propose a novel and efficient scale-measure exploration algorithm, motivating multiple applications for (semi-)automatic scaling. © 2021, Springer Nature Switzerland AG.

关键词： Formal concept analysis