检索结果-内蒙古大学图书馆

A Time-Series Higher-Order Network Hierarchical Evolution Model for Dynamic Interaction of Nodes

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Yang, Xiaoteng Wu, Zhenqiang Zhang, WenBo Javaid, Shumaila School of Computer Science Shaanxi Normal University Xi’an710119 China Key Laboratory of Modern Teaching Technology Ministry of Education Xi’an710062 China Department of Control Science and Engineering College of Electronics and Information Engineering Tongji University Shanghai201804 China Frontiers Science Center for Intelligent Autonomous Systems Shanghai201210 China

The evolution of hierarchies in complex systems is an exciting phenomenon since hierarchies exist in many social and biological networks. So far, many approaches have been proposed, however, they are either based on the locality of the nodes or the cluster relationships between networks. These approaches often use traditional time-series network modeling methods that focus only on local static relationships between different nodes but ignore the dynamic interactions between real network nodes. Local static and dynamic global relationships should be considered to understand better the generation and maintenance of hierarchical phenomena in networks. To address this problem, we propose a long-term, flexible hierarchical evolution model for explaining the hierarchical phenomena arising in networks. Our model can integrate both local static and dynamic global information in the network and use time and higher-order inter-node interactions to integrate static and dynamic relationships. New interactions in the network are formed based on preference information between nodes, while old links fade out over time. In addition, we derive critical points for the hierarchical evolution of the system over long periods. Importantly, our model allows the comparison of network rank formation across different data as a way to perform rank evolution studies. © 2022, The Authors. All rights reserved.

关键词： Time series

A C0 FINITE ELEMENT METHOD FOR THE BIHARMONIC PROBLEM WITH DIRICHLET BOUNDARY CONDITIONS IN A POLYGONAL DOMAIN

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Hengguang Wickramasinghe, Charuka D. Yin, Peimeng Department of Mathematics Wayne State University DetroitMI48202 United States Multiscale Methods and Dynamics Group Computer Science and Mathematics Division Oak Ridge National Laboratory Oak RidgeTN37831 United States

In this paper, we study the biharmonic equation with Dirichlet boundary conditions in a polygonal domain. In particular, we propose a method that effectively decouples the fourth-order problem into a system of two Poison equations and one Stokes equation, or a system of one Stokes equation and one Poisson equation. It is shown that the solution of each system is equivalent to that of the original fourth-order problem on both convex and non-convex polygonal domains. Two finite element algorithms are in turn proposed to solve the decoupled systems. In addition, we show the regularity of the solutions in each decoupled system in both the Sobolev space and the weighted Sobolev space, and we derive the optimal error estimates for the numerical solutions on both quasi-uniform meshes and graded meshes. Numerical test results are presented to justify the theoretical findings. © 2022, CC BY.

关键词： Poisson equation

REASONER: an explainable recommendation dataset with comprehensive labeling ground truths 23

学校读者我要写书评

暂无评论

REASONER: an explainable recommendation dataset with compreh...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Xu Chen Jingsen Zhang Lei Wang Quanyu Dai Zhenhua Dong Ruiming Tang Rui Zhang Li Chen Wayne Xin Zhao Ji-Rong Wen Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China and Gaoling School of Artificial Intelligence Renmin University of China Beijing China Huawei Noah's Ark Lab China www.ruizhang.info Department of Computer Science Hong Kong Baptist University Hong Kong

Explainable recommendation has attracted much attention from the industry and academic communities. It has shown great potential to improve the recommendation persuasiveness, informativeness and user satisfaction. In the past few years, while a lot of promising explainable recommender models have been proposed, the datasets used to evaluate them still suffer from several limitations, for example, the explanation ground truths are not labeled by the real users, the explanations are mostly single-modal and around only one aspect. To bridge these gaps, in this paper, we build a new explainable recommendation dataset, which, to our knowledge, is the first contribution that provides a large amount of real user labeled multi-modal and multi-aspect explanation ground truths. In specific, we firstly develop a video recommendation platform, where a series of questions around the recommendation explainability are carefully designed. Then, we recruit about 3000 high-quality labelers with different backgrounds to use the system, and collect their behaviors and feedback to our questions. In this paper, we detail the construction process of our dataset and also provide extensive analysis on its characteristics. In addition, we develop a library, where many well-known explainable recommender models are implemented in a unified framework. Based on this library, we build several benchmarks for different explainable recommendation tasks. At last, we present many new opportunities brought by our dataset, which are expected to promote the field of explainable recommendation. Our dataset, library and the related documents have been released at https://***/.

关键词：

Machine Learning for Energy Load Prediction and its Interpretation

学校读者我要写书评

暂无评论

Machine Learning for Energy Load Prediction and its Interpre...

International IEEE Conference on Intelligent Systems, IS

作者： Małgorzata Charytanowicz Anna Olwert Weronika Radziszewska Jolanta Jarnicka Krzysztof Gajowniczek Tomasz Ząbkowski Jacek Brożyna Grzegorz Mentel Grzegorz Matejko Center for Methods of Data Analysis Systems Research Institute PAS Warsaw Poland Department of Computer Science Systems Research Institute PAS Warsaw Poland Center for Computer Modelling Systems Research Institute PAS Warsaw Poland Institute of Information Technology Warsaw University of Life Sciences Warsaw Poland Department of Quantitative Methods Rzeszow University of Technology Rzeszów Poland Polskie Towarzystwo Cyfrowe Lublin Poland

ISBN: (纸本)9781665492768

This paper refers to real-life data on energy consumption from three companies, connected to a medium voltage grid. The companies use single-, two-, or three-zone tariffs and the general characteristic of their activity is comparable. The input dataset contains hourly electricity consumption recorded from January 2020 to December 2020. The independent variables used for the study include weather, time-dependent factors, and aggregated energy factors. We perform the prediction of consumption using three methods: naive, multiple regression, and extreme gradient boosting regression. The performance of the methods is compared based on the MSE, RMSE, MAE, and MAPE metrics. The study shows that the scores achieved for the extreme gradient boosting method are higher than for the multiple regression. To gain the interpretability of the energy load forecasting and feature analysis the Shapley additive explanations method is used for the best model. As a result, a ranking of the most important factors is created. It shows the importance of aggregated energy factors and weather conditions while placing daylight and season at the bottom of the ranking.

关键词： Measurement Additives Load forecasting Tariffs Companies Medium voltage Predictive models

RANDOM PLANAR TREES AND THE JACOBIAN CONJECTURE

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bisi, Elia Dyszewski, Piotr Gantert, Nina Johnston, Samuel G.G. Prochno, Joscha Schmid, Dominik Institute of Statistics and Mathematical Methods in Economics TU Vienna Austria Mathematical Institute Wroclaw University Poland Department of Mathematics TU Munich Germany Department of Mathematics King’s College London United Kingdom Faculty of Computer Science and Mathematics University of Passau Germany Mathematical Institute University of Bonn Germany

We develop a probabilistic approach to the celebrated Jacobian conjecture, which states that any Keller map (i.e. any polynomial mapping F: Cn → Cn whose Jacobian determinant is a nonzero constant) has a compositional inverse which is also a polynomial. The Jacobian conjecture may be formulated in terms of a problem involving labellings of rooted trees;we give a new probabilistic derivation of this formulation using multi-type branching processes. Thereafter, we develop a simple and novel approach to the Jacobian conjecture in terms of a problem involving shuffling subtrees of d-Catalan trees, i.e. planar d-ary trees. We also show that, if one can construct a certain Markov chain on large d-Catalan trees which updates its value by randomly shuffling certain nearby subtrees, and in such a way that the stationary distribution of this chain is uniform, then the Jacobian conjecture is true. Finally, we use the local limit theory of large random trees to show that the subtree shuffling conjecture is true in a certain asymptotic sense, and thereafter use our machinery to prove an approximate version of the Jacobian conjecture, stating that inverses of Keller maps have small power series coefficients for their high degree *** Codes 60J80, 05C05, 14R15 (Primary), 60J10, 13F25 (Secondary) Copyright © 2023, The Authors. All rights reserved.

关键词： Polynomials

Human Factors in Model-Driven Engineering: Future Research Goals and Initiatives for MDE

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liebel, Grischa Klünder, Jil Hebig, Regina Lazik, Christopher Nunes, Inês Graßl, Isabella Steghöfer, Jan-Philipp Exelmans, Joeri Oertel, Julian Marquardt, Kai Juhnke, Katharina Schneider, Kurt Gren, Lucas Happe, Lucia Herrmann, Marc Wyrich, Marvin Tichy, Matthias Goulão, Miguel Wohlrab, Rebekka Kalantari, Reyhaneh Heinrich, Robert Greiner, Sandra Rukmono, Satrio Adi Chakraborty, Shalini Abrahão, Silvia Amaral, Vasco Department of Computer Science Reykjavik University Menntavegur 1 Reykjavik102 Iceland Software Engineering Group Leibniz University Hannover Welfengarten 1 Hannover30167 Germany Department of Software Engineering University of Rostock Albert-Einstein-Straße Rostock18057 Germany Department of Software Engineering Humboldt-Universität zu Berlin Unter den Linden 6 Berlin10099 Germany Frankfurt Germany Department of Software Engineering II University of Passau Innstraße 33 Passau94032 Germany XITASO GmbH Austraße 35 Augsburg86153 Germany Department of Computer Science University of Antwerp Middelheimlaan 1 Antwerp2020 Belgium Department of Informatics Karlsruhe Institute of Technology Am Fasanengarten 5 Karlsruhe75131 Germany SMT-EMI6 Carl Zeiss SMT GmbH Rudolf-Eber-Straße 2 Oberkochen73447 Germany Department of Computer Science and Engineering Chalmers | University of Gothenburg Gothenburg41127 Sweden Department of Interdisciplinary Didactics Karlsruhe Institute of Technology Engesserstr. 2 Karlsruhe75131 Germany Department of Computer Science Saarland University Saarland Informatics Campus Saarbrücken66123 Germany Institute of Software Engineering and Languages Ulm University James-Franck-Ring Ulm89081 Germany Department of Computer Science NOVA School of Science & Technology Campus de Caparica Caparica2829-516 Portugal Department of Engineering Design and Teaching Innovation University of Ottawa 800 King Edward Avenue OttawaK1N6N5 Canada KASTEL - Institute of Information Security and Dependability Karlsruhe Institute of Technology Am Fasanengarten 5 Karlsruhe75131 Germany Department of Computer Science University of Bern Bern3012 Switzerland Department of Mathematics and Computer Science Eindhoven University of Technology De Zaale Eindhoven5600 MB Netherlands Instituto Universitario Mixto de Tecnología Informática Universitat Politècnica de València Camino de Vera s/n Valencia46022 Spain

Purpose: Software modelling and Model-Driven Engineering (MDE) is traditionally studied from a technical perspective. However, one of the core motivations behind the use of software models is inherently human-centred. Models aim to enable practitioners to communicate about software designs, make software understandable, or make software easier to write through domain-specific modelling languages. Several recent studies challenge the idea that these aims can always be reached and indicate that human factors play a role in the success of MDE. However, there is an under-representation of research focusing on human factors in modelling. methods: During a GI-Dagstuhl seminar, topics related to human factors in modelling were discussed by 26 expert participants from research and industry. Results: In breakout groups, five topics were covered in depth, namely modelling human aspects, factors of modeller experience, diversity and inclusion in MDE, collaboration and MDE, and teaching human-aware MDE. Conclusion: We summarise our insights gained during the discussions on the five topics. We formulate research goals, questions, and propositions that support directing future initiatives towards an MDE community that is aware of and supportive of human factors and values. © 2024, CC BY.

关键词： Software design

AMBY: A development environment for youth to create conversational agents

学校读者我要写书评

暂无评论

International Journal of Child-computer Interaction 2023年 38卷

作者： Tian, Xiaoyi Kumar, Amit Solomon, Carly E Calder, Kaceja D Katuka, Gloria Ashiya Song, Yukyeong Celepkolu, Mehmet Pezzullo, Lydia Barrett, Joanne Boyer, Kristy Elizabeth Israel, Maya Department of Computer and Information Science and Engineering University of Florida Malachowsky Hall Gainesville Floria 32603 United States School of Teaching and Learning University of Florida 1221 SW 5th Ave Gainesville Floria 32601 United States

Conversational AIs such as Alexa and ChatGPT are increasingly ubiquitous in young people's lives, but these young users are often not afforded the opportunity to learn about the inner workings of these technologies. One of the most powerful ways to foster this learning is to empower youth to create AI that is personally and socially meaningful to them. We have built a novel development environment, AMBY–“AI Made By You”–for youth to create conversational agents. AMBY was iteratively designed with and for youth aged 12–13 through contextual inquiry and usability studies. AMBY is designed to foster AI learning with features that enable users to generate training datasets and visualize conversational flow. We report on results from a two-week summer camp deployment, and contribute design implications for conversational AI authoring tools that empower AI learning for youth. © 2023 Elsevier B.V.

关键词： AI education Artificial intelligence education Conversational agent Conversational AI Development environment K-12 Learning tool Middle school Youth

More than Extracting "Important" Sentences: the Application of PEGASUS 26

学校读者我要写书评

暂无评论

More than Extracting "Important" Sentences: the Application ...

26th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2021

作者： Yang, Ting-Hao Lu, Ching-Ching Hsu, Wen-Lian National Tsing Hua University Institue of Information Systems and Applications Hsinchu City Taiwan National Tsing Hua University Institute of Taiwan Langauges and Langauge Teaching Hsinchu City Taiwan Asia University Department of Computer Science and Information Engineering Taichung City Taiwan

ISBN: (纸本)9781665408257

Pre-trained language models may reduce the amount of training data required. Among the models, PEGASUS, a recently proposed self-supervised approach, is trained to generate the pseudo-summary given the partially masked document. PEGASUS uses gap sentence generation for summarization. The most important sentences are masked, and then PEGASUS predicts the masked sentences as the output summary. In this study, however, we apply PEGASUS in a novel downstream task. We reformulate the task to generate the masked question part in a primary math word problem. In the past research, PEGASUS has shown good potentials on the few-shot datasets, so we try a smaller set of primary math text problems as well. The fine-tuning dataset sizes used in this study are 1000, 500, 50, 10 samples. Their performance are measured by a non-weighted average of the ROUGE-1, ROUGE-2, and ROUGE-L scores. The results show the outstanding performance of PEGASUS applied in our novel downstream task. © 2021 IEEE.

关键词： Natural language processing systems

BAYESDIFF: ESTIMATING PIXEL-WISE UNCERTAINTY IN DIFFUSION VIA BAYESIAN INFERENCE

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kou, Siqi Gan, Lei Wang, Dequan Li, Chongxuan Deng, Zhijie Qing Yuan Research Institute SEIEE Shanghai Jiao Tong University China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China School of Computer Science Fudan University China Shanghai Artificial Intelligence Laboratory China

Diffusion models have impressive image generation capability, but low-quality generations still exist, and their identification remains challenging due to the lack of a proper sample-wise metric. To address this, we propose BayesDiff, a pixel-wise uncertainty estimator for generations from diffusion models based on Bayesian inference. In particular, we derive a novel uncertainty iteration principle to characterize the uncertainty dynamics in diffusion, and leverage the last-layer Laplace approximation for efficient Bayesian inference. The estimated pixel-wise uncertainty can not only be aggregated into a sample-wise metric to filter out low-fidelity images but also aids in augmenting successful generations and rectifying artifacts in failed generations in text-to-image tasks. Extensive experiments demonstrate the efficacy of BayesDiff and its promise for practical applications. Our code is available at https://***/karrykkk/BayesDiff. Copyright © 2023, The Authors. All rights reserved.

关键词： Pixels