检索结果-内蒙古大学图书馆

Causal Discovery in Astrophysics: Unraveling Supermassive Black Hole and Galaxy Coevolution

ASTROPHYSICAL JOURNAL 2025年第2期979卷 212-212页

作者： Jin, Zehao Pasquato, Mario Davis, Benjamin L. Deleu, Tristan Luo, Yu Cho, Changhyun Lemos, Pablo Perreault-Levasseur, Laurence Bengio, Yoshua Kang, Xi Maccio, Andrea Valerio Hezaveh, Yashar New York Univ Abu Dhabi POB 129188 Abu Dhabi U Arab Emirates Mohammed Bin Rashid Space Ctr POB 129188 Dubai U Arab Emirates Montreal Inst Astrophys Data Anal & Machine Learni Montreal PQ Canada Quebec Artificial Intelligence Inst Montreal Inst Learning Algorithms Mila Montreal PQ Canada Univ Montreal Dept Phys 1375 Ave Therese-Lavoie-Roux Montreal PQ Canada Univ Padua Dipartimento Fis & Astron Vicolo Osservatorio 5 Padua Italy Ist Astrofis Spaziale & Fis Cosm INAF IASF MI Via Alfonso Corti 12 I-20133 Milan Italy Univ Montreal Dept Informat & Rech Operat 2920 Chemin Tour Montreal PQ Canada Hunan Normal Univ Sch Phys & Elect Dept Phys Changsha 410081 Peoples R China Purple Mt Observ 10 Yuan Hua Rd Nanjing 210034 Peoples R China Flatiron Inst Ctr Computat Astrophys New York NY USA Zhejiang Univ Inst Astron Hangzhou 310027 Peoples R China Max Planck Inst Astron Konigstuhl 17 Heidelberg Germany

Correlation does not imply causation, but patterns of statistical association between variables can be exploited to infer a causal structure (even with purely observational data) with the burgeoning field of causal discovery. As a purely observational science, astrophysics has much to gain by exploiting these new methods. The supermassive black hole (SMBH)-galaxy interaction has long been constrained by observed scaling relations, which is low-scatter correlations between variables such as SMBH mass and the central velocity dispersion of stars in a host galaxy's bulge. This study, using advanced causal discovery techniques and an up-to-date data set, reveals a causal link between galaxy properties and dynamically measured SMBH masses. We apply a score-based Bayesian framework to compute the exact conditional probabilities of every causal structure that could possibly describe our galaxy sample. With the exact posterior distribution, we determine the most likely causal structures and notice a probable causal reversal when separating galaxies by morphology. In elliptical galaxies, bulge properties (built from major mergers) tend to influence SMBH growth, while, in spiral galaxies, SMBHs are seen to affect host galaxy properties, potentially through feedback in gas-rich environments. For spiral galaxies, SMBHs progressively quench star formation, whereas, in elliptical galaxies, quenching is complete, and the causal connection has reversed. Our findings support theoretical models of hierarchical assembly of galaxies and active galactic nuclei feedback regulating galaxy evolution. Our study suggests the potentiality for further exploration of causal links in astrophysical and cosmological scaling relations, as well as any other observational science.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unimodal Probability Distributions for Deep Ordinal Classification 34

Unimodal Probability Distributions for Deep Ordinal Classifi...

引用

34th International Conference on Machine learning

作者： Beckham, Christopher Pal, Christopher Montreal Inst Learning Algorithms Quebec City PQ Canada

ISBN: (纸本)9781510855144

Probability distributions produced by the cross-entropy loss for ordinal classification problems can possess undesired properties. We propose a straightforward technique to constrain discrete ordinal probability distributions to be unimodal via the use of the Poisson and binomial probability distributions. We evaluate this approach in the context of deep learning on two large ordinal image datasets, obtaining promising results.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

learning and fine-tuning a generic value-selection heuristic inside a constraint programming solver

引用

CONSTRAINTS 2024年第3-4期29卷 234-260页

作者： Marty, Tom Boisvert, Leo Francois, Tristan Tessier, Pierre Gautier, Louis Rousseau, Louis-Martin Cappart, Quentin Polytech Montreal Montreal PQ Canada Ecole Polytech Palaiseau France Quebec Inst Learning Algorithms MILA Montreal PQ Canada

Constraint programming is known for being an efficient approach to solving combinatorial problems. Important design choices in a solver are the branching heuristics, designed to lead the search to the best solutions in a minimum amount of time. However, developing these heuristics is a time-consuming process that requires problem-specific expertise. This observation has motivated many efforts to use machine learning to automatically learn efficient heuristics without expert intervention. Although several generic variable-selection heuristics are available in the literature, the options for value-selection heuristics are more scarce. We propose to tackle this issue by introducing a generic learning procedure that can be used to obtain a value-selection heuristic inside a constraint programming solver. This has been achieved thanks to the combination of a deep Q-learning algorithm, a tailored reward signal, and a heterogeneous graph neural network. Experiments on graph coloring, maximum independent set, maximum cut, and minimum vertex cover problems show that this framework competes with the well-known impact-based and activity-based search heuristics and can find solutions close to optimality without requiring a large number of backtracks. Additionally, we observe that fine-tuning a model with a different problem class can accelerate the learning process.

关键词： Constraint programming Branching heuristics Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Behavioural equivalences for continuous-time Markov processes

引用

MATHEMATICAL STRUCTURES IN COMPUTER SCIENCE 2023年第4-5期33卷 222-258页

作者： Chen, Linan Clerc, Florence Panangaden, Prakash McGill Univ Dept Math & Stat Montreal PQ Canada Sch Comp Sci McGil lUnivers DEEL Quebec Montreal PQ Canada McGill Univ Montreal Inst Learning Algorithms MILA Sch Comp Sci Montreal PQ Canada

Bisimulation is a concept that captures behavioural equivalence of states in a variety of types of transition systems. It has been widely studied in a discrete-time setting. The core of this work is to generalise the discrete-time picture to continuous time by providing a notion of behavioural equivalence for continuous-time Markov processes. In Chen et al. [(2019). Electronic Notes in Theoretical Computer Science 347 45-63.], we proposed two equivalent definitions of bisimulation for continuous-time stochastic processes where the evolution is a flow through time: the first one as an equivalence relation and the second one as a cospan of morphisms. In Chen et al. [(2020). Electronic Notes in Theoretical Computer Science.], we developed the theory further: we introduced different concepts that correspond to different behavioural equivalences and compared them to bisimulation. In particular, we studied the relation between bisimulation and symmetry groups of the dynamics. We also provided a game interpretation for two of the behavioural equivalences. The present work unifies the cited conference presentations and gives detailed proofs.

关键词： Stochastic processes Markov processes continuous time bisimulation diffusion

来源：评论

学校读者我要写书评

暂无评论

DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases 19

DivGraphPointer: A Graph Pointer Network for Extracting Dive...

引用

42nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)

作者： Sun, Zhiqing Tang, Jian Du, Pan Deng, Zhi-Hong Nie, Jian-Yun Peking Univ Beijing Peoples R China HEC Montreal Algorithms Mila Quebec Inst Learning CIFAR AI Res Chair Montreal PQ Canada Univ Montreal Montreal PQ Canada

ISBN: (纸本)9781450361729

Keyphrase extraction from documents is useful to a variety of applications such as information retrieval and document summarization. This paper presents an end-to-end method called DivGraphPointer for extracting a set of diversified keyphrases from a document. DivGraphPointer combines the advantages of traditional graph-based ranking methods and recent neural network-based approaches. Specifically, given a document, a word graph is constructed from the document based on word proximity and is encoded with graph convolutional networks, which effectively capture document-level word salience by modeling long-range dependency between words in the document and aggregating multiple appearances of identical words into one node. Furthermore, we propose a diversified point network to generate a set of diverse keyphrases out of the word graph in the decoding process. Experimental results on five benchmark data sets show that our proposed method significantly outperforms the existing state-of-the-art approaches.

关键词： graph neural networks keyphrase extraction diversified pointer network document-level word salience

来源：评论

学校读者我要写书评

暂无评论

vGraph: A Generative Model for Joint Community Detection and Node Representation learning

vGraph: A Generative Model for Joint Community Detection and...

引用

33rd Conference on Neural Information Processing Systems (NeurIPS)

作者： Sun, Fan-Yun Qu, Meng Hoffmann, Jordan Huang, Chin-Wei Tang, Jian Natl Taiwan Univ Taipei Taiwan Mila Quebec Inst Learning Algorithms Montreal PQ Canada Harvard Univ Cambridge MA 02138 USA Element AI Montreal PQ Canada HEC Montreal Montreal PQ Canada CIFAR AI Res Chair Montreal PQ Canada

This paper focuses on two fundamental tasks of graph analysis: community detection and node representation learning, which capture the global and local structures of graphs, respectively. In the current literature, these two tasks are usually independently studied while they are actually highly correlated. We propose a probabilistic generative model called vGraph to learn community membership and node representation collaboratively. Specifically, we assume that each node can be represented as a mixture of communities, and each community is defined as a multinomial distribution over nodes. Both the mixing coefficients and the community distribution are parameterized by the low-dimensional representations of the nodes and communities. We designed an effective variational inference algorithm which regularizes the community membership of neighboring nodes to be similar in the latent space. Experimental results on multiple real-world graphs show that vGraph is very effective in both community detection and node representation learning, outperforming many competitive baselines in both tasks. We show that the framework of vGraph is quite flexible and can be easily extended to detect hierarchical communities.

关键词： Inference engines

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Information Diffusion Prediction with Reinforced Recurrent Networks 28

Multi-scale Information Diffusion Prediction with Reinforced...

引用

28th International Joint Conference on Artificial Intelligence

作者： Yang, Cheng Tang, Jian Sun, Maosong Cui, Ganqu Liu, Zhiyuan Tsinghua Univ Dept Comp Sci & Technol Beijing Peoples R China Tsinghua Univ Inst Artificial Intelligence Beijing Peoples R China Tsinghua Univ State Key Lab Intelligent Technol & Syst Beijing Peoples R China Mila Quebec Inst Learning Algorithms Montreal PQ Canada HEC Montreal Montreal PQ Canada Canadian Inst Adv Res CIFAR Toronto ON Canada

ISBN: (纸本)9780999241141

Information diffusion prediction is an important task which studies how information items spread among users. With the success of deep learning techniques, recurrent neural networks (RNNs) have shown their powerful capability in modeling information diffusion as sequential data. However, previous works focused on either microscopic diffusion prediction which aims at guessing the next influenced user or macroscopic diffusion prediction which estimates the total numbers of influenced users during the diffusion process. To the best of our knowledge, no previous works have suggested a unified model for both microscopic and macroscopic scales. In this paper, we propose a novel multi-scale diffusion prediction model based on reinforcement learning (RL). RL incorporates the macroscopic diffusion size information into the RNN-based microscopic diffusion model by addressing the non-differentiable problem. We also employ an effective structural context extraction strategy to utilize the underlying social graph information. Experimental results show that our proposed model outperforms state-of-the-art baseline models on both microscopic and macroscopic diffusion predictions on three real-world datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Full-Scale Information Diffusion Prediction With Reinforced Recurrent Networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2023年第5期34卷 2271-2283页

作者： Yang, Cheng Wang, Hao Tang, Jian Shi, Chuan Sun, Maosong Cui, Ganqu Liu, Zhiyuan Beijing Univ Posts & Telecommun Sch Comp Sci Beijing 100876 Peoples R China Mila Quebec Inst Learning Algorithms Montreal PQ H2S 3H1 Canada HEC Montreal Montreal PQ H3T 2A7 Canada Canadian Inst Adv Res CIFAR Toronto ON M5G 1Z8 Canada Tsinghua Univ Dept Comp Sci & Technol Beijing 100084 Peoples R China

Information diffusion prediction is an important task, which studies how information items spread among users. With the success of deep learning techniques, recurrent neural networks (RNNs) have shown their powerful capability in modeling information diffusion as sequential data. However, previous works focused on either microscopic diffusion prediction, which aims at guessing who will be the next influenced user at what time, or macroscopic diffusion prediction, which estimates the total numbers of influenced users during the diffusion process. To the best of our knowledge, few attempts have been made to suggest a unified model for both microscopic and macroscopic scales. In this article, we propose a novel full-scale diffusion prediction model based on reinforcement learning (RL). RL incorporates the macroscopic diffusion size information into the RNN-based microscopic diffusion model by addressing the nondifferentiable problem. We also employ an effective structural context extraction strategy to utilize the underlying social graph information. Experimental results show that our proposed model outperforms state-of-the-art baseline models on both microscopic and macroscopic diffusion predictions on three real-world datasets.

关键词： Microscopy Predictive models Task analysis Integrated circuit modeling Data mining Recurrent neural networks Feature extraction Information diffusion prediction recurrent neural networks (RNNs) reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

An End-to-End Neighborhood-based Interaction Model for Knowledge-enhanced Recommendation 1

An End-to-End Neighborhood-based Interaction Model for Knowl...

引用

1st International Workshop on Deep learning Practice for High-Dimensional Sparse Data with KDD (DLP KDD)

作者： Qu, Yanru Bai, Ting Zhang, Weinan Nie, Jianyun Tang, Jian Shanghai Jiao Tong Univ Shanghai Peoples R China Beijing Univ Posts & Telecommun Beijing Peoples R China Renmin Univ China Beijing Peoples R China Univ Montreal Montreal PQ Canada Mila Quebec Inst Learning Algorithms Montreal PQ Canada HEC Montreal Montreal PQ Canada CIFAR AI Res Chair Edmonton AB Canada

ISBN: (纸本)9781450367837

This paper studies graph-based recommendation, where an interaction graph is built from historical responses and is leveraged to alleviate data sparsity and cold start problems. We reveal an early summarization problem in previous graph-based models, and propose Neighborhood Interaction (NI) model to capture each neighbor pair (between user-side and item-side) distinctively. NI model is more expressive and captures more complicated structural patterns behind user-item interactions. To enrich the neighborhood information, we also introduce Graph Neural Networks (GNNs) and Knowledge Graphs (KGs) to NI, resulting an end-to-end model, namely Knowledge-enhanced Neighborhood Interaction (KNI). Our experiments on 4 real world datasets show that, compared with state-of-the-art feature-based, meta path-based, and KG-based recommendation models, KNI achieves superior performance in click-through rate prediction (1.1%-8.4% absolute AUC improvements) and outperforms by a wide margin in top-N recommendation.

关键词： Knowledge Graph Neighborhood-based Interaction Collaborative Recommendation

来源：评论

学校读者我要写书评

暂无评论

HOW TRANSFERABLE ARE FEATURES IN CONVOLUTIONAL NEURAL NETWORK ACOUSTIC MODELS ACROSS LANGUAGES? 44

HOW TRANSFERABLE ARE FEATURES IN CONVOLUTIONAL NEURAL NETWOR...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Thompson, Jessica A. F. Schoenwiesner, Marc Bengio, Yoshua Willett, Daniel Univ Montreal Int Lab Brain Mus & Sound Res BRAMS Montreal PQ Canada Quebec Inst Learning Algorithms Mila Montreal PQ Canada CRBLM Montreal PQ Canada Univ Leipzig Inst Biol Leipzig Germany Nuance Commun Aachen Germany

ISBN: (纸本)9781479981311

Characterization of the representations learned in intermediate layers of deep networks can provide valuable insight into the nature of a task and can guide the development of well-tailored learning strategies. Here we study convolutional neural network (CNN)-based acoustic models in the context of automatic speech recognition. Adapting a method proposed by [1], we measure the transferability of each layer between English, Dutch and German to assess their language-specificity. We observed three distinct regions of transferability: (1) the first two layers were entirely transferable between languages, (2) layers 2-8 were also highly transferable but we found some evidence of language specificity, (3) the subsequent fully connected layers were more language specific but could be successfully finetuned to the target language. To further probe the effect of weight freezing, we performed follow-up experiments using freeze-training [2]. Our results are consistent with the observation that CNNs converge 'bottom up' during training and demonstrate the benefit of freeze training, especially for transfer learning.

关键词： CNNs acoustic modeling interpretability transfer learning language-specificity freeze training

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：