Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)最新文献_第8页

Learning Optimal Transport Between two Empirical Distributions with Normalizing Flows 用正规化流学习两个经验分布之间的最优传输

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-07-04 DOI: 10.48550/arXiv.2207.01246

Florentin Coeurdoux, N. Dobigeon, P. Chainais

{"title":"Learning Optimal Transport Between two Empirical Distributions with Normalizing Flows","authors":"Florentin Coeurdoux, N. Dobigeon, P. Chainais","doi":"10.48550/arXiv.2207.01246","DOIUrl":"https://doi.org/10.48550/arXiv.2207.01246","url":null,"abstract":"Optimal transport (OT) provides effective tools for comparing and mapping probability measures. We propose to leverage the flexibility of neural networks to learn an approximate optimal transport map. More precisely, we present a new and original method to address the problem of transporting a finite set of samples associated with a first underlying unknown distribution towards another finite set of samples drawn from another unknown distribution. We show that a particular instance of invertible neural networks, namely the normalizing flows, can be used to approximate the solution of this OT problem between a pair of empirical distributions. To this aim, we propose to relax the Monge formulation of OT by replacing the equality constraint on the push-forward measure by the minimization of the corresponding Wasserstein distance. The push-forward operator to be retrieved is then restricted to be a normalizing flow which is trained by optimizing the resulting cost function. This approach allows the transport map to be discretized as a composition of functions. Each of these functions is associated to one sub-flow of the network, whose output provides intermediate steps of the transport between the original and target measures. This discretization yields also a set of intermediate barycenters between the two measures of interest. Experiments conducted on toy examples as well as a challenging task of unsupervised translation demonstrate the interest of the proposed method. Finally, some experiments show that the proposed approach leads to a good approximation of the true OT.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"13 1","pages":"275-290"},"PeriodicalIF":0.0,"publicationDate":"2022-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73301759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Detection of ADHD based on Eye Movements during Natural Viewing 基于自然观看时眼球运动的ADHD检测

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-07-04 DOI: 10.48550/arXiv.2207.01377

Shuwen Deng, Paul Prasse, D. R. Reich, S. Dziemian, Maja Stegenwallner-Schütz, Daniel G. Krakowczyk, Silvia Makowski, N. Langer, T. Scheffer, L. Jäger

引用次数: 6

Transforming PageRank into an Infinite-Depth Graph Neural Network 将PageRank转化为无限深度图神经网络

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-07-01 DOI: 10.48550/arXiv.2207.00684

Andreas Roth, T. Liebig

{"title":"Transforming PageRank into an Infinite-Depth Graph Neural Network","authors":"Andreas Roth, T. Liebig","doi":"10.48550/arXiv.2207.00684","DOIUrl":"https://doi.org/10.48550/arXiv.2207.00684","url":null,"abstract":"Popular graph neural networks are shallow models, despite the success of very deep architectures in other application domains of deep learning. This reduces the modeling capacity and leaves models unable to capture long-range relationships. The primary reason for the shallow design results from over-smoothing, which leads node states to become more similar with increased depth. We build on the close connection between GNNs and PageRank, for which personalized PageRank introduces the consideration of a personalization vector. Adopting this idea, we propose the Personalized PageRank Graph Neural Network (PPRGNN), which extends the graph convolutional network to an infinite-depth model that has a chance to reset the neighbor aggregation back to the initial state in each iteration. We introduce a nicely interpretable tweak to the chance of resetting and prove the convergence of our approach to a unique solution without placing any constraints, even when taking infinitely many neighbor aggregations. As in personalized PageRank, our result does not suffer from over-smoothing. While doing so, time complexity remains linear while we keep memory complexity constant, independently of the depth of the network, making it scale well to large graphs. We empirically show the effectiveness of our approach for various node and graph classification tasks. PPRGNN outperforms comparable methods in almost all cases.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"34 1","pages":"469-484"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89750075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Is this bug severe? A text-cum-graph based model for bug severity prediction 这种病严重吗?基于文本和图形的bug严重性预测模型

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-07-01 DOI: 10.48550/arXiv.2207.00623

Rima Hazra, Arpit Dwivedi, Animesh Mukherjee

引用次数: 2

Open Data Science to Fight COVID-19: Winning the 500k XPRIZE Pandemic Response Challenge 开放数据科学对抗COVID-19:赢得50万XPRIZE大流行应对挑战

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-07-01 DOI: 10.1007/978-3-030-86514-6_24

M. Lozano, Òscar Garibo i Orts, Eloy Piñol, M. Rebollo, K. Polotskaya, M. Garcia-March, J. Conejero, F. Escolano, N. Oliver

引用次数: 16

MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors MEAD:一种评估对抗样本检测器的多臂方法

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-06-30 DOI: 10.48550/arXiv.2206.15415

Federica Granese, Marine Picot, Marco Romanelli, Francisco Messina, P. Piantanida

{"title":"MEAD: A Multi-Armed Approach for Evaluation of Adversarial Examples Detectors","authors":"Federica Granese, Marine Picot, Marco Romanelli, Francisco Messina, P. Piantanida","doi":"10.48550/arXiv.2206.15415","DOIUrl":"https://doi.org/10.48550/arXiv.2206.15415","url":null,"abstract":"Detection of adversarial examples has been a hot topic in the last years due to its importance for safely deploying machine learning algorithms in critical applications. However, the detection methods are generally validated by assuming a single implicitly known attack strategy, which does not necessarily account for real-life threats. Indeed, this can lead to an overoptimistic assessment of the detectors' performance and may induce some bias in the comparison between competing detection schemes. We propose a novel multi-armed framework, called MEAD, for evaluating detectors based on several attack strategies to overcome this limitation. Among them, we make use of three new objectives to generate attacks. The proposed performance metric is based on the worst-case scenario: detection is successful if and only if all different attacks are correctly recognized. Empirically, we show the effectiveness of our approach. Moreover, the poor performance obtained for state-of-the-art detectors opens a new exciting line of research.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"9 2 1","pages":"286-303"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78695879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Customized Conversational Recommender Systems 定制会话推荐系统

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-06-30 DOI: 10.48550/arXiv.2207.00814

Shuokai Li, Yongchun Zhu, Ruobing Xie, Zhenwei Tang, Zhao Zhang, Fuzhen Zhuang, Qing He, Hui Xiong

{"title":"Customized Conversational Recommender Systems","authors":"Shuokai Li, Yongchun Zhu, Ruobing Xie, Zhenwei Tang, Zhao Zhang, Fuzhen Zhuang, Qing He, Hui Xiong","doi":"10.48550/arXiv.2207.00814","DOIUrl":"https://doi.org/10.48550/arXiv.2207.00814","url":null,"abstract":"Conversational recommender systems (CRS) aim to capture user's current intentions and provide recommendations through real-time multi-turn conversational interactions. As a human-machine interactive system, it is essential for CRS to improve the user experience. However, most CRS methods neglect the importance of user experience. In this paper, we propose two key points for CRS to improve the user experience: (1) Speaking like a human, human can speak with different styles according to the current dialogue context. (2) Identifying fine-grained intentions, even for the same utterance, different users have diverse finegrained intentions, which are related to users' inherent preference. Based on the observations, we propose a novel CRS model, coined Customized Conversational Recommender System (CCRS), which customizes CRS model for users from three perspectives. For human-like dialogue services, we propose multi-style dialogue response generator which selects context-aware speaking style for utterance generation. To provide personalized recommendations, we extract user's current fine-grained intentions from dialogue context with the guidance of user's inherent preferences. Finally, to customize the model parameters for each user, we train the model from the meta-learning perspective. Extensive experiments and a series of analyses have shown the superiority of our CCRS on both the recommendation and dialogue services.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"22 1","pages":"740-756"},"PeriodicalIF":0.0,"publicationDate":"2022-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80832037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Placing (Historical) Facts on a Timeline: A Classification cum Coref Resolution Approach 在时间轴上放置(历史)事实:分类和核心解决方法

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-06-28 DOI: 10.48550/arXiv.2206.14089

Sayantan Adak, Altaf Ahmad, Aditya Basu, Animesh Mukherjee

引用次数: 0

DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems DistSPECTRL:多智能体强化学习系统中的分布式规范

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-06-28 DOI: 10.48550/arXiv.2206.13754

Joe Eappen, S. Jagannathan

{"title":"DistSPECTRL: Distributing Specifications in Multi-Agent Reinforcement Learning Systems","authors":"Joe Eappen, S. Jagannathan","doi":"10.48550/arXiv.2206.13754","DOIUrl":"https://doi.org/10.48550/arXiv.2206.13754","url":null,"abstract":"While notable progress has been made in specifying and learning objectives for general cyber-physical systems, applying these methods to distributed multi-agent systems still pose significant challenges. Among these are the need to (a) craft specification primitives that allow expression and interplay of both local and global objectives, (b) tame explosion in the state and action spaces to enable effective learning, and (c) minimize coordination frequency and the set of engaged participants for global objectives. To address these challenges, we propose a novel specification framework that allows natural composition of local and global objectives used to guide training of a multi-agent system. Our technique enables learning expressive policies that allow agents to operate in a coordination-free manner for local objectives, while using a decentralized communication protocol for enforcing global ones. Experimental results support our claim that sophisticated multi-agent distributed planning problems can be effectively realized using specification-guided learning.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"1 1","pages":"233-250"},"PeriodicalIF":0.0,"publicationDate":"2022-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87348667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Learning to Control Local Search for Combinatorial Optimization 学习控制组合优化中的局部搜索

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2022-06-27 DOI: 10.48550/arXiv.2206.13181

Jonas K. Falkner, Daniela Thyssens, Ahmad Bdeir, L. Schmidt-Thieme

引用次数: 4