Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)最新文献_第2页

Modeling Graphs Beyond Hyperbolic: Graph Neural Networks in Symmetric Positive Definite Matrices 超越双曲的图建模:对称正定矩阵中的图神经网络

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-06-24 DOI: 10.48550/arXiv.2306.14064

Weichen Zhao, Federico López, J. M. Riestenberg, M. Strube, Diaaeldin Taha, Steve J. Trettel

{"title":"Modeling Graphs Beyond Hyperbolic: Graph Neural Networks in Symmetric Positive Definite Matrices","authors":"Weichen Zhao, Federico López, J. M. Riestenberg, M. Strube, Diaaeldin Taha, Steve J. Trettel","doi":"10.48550/arXiv.2306.14064","DOIUrl":"https://doi.org/10.48550/arXiv.2306.14064","url":null,"abstract":"Recent research has shown that alignment between the structure of graph data and the geometry of an embedding space is crucial for learning high-quality representations of the data. The uniform geometry of Euclidean and hyperbolic spaces allows for representing graphs with uniform geometric and topological features, such as grids and hierarchies, with minimal distortion. However, real-world graph data is characterized by multiple types of geometric and topological features, necessitating more sophisticated geometric embedding spaces. In this work, we utilize the Riemannian symmetric space of symmetric positive definite matrices (SPD) to construct graph neural networks that can robustly handle complex graphs. To do this, we develop an innovative library that leverages the SPD gyrocalculus tools cite{lopez2021gyroSPD} to implement the building blocks of five popular graph neural networks in SPD. Experimental results demonstrate that our graph neural networks in SPD substantially outperform their counterparts in Euclidean and hyperbolic spaces, as well as the Cartesian product thereof, on complex graphs for node and graph classification tasks. We release the library and datasets at url{https://github.com/andyweizhao/SPD4GNNs}.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"26 1","pages":"122-139"},"PeriodicalIF":0.0,"publicationDate":"2023-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88258828","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

Binary domain generalization for sparsifying binary neural networks 稀疏化二值神经网络的二值域泛化

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-06-23 DOI: 10.48550/arXiv.2306.13515

Riccardo Schiavone, Francesco Galati, Maria A. Zuluaga

{"title":"Binary domain generalization for sparsifying binary neural networks","authors":"Riccardo Schiavone, Francesco Galati, Maria A. Zuluaga","doi":"10.48550/arXiv.2306.13515","DOIUrl":"https://doi.org/10.48550/arXiv.2306.13515","url":null,"abstract":"Binary neural networks (BNNs) are an attractive solution for developing and deploying deep neural network (DNN)-based applications in resource constrained devices. Despite their success, BNNs still suffer from a fixed and limited compression factor that may be explained by the fact that existing pruning methods for full-precision DNNs cannot be directly applied to BNNs. In fact, weight pruning of BNNs leads to performance degradation, which suggests that the standard binarization domain of BNNs is not well adapted for the task. This work proposes a novel more general binary domain that extends the standard binary one that is more robust to pruning techniques, thus guaranteeing improved compression and avoiding severe performance losses. We demonstrate a closed-form solution for quantizing the weights of a full-precision network into the proposed binary domain. Finally, we show the flexibility of our method, which can be combined with other pruning strategies. Experiments over CIFAR-10 and CIFAR-100 demonstrate that the novel approach is able to generate efficient sparse networks with reduced memory usage and run-time latency, while maintaining performance.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"120 1","pages":"123-140"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80730553","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: 0

Learning Conditional Instrumental Variable Representation for Causal Effect Estimation 学习因果效应估计的条件工具变量表示

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-06-21 DOI: 10.48550/arXiv.2306.12453

Debo Cheng, Ziqi Xu, Jiuyong Li, Lin Liu, T. Le, Jixue Liu

{"title":"Learning Conditional Instrumental Variable Representation for Causal Effect Estimation","authors":"Debo Cheng, Ziqi Xu, Jiuyong Li, Lin Liu, T. Le, Jixue Liu","doi":"10.48550/arXiv.2306.12453","DOIUrl":"https://doi.org/10.48550/arXiv.2306.12453","url":null,"abstract":"One of the fundamental challenges in causal inference is to estimate the causal effect of a treatment on its outcome of interest from observational data. However, causal effect estimation often suffers from the impacts of confounding bias caused by unmeasured confounders that affect both the treatment and the outcome. The instrumental variable (IV) approach is a powerful way to eliminate the confounding bias from latent confounders. However, the existing IV-based estimators require a nominated IV, and for a conditional IV (CIV) the corresponding conditioning set too, for causal effect estimation. This limits the application of IV-based estimators. In this paper, by leveraging the advantage of disentangled representation learning, we propose a novel method, named DVAE.CIV, for learning and disentangling the representations of CIV and the representations of its conditioning set for causal effect estimations from data with latent confounders. Extensive experimental results on both synthetic and real-world datasets demonstrate the superiority of the proposed DVAE.CIV method against the existing causal effect estimators.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"115 1","pages":"525-540"},"PeriodicalIF":0.0,"publicationDate":"2023-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85497514","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: 0

Pattern Mining for Anomaly Detection in Graphs: Application to Fraud in Public Procurement 图中异常检测的模式挖掘:在公共采购欺诈中的应用

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-06-19 DOI: 10.48550/arXiv.2306.10857

Lucas Potin, R. Figueiredo, Vincent Labatut, C. Largeron

{"title":"Pattern Mining for Anomaly Detection in Graphs: Application to Fraud in Public Procurement","authors":"Lucas Potin, R. Figueiredo, Vincent Labatut, C. Largeron","doi":"10.48550/arXiv.2306.10857","DOIUrl":"https://doi.org/10.48550/arXiv.2306.10857","url":null,"abstract":"In the context of public procurement, several indicators called red flags are used to estimate fraud risk. They are computed according to certain contract attributes and are therefore dependent on the proper filling of the contract and award notices. However, these attributes are very often missing in practice, which prohibits red flags computation. Traditional fraud detection approaches focus on tabular data only, considering each contract separately, and are therefore very sensitive to this issue. In this work, we adopt a graph-based method allowing leveraging relations between contracts, to compensate for the missing attributes. We propose PANG (Pattern-Based Anomaly Detection in Graphs), a general supervised framework relying on pattern extraction to detect anomalous graphs in a collection of attributed graphs. Notably, it is able to identify induced subgraphs, a type of pattern widely overlooked in the literature. When benchmarked on standard datasets, its predictive performance is on par with state-of-the-art methods, with the additional advantage of being explainable. These experiments also reveal that induced patterns are more discriminative on certain datasets. When applying PANG to public procurement data, the prediction is superior to other methods, and it identifies subgraph patterns that are characteristic of fraud-prone situations, thereby making it possible to better understand fraudulent behavior.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"14 1","pages":"69-87"},"PeriodicalIF":0.0,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81411534","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: 1

FDTI: Fine-grained Deep Traffic Inference with Roadnet-enriched Graph 基于路网富图的细粒度深度交通推断

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-06-19 DOI: 10.48550/arXiv.2306.10945

Zhanyu Liu, Chumeng Liang, Guanjie Zheng, Hua Wei

{"title":"FDTI: Fine-grained Deep Traffic Inference with Roadnet-enriched Graph","authors":"Zhanyu Liu, Chumeng Liang, Guanjie Zheng, Hua Wei","doi":"10.48550/arXiv.2306.10945","DOIUrl":"https://doi.org/10.48550/arXiv.2306.10945","url":null,"abstract":"This paper proposes the fine-grained traffic prediction task (e.g. interval between data points is 1 minute), which is essential to traffic-related downstream applications. Under this setting, traffic flow is highly influenced by traffic signals and the correlation between traffic nodes is dynamic. As a result, the traffic data is non-smooth between nodes, and hard to utilize previous methods which focus on smooth traffic data. To address this problem, we propose Fine-grained Deep Traffic Inference, termed as FDTI. Specifically, we construct a fine-grained traffic graph based on traffic signals to model the inter-road relations. Then, a physically-interpretable dynamic mobility convolution module is proposed to capture vehicle moving dynamics controlled by the traffic signals. Furthermore, traffic flow conservation is introduced to accurately infer future volume. Extensive experiments demonstrate that our method achieves state-of-the-art performance and learned traffic dynamics with good properties. To the best of our knowledge, we are the first to conduct the city-level fine-grained traffic prediction.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"53 1","pages":"174-191"},"PeriodicalIF":0.0,"publicationDate":"2023-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87785705","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: 1

Neural models for Factual Inconsistency Classification with Explanations 带有解释的事实不一致分类的神经模型

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-06-15 DOI: 10.48550/arXiv.2306.08872

Tathagata Raha, Mukund Choudhary, Abhinav Menon, Harshit Gupta, KV Aditya Srivatsa, Manish Gupta, Vasudeva Varma

{"title":"Neural models for Factual Inconsistency Classification with Explanations","authors":"Tathagata Raha, Mukund Choudhary, Abhinav Menon, Harshit Gupta, KV Aditya Srivatsa, Manish Gupta, Vasudeva Varma","doi":"10.48550/arXiv.2306.08872","DOIUrl":"https://doi.org/10.48550/arXiv.2306.08872","url":null,"abstract":"Factual consistency is one of the most important requirements when editing high quality documents. It is extremely important for automatic text generation systems like summarization, question answering, dialog modeling, and language modeling. Still, automated factual inconsistency detection is rather under-studied. Existing work has focused on (a) finding fake news keeping a knowledge base in context, or (b) detecting broad contradiction (as part of natural language inference literature). However, there has been no work on detecting and explaining types of factual inconsistencies in text, without any knowledge base in context. In this paper, we leverage existing work in linguistics to formally define five types of factual inconsistencies. Based on this categorization, we contribute a novel dataset, FICLE (Factual Inconsistency CLassification with Explanation), with ~8K samples where each sample consists of two sentences (claim and context) annotated with type and span of inconsistency. When the inconsistency relates to an entity type, it is labeled as well at two levels (coarse and fine-grained). Further, we leverage this dataset to train a pipeline of four neural models to predict inconsistency type with explanations, given a (claim, context) sentence pair. Explanations include inconsistent claim fact triple, inconsistent context span, inconsistent claim component, coarse and fine-grained inconsistent entity types. The proposed system first predicts inconsistent spans from claim and context; and then uses them to predict inconsistency types and inconsistent entity types (when inconsistency is due to entities). We experiment with multiple Transformer-based natural language classification as well as generative models, and find that DeBERTa performs the best. Our proposed methods provide a weighted F1 of ~87% for inconsistency type classification across the five classes.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"92 1","pages":"410-427"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80597684","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

Towards Memory-Efficient Training for Extremely Large Output Spaces - Learning with 500k Labels on a Single Commodity GPU 面向超大输出空间的高效内存训练——在单个商用GPU上学习500k个标签

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-06-06 DOI: 10.48550/arXiv.2306.03725

Erik Schultheis, Rohit Babbar

引用次数: 1

Lumos in the Night Sky: AI-enabled Visual Tool for Exploring Night-Time Light Patterns 夜空中的荧光:用于探索夜间光线模式的ai支持的视觉工具

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-06-05 DOI: 10.48550/arXiv.2306.03195

Jakob Hederich, Shreya Ghosh, Zeyu He, P. Mitra

引用次数: 0

Symbolic Regression via Control Variable Genetic Programming 通过控制变量遗传规划的符号回归

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-05-25 DOI: 10.48550/arXiv.2306.08057

Nan Jiang, Yexiang Xue

{"title":"Symbolic Regression via Control Variable Genetic Programming","authors":"Nan Jiang, Yexiang Xue","doi":"10.48550/arXiv.2306.08057","DOIUrl":"https://doi.org/10.48550/arXiv.2306.08057","url":null,"abstract":"Learning symbolic expressions directly from experiment data is a vital step in AI-driven scientific discovery. Nevertheless, state-of-the-art approaches are limited to learning simple expressions. Regressing expressions involving many independent variables still remain out of reach. Motivated by the control variable experiments widely utilized in science, we propose Control Variable Genetic Programming (CVGP) for symbolic regression over many independent variables. CVGP expedites symbolic expression discovery via customized experiment design, rather than learning from a fixed dataset collected a priori. CVGP starts by fitting simple expressions involving a small set of independent variables using genetic programming, under controlled experiments where other variables are held as constants. It then extends expressions learned in previous generations by adding new independent variables, using new control variable experiments in which these variables are allowed to vary. Theoretically, we show CVGP as an incremental building approach can yield an exponential reduction in the search space when learning a class of expressions. Experimentally, CVGP outperforms several baselines in learning symbolic expressions involving multiple independent variables.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":"90 10 1","pages":"178-195"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87719531","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: 1

Interpretable Regional Descriptors: Hyperbox-Based Local Explanations 可解释的区域描述符:基于hyperbox的局部解释

Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference) Pub Date : 2023-05-04 DOI: 10.48550/arXiv.2305.02780

Susanne Dandl, Giuseppe Casalicchio, Bernd Bischl, Ludwig Bothmann

引用次数: 0