Data Mining and Knowledge Discovery最新文献

{"title":"Effective interpretable learning for large-scale categorical data","authors":"Yishuo Zhang, Nayyar Zaidi, Jiahui Zhou, Tao Wang, Gang Li","doi":"10.1007/s10618-024-01030-1","DOIUrl":"https://doi.org/10.1007/s10618-024-01030-1","url":null,"abstract":"<p>Large scale categorical datasets are ubiquitous in machine learning and the success of most deployed machine learning models rely on how effectively the features are engineered. For large-scale datasets, parametric methods are generally used, among which three strategies for feature engineering are quite common. The first strategy focuses on managing the breadth (or width) of a network, e.g., generalized linear models (aka. <span>wide learning</span>). The second strategy focuses on the depth of a network, e.g., Artificial Neural networks or <span>ANN</span> (aka. <span>deep learning</span>). The third strategy relies on factorizing the interaction terms, e.g., Factorization Machines (aka. <span>factorized learning</span>). Each of these strategies brings its own advantages and disadvantages. Recently, it has been shown that for categorical data, combination of various strategies leads to excellent results. For example, <span>WD</span>-Learning, <span>xdeepFM</span>, etc., leads to state-of-the-art results. Following the trend, in this work, we have proposed another learning framework—<span>WBDF</span>-Learning, based on the combination of <span>wide</span>, <span>deep</span>, <span>factorization</span>, and a newly introduced component named <span>Broad Interaction network</span> (<span>BIN</span>). <span>BIN</span> is in the form of a Bayesian network classifier whose structure is learned apriori, and parameters are learned by optimizing a joint objective function along with <span>wide</span>, <span>deep</span> and <span>factorized</span> parts. We denote the learning of <span>BIN</span> parameters as <span>broad learning</span>. Additionally, the parameters of <span>BIN</span> are constrained to be actual probabilities—therefore, it is extremely interpretable. Furthermore, one can sample or generate data from <span>BIN</span>, which can facilitate learning and provides a framework for <i>knowledge-guided machine learning</i>. We demonstrate that our proposed framework possesses the resilience to maintain excellent classification performance when confronted with biased datasets. We evaluate the efficacy of our framework in terms of classification performance on various benchmark large-scale categorical datasets and compare against state-of-the-art methods. It is shown that, <span>WBDF</span> framework (a) exhibits superior performance on classification tasks, (b) boasts outstanding interpretability and (c) demonstrates exceptional resilience and effectiveness in scenarios involving skewed distributions.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"22 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141172239","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"WaveLSea: helping experts interactively explore pattern mining search spaces","authors":"Etienne Lehembre, Bruno Cremilleux, Albrecht Zimmermann, Bertrand Cuissart, Abdelkader Ouali","doi":"10.1007/s10618-024-01037-8","DOIUrl":"https://doi.org/10.1007/s10618-024-01037-8","url":null,"abstract":"<p>This article presents the method Wave Top-k Random-d Lineage Search (WaveLSea) which guides an expert through data mining results according to her interest. The method exploits expert feedback, combined with the relation between patterns to spread the expert’s interest. It avoids the typical feature definition step commonly used in interactive data mining which limits the flexibility of the discovery process. We empirically demonstrate that WaveLSea returns the most relevant results for the user’s subjective interest. Even with imperfect feedback, WaveLSea behavior remains robust as it primarily still delivers most interesting results during experiments on graph-structured data. In order to assess the robustness of the method we design novel oracles called soothsayers giving imperfect feedback. Finally, we complete our quantitative study with a qualitative study using a user interface to evaluate WaveLSea.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"98 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141150064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Active learning with biased non-response to label requests","authors":"Thomas S. Robinson, Niek Tax, Richard Mudd, Ido Guy","doi":"10.1007/s10618-024-01026-x","DOIUrl":"https://doi.org/10.1007/s10618-024-01026-x","url":null,"abstract":"<p>Active learning can improve the efficiency of training prediction models by identifying the most informative new labels to acquire. However, non-response to label requests can impact active learning’s effectiveness in real-world contexts. We conceptualise this degradation by considering the type of non-response present in the data, demonstrating that biased non-response is particularly detrimental to model performance. We argue that biased non-response is likely in contexts where the labelling process, by nature, relies on user interactions. To mitigate the impact of biased non-response, we propose a cost-based correction to the sampling strategy–the <i>Upper Confidence Bound of the Expected Utility (UCB-EU)</i>–that can, plausibly, be applied to any active learning algorithm. Through experiments, we demonstrate that our method successfully reduces the harm from labelling non-response in many settings. However, we also characterise settings where the non-response bias in the annotations remains detrimental under UCB-EU for specific sampling methods and data generating processes. Finally, we evaluate our method on a real-world dataset from an e-commerce platform. We show that UCB-EU yields substantial performance improvements to conversion models that are trained on clicked impressions. Most generally, this research serves to both better conceptualise the interplay between types of non-response and model improvements via active learning, and to provide a practical, easy-to-implement correction that mitigates model degradation.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"36 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141150105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"quant: a minimalist interval method for time series classification","authors":"Angus Dempster, Daniel F. Schmidt, Geoffrey I. Webb","doi":"10.1007/s10618-024-01036-9","DOIUrl":"https://doi.org/10.1007/s10618-024-01036-9","url":null,"abstract":"<p>We show that it is possible to achieve the same accuracy, on average, as the most accurate existing interval methods for time series classification on a standard set of benchmark datasets using a single type of feature (quantiles), fixed intervals, and an ‘off the shelf’ classifier. This distillation of interval-based approaches represents a fast and accurate method for time series classification, achieving state-of-the-art accuracy on the expanded set of 142 datasets in the UCR archive with a total compute time (training and inference) of less than 15 min using a single CPU core.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"50 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141150085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MSGNN: Multi-scale Spatio-temporal Graph Neural Network for epidemic forecasting","authors":"Mingjie Qiu, Zhiyi Tan, Bing-Kun Bao","doi":"10.1007/s10618-024-01035-w","DOIUrl":"https://doi.org/10.1007/s10618-024-01035-w","url":null,"abstract":"<p>Infectious disease forecasting has been a key focus and proved to be crucial in controlling epidemic. A recent trend is to develop forecasting models based on graph neural networks (GNNs). However, existing GNN-based methods suffer from two key limitations: (1) current models broaden receptive fields by scaling the depth of GNNs, which is insufficient to preserve the semantics of long-range connectivity between distant but epidemic related areas. (2) Previous approaches model epidemics within single spatial scale, while ignoring the multi-scale epidemic patterns derived from different scales. To address these deficiencies, we devise the Multi-scale Spatio-temporal Graph Neural Network (MSGNN) based on an innovative multi-scale view. To be specific, in the proposed MSGNN model, we first devise a novel graph learning module, which directly captures long-range connectivity from trans-regional epidemic signals and integrates them into a multi-scale graph. Based on the learned multi-scale graph, we utilize a newly designed graph convolution module to exploit multi-scale epidemic patterns. This module allows us to facilitate multi-scale epidemic modeling by mining both scale-shared and scale-specific patterns. Experimental results on forecasting new cases of COVID-19 in United State demonstrate the superiority of our method over state-of-arts. Further analyses and visualization also show that MSGNN offers not only accurate, but also robust and interpretable forecasting result. Code is available at https://github.com/JashinKorone/MSGNN.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"22 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141150030","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unsupervised feature based algorithms for time series extrinsic regression","authors":"David Guijo-Rubio, Matthew Middlehurst, Guilherme Arcencio, Diego Furtado Silva, Anthony Bagnall","doi":"10.1007/s10618-024-01027-w","DOIUrl":"https://doi.org/10.1007/s10618-024-01027-w","url":null,"abstract":"<p>Time Series Extrinsic Regression (TSER) involves using a set of training time series to form a predictive model of a continuous response variable that is not directly related to the regressor series. The TSER archive for comparing algorithms was released in 2022 with 19 problems. We increase the size of this archive to 63 problems and reproduce the previous comparison of baseline algorithms. We then extend the comparison to include a wider range of standard regressors and the latest versions of TSER models used in the previous study. We show that none of the previously evaluated regressors can outperform a regression adaptation of a standard classifier, rotation forest. We introduce two new TSER algorithms developed from related work in time series classification. FreshPRINCE is a pipeline estimator consisting of a transform into a wide range of summary features followed by a rotation forest regressor. DrCIF is a tree ensemble that creates features from summary statistics over random intervals. Our study demonstrates that both algorithms, along with InceptionTime, exhibit significantly better performance compared to the other 18 regressors tested. More importantly, DrCIF is the only one that significantly outperforms a standard rotation forest regressor.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"32 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141063378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Towards more sustainable and trustworthy reporting in machine learning","authors":"Raphael Fischer, Thomas Liebig, Katharina Morik","doi":"10.1007/s10618-024-01020-3","DOIUrl":"https://doi.org/10.1007/s10618-024-01020-3","url":null,"abstract":"<p>With machine learning (ML) becoming a popular tool across all domains, practitioners are in dire need of comprehensive reporting on the state-of-the-art. Benchmarks and open databases provide helpful insights for many tasks, however suffer from several phenomena: Firstly, they overly focus on prediction quality, which is problematic considering the demand for more sustainability in ML. Depending on the use case at hand, interested users might also face tight resource constraints and thus should be allowed to interact with reporting frameworks, in order to prioritize certain reported characteristics. Furthermore, as some practitioners might not yet be well-skilled in ML, it is important to convey information on a more abstract, comprehensible level. Usability and extendability are key for moving with the state-of-the-art and in order to be trustworthy, frameworks should explicitly address reproducibility. In this work, we analyze established reporting systems under consideration of the aforementioned issues. Afterwards, we propose STREP, our novel framework that aims at overcoming these shortcomings and paves the way towards more sustainable and trustworthy reporting. We use STREP’s (publicly available) implementation to investigate various existing report databases. Our experimental results unveil the need for making reporting more resource-aware and demonstrate our framework’s capabilities of overcoming current reporting limitations. With our work, we want to initiate a paradigm shift in reporting and help with making ML advances more considerate of sustainability and trustworthiness.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"8 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140841715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interpretable representations in explainable AI: from theory to practice","authors":"Kacper Sokol, Peter Flach","doi":"10.1007/s10618-024-01010-5","DOIUrl":"https://doi.org/10.1007/s10618-024-01010-5","url":null,"abstract":"<p>Interpretable representations are the backbone of many explainers that target black-box predictive systems based on artificial intelligence and machine learning algorithms. They translate the low-level data representation necessary for good predictive performance into high-level human-intelligible concepts used to convey the explanatory insights. Notably, the explanation type and its cognitive complexity are directly controlled by the interpretable representation, tweaking which allows to target a particular audience and use case. However, many explainers built upon interpretable representations overlook their merit and fall back on default solutions that often carry implicit assumptions, thereby degrading the explanatory power and reliability of such techniques. To address this problem, we study properties of interpretable representations that encode presence and absence of human-comprehensible concepts. We demonstrate how they are operationalised for tabular, image and text data; discuss their assumptions, strengths and weaknesses; identify their core building blocks; and scrutinise their configuration and parameterisation. In particular, this in-depth analysis allows us to pinpoint their explanatory properties, desiderata and scope for (malicious) manipulation in the context of tabular data where a linear model is used to quantify the influence of interpretable concepts on a black-box prediction. Our findings lead to a range of recommendations for designing trustworthy interpretable representations; specifically, the benefits of class-aware (supervised) discretisation of tabular data, e.g., with decision trees, and sensitivity of image interpretable representations to segmentation granularity and occlusion colour.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"50 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140800893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bake off redux: a review and experimental evaluation of recent time series classification algorithms","authors":"Matthew Middlehurst, Patrick Schäfer, Anthony Bagnall","doi":"10.1007/s10618-024-01022-1","DOIUrl":"https://doi.org/10.1007/s10618-024-01022-1","url":null,"abstract":"<p>In 2017, a research paper (Bagnall et al. Data Mining and Knowledge Discovery 31(3):606-660. 2017) compared 18 Time Series Classification (TSC) algorithms on 85 datasets from the University of California, Riverside (UCR) archive. This study, commonly referred to as a ‘bake off’, identified that only nine algorithms performed significantly better than the Dynamic Time Warping (DTW) and Rotation Forest benchmarks that were used. The study categorised each algorithm by the type of feature they extract from time series data, forming a taxonomy of five main algorithm types. This categorisation of algorithms alongside the provision of code and accessible results for reproducibility has helped fuel an increase in popularity of the TSC field. Over six years have passed since this bake off, the UCR archive has expanded to 112 datasets and there have been a large number of new algorithms proposed. We revisit the bake off, seeing how each of the proposed categories have advanced since the original publication, and evaluate the performance of newer algorithms against the previous best-of-category using an expanded UCR archive. We extend the taxonomy to include three new categories to reflect recent developments. Alongside the originally proposed distance, interval, shapelet, dictionary and hybrid based algorithms, we compare newer convolution and feature based algorithms as well as deep learning approaches. We introduce 30 classification datasets either recently donated to the archive or reformatted to the TSC format, and use these to further evaluate the best performing algorithm from each category. Overall, we find that two recently proposed algorithms, MultiROCKET+Hydra (Dempster et al. 2022) and HIVE-COTEv2 (Middlehurst et al. Mach Learn 110:3211-3243. 2021), perform significantly better than other approaches on both the current and new TSC problems.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"54 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140627694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lost in the Forest: Encoding categorical variables and the absent levels problem","authors":"Helen L. Smith, Patrick J. Biggs, Nigel P. French, Adam N. H. Smith, Jonathan C. Marshall","doi":"10.1007/s10618-024-01019-w","DOIUrl":"https://doi.org/10.1007/s10618-024-01019-w","url":null,"abstract":"<p>Levels of a predictor variable that are absent when a classification tree is grown can not be subject to an explicit splitting rule. This is an issue if these absent levels are present in a new observation for prediction. To date, there remains no satisfactory solution for absent levels in random forest models. Unlike missing data, absent levels are fully observed and known. Ordinal encoding of predictors allows absent levels to be integrated and used for prediction. Using a case study on source attribution of <i>Campylobacter</i> species using whole genome sequencing (WGS) data as predictors, we examine how target-agnostic <i>versus</i> target-based encoding of predictor variables with absent levels affects the accuracy of random forest models. We show that a target-based encoding approach using class probabilities, with absent levels designated the highest rank, is systematically biased, and that this bias is resolved by encoding absent levels according to the <i>a priori</i> hypothesis of equal class probability. We present a novel method of ordinal encoding predictors <i>via</i> principal coordinates analysis (PCO) which capitalizes on the similarity between pairs of predictor levels. Absent levels are encoded according to their similarity to each of the other levels in the training data. We show that the PCO-encoding method performs at least as well as the target-based approach and is not biased.</p>","PeriodicalId":55183,"journal":{"name":"Data Mining and Knowledge Discovery","volume":"13 1","pages":""},"PeriodicalIF":4.8,"publicationDate":"2024-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140562689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}