Topology only pre-training: towards generalised multi-domain graph models [0.03%]
仅拓扑的预训练：面向通用化的多域图模型
Alex O Davies,Riku Green,Telmo M Silva Filho et al.
Alex O Davies et al.
The principal benefit of unsupervised representation learning is that a pre-trained model can be fine-tuned where data or labels are scarce. Existing approaches for graph representation learning are domain specific, maintaining consistent n...
Alexander Van Werde,Albert Senen-Cerda,Gianluca Kosmella et al.
Alexander Van Werde et al.
Sequential data is ubiquitous-it is routinely gathered to gain insights into complex processes such as behavioral, biological, or physical processes. Challengingly, such data not only has dependencies within the observed sequences, but the ...
Universal representation learning for multivariate time series using the instance-level and cluster-level supervised contrastive learning [0.03%]
基于实例级和聚类级监督对比学习的多变量时间序列通用表示学习
Nazanin Moradinasab,Suchetha Sharma,Ronen Bar-Yoseph et al.
Nazanin Moradinasab et al.
The multivariate time series classification (MTSC) task aims to predict a class label for a given time series. Recently, modern deep learning-based approaches have achieved promising performance over traditional methods for MTSC tasks. The ...
Giulia Bernardini,Chang Liu,Grigorios Loukides et al.
Giulia Bernardini et al.
Missing values arise routinely in real-world sequential (string) datasets due to: (1) imprecise data measurements; (2) flexible sequence modeling, such as binding profiles of molecular sequences; or (3) the existence of confidential informa...
Thu Trang Nguyen,Thach Le Nguyen,Georgiana Ifrim
Thu Trang Nguyen
Time series classification is a task which deals with temporal sequences, a prevalent data type common in domains such as human activity recognition, sports analytics and general sensing. In this area, interest in explanability has been gro...
Somtimes: self organizing maps for time series clustering and its application to serious illness conversations [0.03%]
基于自组织映射的时间序列聚类及其在严重疾病对话中的应用
Ali Javed,Donna M Rizzo,Byung Suk Lee et al.
Ali Javed et al.
There is demand for scalable algorithms capable of clustering and analyzing large time series data. The Kohonen self-organizing map (SOM) is an unsupervised artificial neural network for clustering, visualizing, and reducing the dimensional...
Counting frequent patterns in large labeled graphs: a hypergraph-based approach [0.03%]
在大型标记图中计数频繁模式：超图方法
Jinghan Meng,Napath Pitaksirianan,Yi-Cheng Tu
Jinghan Meng
In recent years, the popularity of graph databases has grown rapidly. This paper focuses on single-graph as an effective model to represent information and its related graph mining techniques. In frequent pattern mining in a single-graph se...
On the evaluation of outlier detection and one-class classification: a comparative study of algorithms, model selection, and ensembles [0.03%]
异常检测和单类分类的评价研究：算法、模型选择及集成方法的比较研究
Henrique O Marques,Lorne Swersky,Jörg Sander et al.
Henrique O Marques et al.
It has been shown that unsupervised outlier detection methods can be adapted to the one-class classification problem (Janssens and Postma, in: Proceedings of the 18th annual Belgian-Dutch on machine learning, pp 56-64, 2009; Janssens et al....
Ashkan Farhangi,Jiang Bian,Arthur Huang et al.
Ashkan Farhangi et al.
Time series models often are impacted by extreme events and anomalies, both prevalent in real-world datasets. Such models require careful probabilistic forecasts, which is vital in risk management for extreme events such as hurricanes and p...
Hubert Baniecki,Dariusz Parzych,Przemyslaw Biecek
Hubert Baniecki
The growing need for in-depth analysis of predictive models leads to a series of new methods for explaining their local and global properties. Which of these methods is the best? It turns out that this is an ill-posed question. One cannot s...