@article{SchneiderWenigPapenbrock2021,
  author    = {Schneider, Johannes and Wenig, Phillip and Papenbrock, Thorsten},
  title     = {Distributed detection of sequential anomalies in univariate time series},
  series = {The VLDB journal : the international journal on very large data bases},
  volume    = {30},
  journal   = {The VLDB journal : the international journal on very large data bases},
  number    = {4},
  publisher = {Springer},
  address   = {Berlin},
  issn      = {1066-8888},
  doi       = {10.1007/s00778-021-00657-6},
  pages     = {579 -- 602},
  year      = {2021},
  abstract  = {The automated detection of sequential anomalies in time series is an essential task for many applications, such as the monitoring of technical systems, fraud detection in high-frequency trading, or the early detection of disease symptoms. All these applications require the detection to find all sequential anomalies possibly fast on potentially very large time series. In other words, the detection needs to be effective, efficient and scalable w.r.t. the input size. Series2Graph is an effective solution based on graph embeddings that are robust against re-occurring anomalies and can discover sequential anomalies of arbitrary length and works without training data. Yet, Series2Graph is no t scalable due to its single-threaded approach; it cannot, in particular, process arbitrarily large sequences due to the memory constraints of a single machine. In this paper, we propose our distributed anomaly detection system, short DADS, which is an efficient and scalable adaptation of Series2Graph. Based on the actor programming model, DADS distributes the input time sequence, intermediate state and the computation to all processors of a cluster in a way that minimizes communication costs and synchronization barriers. Our evaluation shows that DADS is orders of magnitude faster than S2G, scales almost linearly with the number of processors in the cluster and can process much larger input sequences due to its scale-out property.},
  language  = {en}
}
@misc{ShaabaniMeinel2018,
  author    = {Shaabani, Nuhad and Meinel, Christoph},
  title     = {Improving the efficiency of inclusion dependency detection},
  series = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management},
  journal   = {Proceedings of the 27th ACM International Conference on Information and Knowledge Management},
  publisher = {Association for Computing Machinery},
  address   = {New York},
  isbn      = {978-1-4503-6014-2},
  doi       = {10.1145/3269206.3271724},
  pages     = {207 -- 216},
  year      = {2018},
  abstract  = {The detection of all inclusion dependencies (INDs) in an unknown dataset is at the core of any data profiling effort. Apart from the discovery of foreign key relationships, INDs can help perform data integration, integrity checking, schema (re-)design, and query optimization. With the advent of Big Data, the demand increases for efficient INDs discovery algorithms that can scale with the input data size. To this end, we propose S-INDD++ as a scalable system for detecting unary INDs in large datasets. S-INDD++ applies a new stepwise partitioning technique that helps discard a large number of attributes in early phases of the detection by processing the first partitions of smaller sizes. S-INDD++ also extends the concept of the attribute clustering to decide which attributes to be discarded based on the clustering result of each partition. Moreover, in contrast to the state-of-the-art, S-INDD++ does not require the partition to fit into the main memory-which is a highly appreciable property in the face of the ever growing datasets. We conducted an exhaustive evaluation of S-INDD++ by applying it to large datasets with thousands attributes and more than 266 million tuples. The results show the high superiority of S-INDD++ over the state-of-the-art. S-INDD++ reduced up to 50 \% of the runtime in comparison with BINDER, and up to 98 \% in comparison with S-INDD.},
  language  = {en}
}