MUFASA: Fast and Accurate Multivariate Time-Series Clustering

Summary: MUFASA extends k-Shape with SBD-D for global cross-channel alignment and a joint, efficient centroid update, capturing multivariate dependencies without cubic costs. It matches elastic-distance accuracy 2–4 orders faster and outperforms scalable and deep baselines. (summarized by gpt-5.6-luna on Jul 26 2026)

Paper ID: h7393e60532bc7357
Venue: SIGMOD
Year: 2026
Pagerank: 4.9769913e-05
Overall Rank: 10,494 | 29.47%
DOI: 10.1145/3802090
PDF: Download (CC BY 4.0)

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

1. Haojun Li (Ohio State University)
2. John Paparrizos (Ohio State University)

BibTeX Citation

@inproceedings{li_sigmod26,
        title = {{MUFASA: Fast and Accurate Multivariate Time-Series Clustering}},
        author = {Li, Haojun and Paparrizos, John},
        series = {{SIGMOD} '26},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3802090},
        url = {https://dl.acm.org/doi/10.1145/3802090},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 2 of 2 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,480	HYDRA: A Multi-Level Hierarchy-Driven Approach for Robust Anomaly Detection in Time Series	2026	SIGMOD	4.9769913e-05
10,521	The Power of Anomaly Detection in Predictive Maintenance: [Experiments & Analysis]	2026	SIGMOD	4.9769913e-05

Outgoing Citations (Sorted by Pagerank)

Showing 29 of 29 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Rank	Cited Paper	Year	Venue	Pagerank
306	On The Marriage of Lp-norms and Edit Distance	2004	VLDB	0.00021565993
1,579	k-Shape: Efficient and Accurate Clustering of Time Series	2015	SIGMOD	0.00010182038
1,629	SAND: Streaming Subsequence Anomaly Detection	2021	VLDB	0.0001003165
1,938	TSB-UAD: An End-to-End Benchmark Suite for Univariate Time-Series Anomaly Detection	2022	VLDB	9.334286e-05
1,974	Decomposed Bounded Floats for Fast Compression and Queries	2021	VLDB	9.2806652e-05
3,728	Choose Wisely: An Extensive Evaluation of Model Selection for Anomaly Detection in Time Series	2023	VLDB	7.0667899e-05
3,991	Time2Feat: Learning Interpretable Representations for Multivariate Time Series Clustering	2023	VLDB	6.8669111e-05
4,317	GRAIL: Efficient Time-Series Representation Learning	2019	VLDB	6.6651881e-05
4,705	Debunking Four Long-Standing Misconceptions of Time-Series Distance Measures	2020	SIGMOD	6.4591377e-05
5,477	Good to the Last Bit: Data-Driven Encoding with CodecDB	2021	SIGMOD	6.1152706e-05
6,192	VergeDB: A Database for IoT Analytics on Edge Devices	2021	CIDR	5.8540507e-05
7,096	Time-Series Clustering: A Comprehensive Study of Data Mining, Machine Learning, and Deep Learning Methods	2025	VLDB	5.5991152e-05
7,647	A Structured Study of Multivariate Time-Series Distance Measures	2025	SIGMOD	5.4746904e-05
8,166	PIDS: Attribute Decomposition for Improved Compression and Query Performance in Columnar Storage	2020	VLDB	5.3846089e-05
9,493	TSB-AutoAD: Towards Automated Solutions for Time-Series Anomaly Detection	2025	VLDB	5.168414e-05
9,494	Beyond Compression: A Comprehensive Evaluation of Lossless Floating-Point Compression	2025	VLDB	5.168414e-05
9,499	Time-Series Anomaly Detection: Overview and New Trends	2024	VLDB	5.168414e-05
9,633	Theseus: Navigating the Labyrinth of Time-Series Anomaly Detection	2022	VLDB	5.1459383e-05
9,665	Odyssey: An Engine Enabling The Time-Series Clustering Journey	2023	VLDB	5.142891e-05
9,916	SPARTAN: Data-Adaptive Symbolic Time-Series Approximation	2025	SIGMOD	5.1079647e-05
10,480	HYDRA: A Multi-Level Hierarchy-Driven Approach for Robust Anomaly Detection in Time Series	2026	SIGMOD	4.9769913e-05
10,521	The Power of Anomaly Detection in Predictive Maintenance: [Experiments & Analysis]	2026	SIGMOD	4.9769913e-05
11,220	Understanding the Black Box: A Deep Empirical Dive into Shapley Value Approximations for Tabular Data	2025	SIGMOD	4.9769913e-05
11,355	BURST: Rendering Clustering Techniques Suitable for Evolving Streams	2025	VLDB	4.9769913e-05
11,425	EasyAD: A Demonstration of Automated Solutions for Time-Series Anomaly Detection	2025	VLDB	4.9769913e-05
11,755	Accelerating Similarity Search for Elastic Measures: A Study and New Generalization of Lower Bounding Distances	2023	VLDB	4.9769913e-05
13,643	ShapX Engine: A Demonstration of Shapley Value Approximations	2025	SIGMOD	-
13,665	SAIL: A Voyage to Symbolic Approximation Solutions for Time-Series Analysis	2025	VLDB	-
13,782	SAND in Action: Subsequence Anomaly Detection for Streams	2021	VLDB	-

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,084	MS-Index: Fast Top-k Subsequence Search for Multivariate Time Series under Euclidean Distance	2026	VLDB
2	11,270	Time Series Motif Discovery: A Comprehensive Evaluation	2025	VLDB
3	11,326	MOMENTI: Scalable Motif Mining in Multidimensional Time Series	2025	VLDB
4	8,209	FeatTS: Feature-based Time Series Clustering	2021	SIGMOD
5	11,313	UFGTime: Mining Intertwined Dependencies in Multivariate Time Series via an Efficient Pure Graph Approach	2025	VLDB
6	7,154	Interpretable Clustering of Multivariate Time Series with Time2Feat	2023	VLDB
7	7,647	A Structured Study of Multivariate Time-Series Distance Measures	2025	SIGMOD
8	7,096	Time-Series Clustering: A Comprehensive Study of Data Mining, Machine Learning, and Deep Learning Methods	2025	VLDB
9	3,991	Time2Feat: Learning Interpretable Representations for Multivariate Time Series Clustering	2023	VLDB
10	1,579	k-Shape: Efficient and Accurate Clustering of Time Series	2015	SIGMOD