Rate My Professor Mahsa Salehi

Mahsa Salehi is a Senior Lecturer in the Department of Data Science and AI, Faculty of Information Technology, Monash University, a position she has held since July 2017. Prior to joining Monash, she was a postdoctoral researcher at IBM Research Australia. She received her PhD in Computer Science from the Department of Computing and Information Systems at the University of Melbourne in 2016, in collaboration with the Machine Learning research group in NICTA. Her academic background also includes a Master of Science in Software Engineering from Amirkabir University of Technology in 2009, a Bachelor of Science in Information Technology in 2008, and a Bachelor of Science in Computer Engineering in 2006, both from the same institution.

Salehi's research focuses on multi-dimensional time series analysis, anomaly detection, time series classification, learning from non-stationary distributions, brain-inspired machine learning, and spatio-temporal data analysis within the broader fields of machine learning and data mining. She serves as Associate Editor for ACM Transactions on Knowledge Discovery from Data since 2023 and has contributed to program committees for conferences including ACM KDD 2016, SIAM SDM 2017-2018, and PAKDD 2018. Her accolades include the SIGKDD 2025 Audience Appreciation Award, ICDM 2022 Best Paper Runner-up Award, IBM Manager’s Choice Award in 2016, selection among the Top 200 Most Qualified Young Researchers in Computer Science and Mathematics by the Heidelberg Laureate Forum Foundation in 2016, Melbourne School of Engineering Teaching Excellence Award in 2014, and winning the Australian Microsoft Imagine Cup Final in 2012. Key publications encompass "CARLA: Self-supervised contrastive representation learning for time series anomaly detection" (Pattern Recognition, 2025), "DACAD: Domain Adaptation Contrastive Learning for Anomaly Detection in Multivariate Time Series" (IEEE Transactions on Knowledge and Data Engineering, 2025), "CNN-Transformer with Absolute Positional Encoding Optimized for Low-Dimensional Inputs" (ECML PKDD 2025), "Open-Set Graph Anomaly Detection via Normal Structure Regularisation" (ICLR 2025), and "Deep Learning for Time Series Anomaly Detection: A Survey" (2024). She supervises PhD projects on topics such as foundation models for time series anomaly detection and learning from EEG data, and is the Inaugural Director of the Temporal Analytics Lab.