Farimah Poursafaei

I am a Postdoctoral Fellow at Mila, Québec AI Institute & School of Computer Science (SoCS) at McGill University. I received my PhD from the Department of Electrical and Computer Engineering (ECE) at McGill University in 2022, under the supervison of Prof. Zeljko Zilic and Prof. Reihaneh Rabbany.

Currently, I am working on dynamic graph representation learning, graph neural networks, and generally graph machine learning. My background also includes anomaly detection, network analysis, and data mining applied in real-world networks including cryptocurrency transaction networks. In a previous life, I was doing research on the operating systems and compilers for real-time embedded systems.

News!


Publications


  • Poursafaei, Farimah*, Shenyang Huang*, Kellin Pelrine, and Reihaneh Rabbany. "Towards Better Evaluation for Dynamic Link Prediction." In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track, Dec. 2022.
    NeurIPS arXiv Video Link Github Repo Poster Blog Post

  • Poursafaei, Farimah, Zeljko Zilic, and Reihaneh Rabbany. "A Strong Node Classification Baseline for Temporal Graphs." In Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), pp. 648-656. Society for Industrial and Applied Mathematics, 2022.
    paper Github Repo

  • Poursafaei, Farimah, Zeljko Zilic, and Reihaneh Rabbany. "On Anomaly Detection in Graphs as Node Classification." In Proceedings of the Big Data Engineering and Technology, 2022.
    paper

  • Poursafaei, Farimah, Reihaneh Rabbany, and Zeljko Zilic. "SigTran: Signature Vectors for Detecting Illicit Activities in Blockchain Transaction Networks." In Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD), pp. 27-39. Springer, Cham, 2021.
    paper Github Repo

  • Poursafaei, Farimah, Ghaith Bany Hamad, and Zeljko Zilic. "Detecting Malicious Ethereum Entities via Application of Machine Learning Classification." In 2nd Conference on Blockchain Research & Applications for Innovative Networks and Services (BRAINS), pp. 120-127. IEEE, 2020.
    paper

  • Poursafaei, Farimah, Sepideh Safari, Mohsen Ansari, Amir Yeganeh-Khaksar, Mohammad Salehi, and Alireza Ejlali. "Energy-and Reliability-Aware Task Replication in Safety-Critical Embedded Systems." In Proceedings of the 4th International of CSI Symposium on Real-Time and Embedded Systems and Technologies (RTEST), 2022.
    paper

  • Poursafaei, Farimah, Mostafa Bazzaz, Morteza Mohajjel Kafshdooz, and Alireza Ejlali. "Slack Clustering for Scheduling Frame-Based Tasks on Multicore Embedded Systems." Microelectronics Journal 81 (2018): 144-153.
    paper

  • Lévy, Sacha, Farimah Poursafaei, Kellin Pelrine, and Reihaneh Rabbany. "Active Keyword Selection to Track Evolving Topics on Twitter." Accepted in Utility-Driven Mining and Learning (UDML) at ICDM 2022. arXiv preprint arXiv:2209.11135.
    arXiv

  • Bazzaz, Mostafa, Ali Hoseinghorban, Farimah Poursafaei, and Alireza Ejlali. "High-Performance Predictable NVM-Based Instruction Memory for Real-Time Embedded Systems." IEEE Transactions on Emerging Topics in Computing, 2018: 441-455.
    paper

  • Poursafaei, Farimah R., Mostafa Bazzaz, and Alireza Ejlali. "NPAM: NVM-Aware Page Allocation for Multi-Core Embedded Systems." IEEE Transactions on Computers, 2017: 1703-1716.
    paper

  • Ansari, Mohsen, Sepideh Safari, Farimah R. Poursafaei, Mohammad Salehi, and Alireza Ejlali. "AdDQ: Low-Energy Hardware Replication for Real-Time Systems through Adaptive Dual Queue Scheduling." The CSI Journal on Computer Science and Engineering (JCSE), 2017: 31-38.
    paper

  • Poursafaei, Farimah, Sepideh Safari, Mohsen Ansari, Mohammad Salehi, and Alireza Ejlali. "Offline Replication and Online Energy Management for Hard Real-Time Multicore Systems." In 2015 CSI Symposium on Real-Time and Embedded Systems and Technologies (RTEST), IEEE, 2015.
    paper