Efthymia Tsamoura

Moving to Huawei Labs

efi.jpg

I am a researcher working on logic, knowledge representation and reasoning, and neurosymbolic learning. From 2019 to 2025, I was a Senior Researcher at Samsung AI, Cambridge, UK, leading research on reasoning and neurosymbolic learning. In 2016, I was awarded a prestigious early career fellowship from the Alan Turing Institute, UK, for my work on logic and databases, and before that, I was a Postdoctoral Researcher in the Department of Computer Science of the University of Oxford.

One of the best moments in my career was my participation in the Samsung AI Forum in 2021, where I joined the panel on neurosymbolic AI with professors Leslie Valiant and Daniel Dongyuel Lee. A second highlight was an invitation I received from the Royal Society, London, in 2024 to participate in the Frontiers of Science (FoS) meeting and discuss the challenges of deep learning with leaders in the field, including professors Yoshua Bengio and Doina Precup.

My recent outcomes involve scaling symbolic reasoning and query answering to billions of triples, as well as addressing open problems in neurosymbolic learning, see NeurIPS 2023 and arXiv 2024. I was also the first to develop goal-driven query answering techniques under second-order theories that run in the order of milliseconds, correcting an incompleteness error of previous work. See my software page for further information.

I am joining Huawei Labs as a Technical Expert in May 2025.

news

Apr 02, 2025 Very excited to receive an invitation to give a keynote at the 8th Workshop on Tractable Probabilistic Modeling that will be collocated with UAI 2025. Special thanks to all the organizers :sparkles:
Mar 31, 2025 Visiting Huawei Labs in Edinburgh to give a technical talk and meet my colleagues :sparkles:
Mar 18, 2025 Very honored to receive an invitation from Gilles Pesant from École Polytechnique de Montréal to present my research at the IVADO Montreal workshop on Neuro-Symbolic AI, May 5-7, and discuss the latest advances in the field with Yoshua Bengio, Luc De Raedt, Francesca Rossi, and many other leaders in AI :sparkles:
Feb 28, 2025 Uploaded a new version of our rule mining technique, SPECTRUM, to arXiv. Special thanks to Jonathan Feldstein and Dominic Phillips :sparkles:
Feb 18, 2025 Thrilled to join Huawei Labs and lead a team on ondevice systems :sparkles:
Feb 17, 2025 The webpage of our 1st Workshop on New Ideas for Large-Scale Neurosymbolic Learning Systems (LS-NSL) is out :sparkles: We look forward to receiving your papers!
Oct 29, 2024 Uploaded our neurosymbolic literature review paper to arXiv. Special thanks to Jonathan Feldstein, Paulius Dilkas, and Vaishak Belle :sparkles:

selected publications

  1. Review paper
    Mapping the Neuro-Symbolic AI Landscape by Architectures: A Handbook on Augmenting Deep Learning Through Symbolic Reasoning
    Jonathan Feldstein, Paulius Dilkas, Vaishak Belle, and Efthymia Tsamoura
    2024
    arXiv
  2. arXiv
    Efficiently Learning Probabilistic Logical Models by Cheaply Ranking Mined Rules
    Jonathan Feldstein, Dominic Phillips, and Efthymia Tsamoura
    2025
    arXiv
  3. arXiv
    On Characterizing and Mitigating Imbalances in Multi-Instance Partial Label Learning
    Kaifu Wang*, Efthymia Tsamoura*, and Dan Roth
    2024
    arXiv
  4. NeurIPS
    On Learning Latent Models with Multi-Instance Weak Supervision
    Kaifu Wang, Efthymia Tsamoura, and Dan Roth
    In Proceedings of the Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023
    arXiv HTML
  5. VLDB
    Materializing Knowledge Bases via Trigger Graphs
    Efthymia Tsamoura, David Carral, Enrico Malizia, and Jacopo Urbani
    Proceedings of the VLDB Endowment, 2021
    DOI arXiv PDF Code
  6. TODS
    Generating Plans from Proofs
    Michael Benedikt*, Balder Cate*, and Efthymia Tsamoura*
    ACM Transactions on Database Systems, 2016
    DOI