Tobaben, Alrawajfeh, Klasson, Heikkilä, Solin & Honkela 2025:
Differential Privacy in Continual Learning: Which Labels to Update?. On ArXiv.
Zhao, Rehn, Heikkilä, Tajeddine & Honkela 2025:
Mitigating disparate impact of differentially private learning through bounded adaptive clipping. On ArXiv.
Jimenez G., Solans, Heikkilä, Vitaletti, Kourtellis, Anagnostopoulos & Chatzigiannakis 2025:
Non-IID data in federated learning: A survey with taxonomy, metrics, methods, frameworks and future directions. On ArXiv.
Heikkilä 2025:
On using secure aggregation in differentially private federated learning with multiple local steps. In TMLR ‘25.
Shah, Solans, Heikkilä, Raj & Kourtellis 2025:
Speech robust bench: A robustness benchmark for speech recognition. In ICLR ‘25.
Corbucci, Heikkilä, Solans, Monreale & Kourtellis 2024:
PUFFLE: Balancing privacy, utility, and fairness in federated learning. In ECAI ‘24.
Heikkilä, Ashman, Swaroop, Turner & Honkela 2023:
Differentially private partitioned variational inference. In TMLR.
Koskela, Heikkilä & Honkela 2023:
Numerical accounting in the shuffle model of differential privacy. In TMLR (Featured certification).
Heikkilä, Koskela, Shimizu, Kaski & Honkela 2020:
Differentially private cross-silo federated learning. On ArXiv.
Heikkilä, Jälkö, Dikmen & Honkela 2019:
Differentially private Markov chain Monte Carlo.
In NeurIPS ‘19 (Spotlight).
Niinimäki, Heikkilä, Honkela & Kaski 2019:
Representation transfer for differentially private drug sensitivity prediction.
In ISMB ‘19.
Heikkilä, Lagerspetz, Kaski, Shimizu, Tarkoma & Honkela 2017:
Differentially private Bayesian learning on distributed data.
In NeurIPS ‘17.
Dissertation
My PhD thesis “Differentially private and distributed Bayesian learning” has been accepted with distinction.