DOI,IST REx ID,Research Group,Title of publication
10.15479/AT-ISTA-21198,21198,"GradSch,ChLa",Data heterogeneity and personalization in federated learning
10.1145/3774904.3792868,21916,ChLa,Fedivertex: A graph dataset based on decentralized Social Media
10.1007/s00521-024-10616-1,12662,ChLa,Generalization in multi-objective machine learning
null,20256,"ToHe,ChLa",Predictive monitoring of black-box dynamical systems
null,20296,"ChLa,ToHe",Logic gate neural networks are good for verification
null,20298,ChLa,Efficient estimation of a Gaussian mean with local differential privacy
10.1109/CVPRW67362.2025.00071,20455,ChLa,Intriguing properties of robust classification
null,20819,"ChLa,MoHe",Differentially private federated k-means clustering with server-side data
10.48550/ARXIV.2505.15579,21207,ChLa,Federated learning with unlabeled clients: Personalization can happen in low dimensions
10.15479/10.15479/at-ista-19759,19759,"GradSch,ChLa",Robust image classification with 1-Lipschitz networks
10.5311/JOSIS.2024.29.295,18856,ChLa,Predicting the geolocation of tweets using transformer models on customized data
null,18875,"GradSch,ChLa",Banded square root matrix factorization for differentially private model training
null,18891,"GradSch,MaMo,ChLa",Neural collapse versus low-rank bias: Is deep neural collapse really optimal?
10.48550/arXiv.2403.06833,19063,"GradSch,ChLa",Can LLMs separate instructions from data? And what do we even mean by that?
null,19408,ChLa,Continual learning: Applications and the road forward
null,17093,"DaAl,ChLa",Communication-efficient federated learning with data and client heterogeneity
null,17411,ChLa,PEFLL: Personalized federated learning by learning to learn
null,18120,ChLa,Improved modelling of federated datasets using mixtures-of-Dirichlet-multinomials
10.1109/CVPR52733.2024.02320,17426,"GradSch,ChLa","1-Lipschitz layers compared: Memory, speed, and certifiable robustness"
10.48550/arXiv.2412.04245,18874,"GradSch,ChLa",Intriguing properties of robust classification