Isak Falk
YOU?
Author Swipe
View article: Robust Meta-Representation Learning via Global Label Inference and Classification
Robust Meta-Representation Learning via Global Label Inference and Classification Open
Few-shot learning (FSL) is a central problem in meta-learning, where learners must efficiently learn from few labeled examples. Within FSL, feature pre-training has become a popular strategy to significantly improve generalization performa…
View article: Learning the kernel for rare variant genetic association test
Learning the kernel for rare variant genetic association test Open
Introduction: Compared to Genome-Wide Association Studies (GWAS) for common variants, single-marker association analysis for rare variants is underpowered. Set-based association analyses for rare variants are powerful tools that capture so…
View article: Transfer learning for atomistic simulations using GNNs and kernel mean embeddings
Transfer learning for atomistic simulations using GNNs and kernel mean embeddings Open
Interatomic potentials learned using machine learning methods have been successfully applied to atomistic simulations. However, accurate models require large training datasets, while generating reference calculations is computationally dem…
View article: Robust Meta-Representation Learning via Global Label Inference and Classification
Robust Meta-Representation Learning via Global Label Inference and Classification Open
Few-shot learning (FSL) is a central problem in meta-learning, where learners must efficiently learn from few labeled examples. Within FSL, feature pre-training has recently become an increasingly popular strategy to significantly improve …
View article: Group Meritocratic Fairness in Linear Contextual Bandits
Group Meritocratic Fairness in Linear Contextual Bandits Open
We study the linear contextual bandit problem where an agent has to select one candidate from a pool and each candidate belongs to a sensitive group. In this setting, candidates' rewards may not be directly comparable between groups, for e…
View article: GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability
GENNI: Visualising the Geometry of Equivalences for Neural Network Identifiability Open
We propose an efficient algorithm to visualise symmetries in neural networks. Typically, models are defined with respect to a parameter space, where non-equal parameters can produce the same input-output map. Our proposed method, GENNI, al…