1 citations · 1 across the 13 of their papers we have counts for
7 papers · 1 filter
What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much?
Rafał Karczewski, Samuel Kaski, Markus Heinonen +1
Several generative models with elaborate training and sampling procedures have been proposed to accelerate structure-based drug design (SBDD); however, their empirical performance…
Transformer Normalisation Layers and the Independence of Semantic Subspaces
Stephen Menary, Samuel Kaski, Andre Freitas
Recent works have shown that transformers can solve contextual reasoning tasks by internally executing computational graphs called circuits. Circuits often use attention to logical…
Embarrassingly Parallel GFlowNets
Tiago da Silva, Luiz Max Carvalho, Amauri Souza +2
GFlowNets are a promising alternative to MCMC sampling for discrete compositional random variables. Training GFlowNets requires repeated evaluations of the unnormalized target dist…
Improving robustness to corruptions with multiplicative weight perturbations
Trung Trinh, Markus Heinonen, Luigi Acerbi +1
Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones. Incorporating specific corruptions into the data augmentation pipeline can improve robustness to…
Attaining Human`s Desirable Outcomes in Human-AI Interaction via Structural Causal Games
Anjie Liu, Jianhong Wang, Haoxuan Li +4
In human-AI interaction, a prominent goal is to attain human`s desirable outcome with the assistance of AI agents, which can be ideally delineated as a problem of seeking the optim…
Anchor-Based Heteroscedastic Noise for Preferential Bayesian Optimization
Marshal Arijona Sinaga, Julien Martinelli, Samuel Kaski
Preferential Bayesian optimization (PBO) learns latent utilities from pairwise comparisons, but most existing methods assume homoscedastic comparison noise. This is inadequate in h…
In-n-Out: Calibrating Graph Neural Networks for Link Prediction
Erik Nascimento, Diego Mesquita, Samuel Kaski +1
Deep neural networks are notoriously miscalibrated, i.e., their outputs do not reflect the true probability of the event we aim to predict. While networks for tabular or image data…