3 papers
cs.LG2025
Layer-to-Layer Knowledge Mixing in Graph Neural Network for Chemical Property Prediction
Teng Jiek See, Daokun Zhang, Mario Boley +1
Graph Neural Networks (GNNs) are the currently most effective methods for predicting molecular properties but there remains a need for more accurate models. GNN accuracy can be imp…
cs.LG2025
Towards the Next-generation Bayesian Network Classifiers
Huan Zhang, Daokun Zhang, Kexin Meng +1
Bayesian network classifiers provide a feasible solution to tabular data classification, with a number of merits like high time and memory efficiency, and great explainability. How…
cs.LG2025
Label Distribution Learning using the Squared Neural Family on the Probability Simplex
Daokun Zhang, Russell Tsuchida, Dino Sejdinovic
Label distribution learning (LDL) provides a framework wherein a distribution over categories rather than a single category is predicted, with the aim of addressing ambiguity in la…