no code implementations • 27 Jun 2023 • Navindu Leelarathna, Andrei Margeloiu, Mateja Jamnik, Nikola Simidjievski
Variational Autoencoders and their many variants have displayed impressive ability to perform dimensionality reduction, often achieving state-of-the-art performance.
no code implementations • 21 Jun 2023 • Xiangjian Jiang, Andrei Margeloiu, Nikola Simidjievski, Mateja Jamnik
In this paper, we propose ProtoGate, a prototype-based neural model that introduces an inductive bias by attending to both homogeneity and heterogeneity across samples.
1 code implementation • 28 Nov 2022 • Andrei Margeloiu, Nikola Simidjievski, Pietro Lio, Mateja Jamnik
Tabular biomedical data is often high-dimensional but with a very small number of samples.
no code implementations • 11 Nov 2022 • Andrei Margeloiu, Nikola Simidjievski, Pietro Lio, Mateja Jamnik
We create a graph between samples for each data dimension, and utilise Graph Neural Networks (GNNs) for extracting this implicit structure, and for conditioning the parameters of the first layer of an underlying predictor network.
no code implementations • 10 May 2021 • Andrei Margeloiu, Matthew Ashman, Umang Bhatt, Yanzhi Chen, Mateja Jamnik, Adrian Weller
Concept bottleneck models map from raw inputs to concepts, and then from concepts to targets.
1 code implementation • 2 Dec 2020 • Andrei Margeloiu, Nikola Simidjievski, Mateja Jamnik, Adrian Weller
We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer.