Search Results for author:
Found 30 papers, 19 papers with code
Measuring Cross-Modal Interactions in Multimodal Models
We show that InterSHAP accurately measures the presence of cross-modal interactions, can handle multiple modalities, and provides detailed explanations at a local level for individual samples.
PATHS: A Hierarchical Transformer for Efficient Whole Slide Image Analysis
Computational analysis of whole slide images (WSIs) has seen significant research progress in recent years, with applications ranging across important diagnostic and prognostic tasks such as survival or cancer subtype prediction.
TabEBM: A Tabular Data Augmentation Method with Distinct Class-Specific Energy-Based Models
As a result, classification methods usually perform poorly with these small datasets, leading to weak predictive performance.
TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsetting
To overcome this challenge, we introduce TabMDA, a novel method for manifold data augmentation on tabular data.
MM-Lego: Modular Biomedical Multimodal Models with Minimal Fine-Tuning
Learning holistic computational representations in physical, chemical or biological systems requires the ability to process information from different distributions and modalities within the same model.
Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts
A line of interpretable methods approach this by discovering a small set of relevant concepts as subgraphs in the last GNN layer that together explain the prediction.
HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data
Technological advances in medical data collection, such as high-throughput genomic sequencing and digital high-resolution histopathology, have contributed to the rising requirement for multimodal biomedical modelling, specifically for image, tabular and graph data.
In-Domain Self-Supervised Learning Improves Remote Sensing Image Scene Classification
A common approach in practice to SSL pre-training is utilizing standard pre-training datasets, such as ImageNet.
SHARCS: Shared Concept Space for Explainable Multimodal Learning
Multimodal learning is an essential paradigm for addressing complex real-world problems, where individual data modalities are typically insufficient to accurately solve a given modelling task.
Enhancing Representation Learning on High-Dimensional, Small-Size Tabular Data: A Divide and Conquer Method with Ensembled VAEs
Variational Autoencoders and their many variants have displayed impressive ability to perform dimensionality reduction, often achieving state-of-the-art performance.
ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data
Tabular biomedical data poses challenges in machine learning because it is often high-dimensional and typically low-sample-size (HDLSS).
Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data
Tabular biomedical data is often high-dimensional but with a very small number of samples.
GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data
We create a graph between samples for each data dimension, and utilise Graph Neural Networks (GNNs) to extract this implicit structure, and for conditioning the parameters of the first layer of an underlying predictor network.
Discover the Mysteries of the Maya: Selected Contributions from the Machine Learning Challenge & The Discovery Challenge Workshop at ECML PKDD 2021
The volume contains selected contributions from the Machine Learning Challenge "Discover the Mysteries of the Maya", presented at the Discovery Challenge Track of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021).
Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image Classification
We present AiTLAS: Benchmark Arena -- an open-source benchmark suite for evaluating state-of-the-art deep learning approaches for image classification in Earth Observation (EO).
AiTLAS: Artificial Intelligence Toolbox for Earth Observation
The AiTLAS toolbox (Artificial Intelligence Toolbox for Earth Observation) includes state-of-the-art machine learning methods for exploratory and predictive analysis of satellite imagery as well as repository of AI-ready Earth Observation (EO) datasets.
Heavy-tailed denoising score matching
Score-based model research in the last few years has produced state of the art generative models by employing Gaussian denoising score-matching (DSM).
On Second Order Behaviour in Augmented Neural ODEs: A Short Summary
In Norcliffe et al.[13], we discussed and systematically analysed how Neural ODEs (NODEs) can learn higher-order order dynamics.
Discovering outliers in the Mars Express thermal power consumption patterns
The Mars Express (MEX) spacecraft has been orbiting Mars since 2004.
GalaxAI: Machine learning toolbox for interpretable analysis of spacecraft telemetry data
We present GalaxAI - a versatile machine learning toolbox for efficient and interpretable end-to-end analysis of spacecraft telemetry data.
Attentional Meta-learners for Few-shot Polythetic Classification
Polythetic classifications, based on shared patterns of features that need neither be universal nor constant among members of a class, are common in the natural world and greatly outnumber monothetic classifications over a set of features.
$\alpha$-VAEs : Optimising variational inference by learning data-dependent divergence skew
The {\em skew-geometric Jensen-Shannon divergence} $\left(\textrm{JS}^{\textrm{G}_{\alpha}}\right)$ allows for an intuitive interpolation between forward and reverse Kullback-Leibler (KL) divergence based on the skew parameter $\alpha$.
Improving Interpretability in Medical Imaging Diagnosis using Adversarial Training
We investigate the influence of adversarial training on the interpretability of convolutional neural networks (CNNs), specifically applied to diagnosing skin cancer.
Using ontology embeddings for structural inductive bias in gene expression data analysis
Stratifying cancer patients based on their gene expression levels allows improving diagnosis, survival analysis and treatment planning.
Incorporating network based protein complex discovery into automated model construction
We propose a method for gene expression based analysis of cancer phenotypes incorporating network biology knowledge through unsupervised construction of computational graphs.
Fuzzy Jaccard Index: A robust comparison of ordered lists
In real-life, and in particular high-dimensional domains, where only a small percentage of the whole feature space might be relevant, a robust and confident feature ranking leads to interpretable findings as well as efficient computation and good predictive performance.
Constraining Variational Inference with Geometric Jensen-Shannon Divergence
We examine the problem of controlling divergences for latent space regularisation in variational autoencoders.
On Second Order Behaviour in Augmented Neural ODEs
Neural Ordinary Differential Equations (NODEs) are a new class of models that transform data continuously through infinite-depth architectures.
Ranked #22 on
Image Classification
on MNIST
Equation Discovery for Nonlinear System Identification
In this paper, recent developments of the equation discovery method called process-based modeling, suited for nonlinear system identification, are elaborated and illustrated on two continuous-time case studies.
Machine learning for predicting thermal power consumption of the Mars Express Spacecraft
The thermal subsystem of the Mars Express (MEX) spacecraft keeps the on-board equipment within its pre-defined operating temperatures range.
