23 citations · 57 across the 18 of their papers we have counts for
22 papers
An AI Monkey Gets Grapes for Sure -- Sphere Neural Networks for Reliable Decision-Making
Tiansi Dong, Henry He, Pietro Liò +1
This paper compares three methodological categories of neural reasoning: LLM reasoning, supervised learning-based reasoning, and explicit model-based reasoning. LLMs remain unrelia…
TabMDA: Tabular Manifold Data Augmentation for Any Classifier using Transformers with In-context Subsetting
Andrei Margeloiu, Adrián Bazaga, Nikola Simidjievski +2
Tabular data is prevalent in many critical domains, yet it is often challenging to acquire in large quantities. This scarcity usually results in poor performance of machine learnin…
Sphere Neural-Networks for Rational Reasoning
Tiansi Dong, Mateja Jamnik, Pietro Liò
The success of Large Language Models (LLMs), e.g., ChatGPT, is witnessed by their planetary popularity, their capability of human-like communication, and also by their steadily imp…
GCI: A (G)raph (C)oncept (I)nterpretation Framework
Dmitry Kazhdan, Botty Dimanov, Lucie Charlotte Magister +3
Explainable AI (XAI) underwent a recent surge in research on concept extraction, focusing on extracting human-interpretable concepts from Deep Neural Networks. An important challen…
Weight Predictor Network with Feature Selection for Small Sample Tabular Biomedical Data
Andrei Margeloiu, Nikola Simidjievski, Pietro Lio +1
Tabular biomedical data is often high-dimensional but with a very small number of samples. Although recent work showed that well-regularised simple neural networks could outperform…
Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations
Shea Cardozo, Gabriel Islas Montero, Dmitry Kazhdan +4
Recent work has suggested post-hoc explainers might be ineffective for detecting spurious correlations in Deep Neural Networks (DNNs). However, we show there are serious weaknesses…
Discrete Lagrangian Neural Networks with Automatic Symmetry Discovery
Yana Lishkova, Paul Scherer, Steffen Ridderbusch +4
By one of the most fundamental principles in physics, a dynamical system will exhibit those motions which extremise an action functional. This leads to the formation of the Euler-L…
GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data
Andrei Margeloiu, Nikola Simidjievski, Pietro Lio +1
Neural networks often struggle with high-dimensional but small sample-size tabular datasets. One reason is that current weight initialisation methods assume independence between we…
Distributed representations of graphs for drug pair scoring
Paul Scherer, Pietro Liò, Mateja Jamnik
In this paper we study the practicality and usefulness of incorporating distributed representations of graphs into models within the context of drug pair scoring. We argue that the…
Heavy-tailed denoising score matching
Jacob Deasy, Nikola Simidjievski, Pietro Liò
Score-based model research in the last few years has produced state of the art generative models by employing Gaussian denoising score-matching (DSM). However, the Gaussian noise a…
Attentional Meta-learners for Few-shot Polythetic Classification
Ben Day, Ramon Viñas, Nikola Simidjievski +1
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 o…
Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches
Dmitry Kazhdan, Botty Dimanov, Helena Andres Terre +3
Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models. At the same time, the disentanglement le…
MEME: Generating RNN Model Explanations via Model Extraction
Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik +1
Recurrent Neural Networks (RNNs) have achieved remarkable performance on a range of tasks. A key step to further empowering RNN-based approaches is improving their explainability a…
Using ontology embeddings for structural inductive bias in gene expression data analysis
Maja Trębacz, Zohreh Shams, Mateja Jamnik +4
Stratifying cancer patients based on their gene expression levels allows improving diagnosis, survival analysis and treatment planning. However, such data is extremely highly dimen…
Now You See Me (CME): Concept-based Model Extraction
Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik +2
Deep Neural Networks (DNNs) have achieved remarkable performance on a range of tasks. A key step to further empowering DNN-based approaches is improving their explainability. In th…
Incorporating network based protein complex discovery into automated model construction
Paul Scherer, Maja Trȩbacz, Nikola Simidjievski +4
We propose a method for gene expression based analysis of cancer phenotypes incorporating network biology knowledge through unsupervised construction of computational graphs. The s…
Abstract Diagrammatic Reasoning with Multiplex Graph Networks
Duo Wang, Mateja Jamnik, Pietro Lio
Abstract reasoning, particularly in the visual domain, is a complex human ability, but it remains a challenging problem for artificial neural learning systems. In this work we prop…
Constraining Variational Inference with Geometric Jensen-Shannon Divergence
Jacob Deasy, Nikola Simidjievski, Pietro Liò
We examine the problem of controlling divergences for latent space regularisation in variational autoencoders. Specifically, when aiming to reconstruct example …
Extrapolatable Relational Reasoning With Comparators in Low-Dimensional Manifolds
Duo Wang, Mateja Jamnik, Pietro Lio
While modern deep neural architectures generalise well when test data is sampled from the same distribution as training data, they fail badly for cases when the test data distribut…
MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library
Dmitry Kazhdan, Zohreh Shams, Pietro Liò
Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields. An effective way to further empower these…
Learning distributed representations of graphs with Geo2DR
Paul Scherer, Pietro Lio
We present Geo2DR (Geometric to Distributed Representations), a GPU ready Python library for unsupervised learning on graph-structured data using discrete substructure patterns and…
Unsupervised and interpretable scene discovery with Discrete-Attend-Infer-Repeat
Duo Wang, Mateja Jamnik, Pietro Lio
In this work we present Discrete Attend Infer Repeat (Discrete-AIR), a Recurrent Auto-Encoder with structured latent distributions containing discrete categorical distributions, co…