Search Results for author:
Found 45 papers, 19 papers with code
Sphere Neural-Networks for Rational Reasoning
SphNN is the first neural model that can determine the validity of long-chained syllogistic reasoning in one epoch by constructing sphere configurations as Euler diagrams, with the worst computational complexity of O(N^2).
Do Concept Bottleneck Models Obey Locality?
Deep learning models trained under this paradigm heavily rely on the assumption that neural networks can learn to predict the presence or absence of a given concept independently of other concepts.
HEALNet -- Hybrid Multi-Modal Fusion for Heterogeneous Biomedical Data
Technological advances in medical data collection such as high-resolution histopathology and high-throughput genomic sequencing have contributed to the rising requirement for multi-modal biomedical modelling, specifically for image, tabular, and graph data.
Multilingual Mathematical Autoformalization
In this work, we create $\texttt{MMA}$, a large, flexible, multilingual, and multi-domain dataset of informal-formal pairs, by using a language model to translate in the reverse direction, that is, from formal mathematical statements into corresponding informal ones.
Learning to Receive Help: Intervention-Aware Concept Embedding Models
To address this, we propose Intervention-aware Concept Embedding models (IntCEMs), a novel CBM-based architecture and training paradigm that improves a model's receptiveness to test-time interventions.
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 Local Feature Selection for Tabular Biomedical Data
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.
Evaluating Language Models for Mathematics through Interactions
There is much excitement about the opportunity to harness the power of large language models (LLMs) when building problem-solving assistants.
Interpretable Neural-Symbolic Concept Reasoning
Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust.
CGXplain: Rule-Based Deep Neural Network Explanations Using Dual Linear Programs
Rule-based surrogate models are an effective and interpretable way to approximate a Deep Neural Network's (DNN) decision boundaries, allowing humans to easily understand deep learning models.
Human Uncertainty in Concept-Based AI Systems
We study how existing concept-based models deal with uncertain interventions from humans using two novel datasets: UMNIST, a visual dataset with controlled simulated uncertainty based on the MNIST dataset, and CUB-S, a relabeling of the popular CUB concept dataset with rich, densely-annotated soft labels from humans.
GCI: A (G)raph (C)oncept (I)nterpretation Framework
Explainable AI (XAI) underwent a recent surge in research on concept extraction, focusing on extracting human-interpretable concepts from Deep Neural Networks.
Explainable Artificial Intelligence (XAI)
Molecular Property Prediction
+1
Towards Robust Metrics for Concept Representation Evaluation
In this paper, we show that such metrics are not appropriate for concept learning and propose novel metrics for evaluating the purity of concept representations in both approaches.
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.
Discrete Lagrangian Neural Networks with Automatic Symmetry Discovery
By one of the most fundamental principles in physics, a dynamical system will exhibit those motions which extremise an action functional.
Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations
Recent work has suggested post-hoc explainers might be ineffective for detecting spurious correlations in Deep Neural Networks (DNNs).
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) for extracting this implicit structure, and for conditioning the parameters of the first layer of an underlying predictor network.
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
In this work, we introduce Draft, Sketch, and Prove (DSP), a method that maps informal proofs to formal proof sketches, and uses the sketches to guide an automated prover by directing its search to easier sub-problems.
Ranked #3 on
Automated Theorem Proving
on miniF2F-valid
(Pass@100 metric)
Distributed representations of graphs for drug pair scoring
In this paper we study the practicality and usefulness of incorporating distributed representations of graphs into models within the context of drug pair scoring.
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy.
Encoding Concepts in Graph Neural Networks
The opaque reasoning of Graph Neural Networks induces a lack of human trust.
Representational Systems Theory: A Unified Approach to Encoding, Analysing and Transforming Representations
Since Representational Systems Theory provides a universal approach to encoding representational systems, a further key barrier is eliminated: the need to devise system-specific structural transformation algorithms, that are necessary when different systems adopt different formalisation approaches.
Autoformalization with Large Language Models
Autoformalization is the process of automatically translating from natural language mathematics to formal specifications and proofs.
Ranked #1 on
Automated Theorem Proving
on miniF2F-test
(using extra training data)
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
Thor increases a language model's success rate on the PISA dataset from $39\%$ to $57\%$, while solving $8. 2\%$ of problems neither language models nor automated theorem provers are able to solve on their own.
Ranked #2 on
Automated Theorem Proving
on miniF2F-test
Efficient Decompositional Rule Extraction for Deep Neural Networks
In recent years, there has been significant work on increasing both interpretability and debuggability of a Deep Neural Network (DNN) by extracting a rule-based model that approximates its decision boundary.
On The Quality Assurance Of Concept-Based Representations
Recent work on Explainable AI has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as concepts.
Do Concept Bottleneck Models Learn as Intended?
Concept bottleneck models map from raw inputs to concepts, and then from concepts to targets.
Failing Conceptually: Concept-Based Explanations of Dataset Shift
Using two case studies (dSprites and 3dshapes), we demonstrate how CBSD can accurately detect underlying concepts that are affected by shifts and achieve higher detection accuracy compared to state-of-the-art shift detection methods.
Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches
Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models.
MEME: Generating RNN Model Explanations via Model Extraction
Recurrent Neural Networks (RNNs) have achieved remarkable performance on a range of tasks.
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.
Pairwise Relations Discriminator for Unsupervised Raven's Progressive Matrices
PRD reframes the RPM problem into a relation comparison task, which we can solve without requiring the labelling of the RPM problem.
Now You See Me (CME): Concept-based Model Extraction
Deep Neural Networks (DNNs) have achieved remarkable performance on a range of tasks.
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.
Learned Low Precision Graph Neural Networks
LPGNAS learns the optimal architecture coupled with the best quantisation strategy for different components in the GNN automatically using back-propagation in a single search round.
Abstract Diagrammatic Reasoning with Multiplex Graph Networks
We have tested MXGNet on two types of diagrammatic reasoning tasks, namely Diagram Syllogisms and Raven Progressive Matrices (RPM).
Extrapolatable Relational Reasoning With Comparators in Low-Dimensional Manifolds
We show that neural nets with this inductive bias achieve considerably better o. o. d generalisation performance for a range of relational reasoning tasks.
Probabilistic Dual Network Architecture Search on Graphs
We present the first differentiable Network Architecture Search (NAS) for Graph Neural Networks (GNNs).
Structural Inductive Biases in Emergent Communication
In order to communicate, humans flatten a complex representation of ideas and their attributes into a single word or a sentence.
Towards Graph Representation Learning in Emergent Communication
Recent findings in neuroscience suggest that the human brain represents information in a geometric structure (for instance, through conceptual spaces).
Decoupling feature propagation from the design of graph auto-encoders
We present two instances, L-GAE and L-VGAE, of the variational graph auto-encoding family (VGAE) based on separating feature propagation operations from graph convolution layers typically found in graph learning methods to a single linear matrix computation made prior to input in standard auto-encoder architectures.
Bayesian Optimisation with Gaussian Processes for Premise Selection
Heuristics in theorem provers are often parameterised.
Unsupervised and interpretable scene discovery with Discrete-Attend-Infer-Repeat
In this work we present Discrete Attend Infer Repeat (Discrete-AIR), a Recurrent Auto-Encoder with structured latent distributions containing discrete categorical distributions, continuous attribute distributions, and factorised spatial attention.
Step-wise Sensitivity Analysis: Identifying Partially Distributed Representations for Interpretable Deep Learning
In this paper, we introduce a novel method, called step-wise sensitivity analysis, which makes three contributions towards increasing the interpretability of Deep Neural Networks (DNNs).
