Search Results for author: Pietro Liò

Found 58 papers, 33 papers with code

Neural Distance Embeddings for Biological Sequences

1 code implementation20 Sep 2021 Gabriele Corso, Rex Ying, Michal Pándy, Petar Veličković, Jure Leskovec, Pietro Liò

The development of data-dependent heuristics and representations for biological sequences that reflect their evolutionary distance is critical for large-scale biological research.

Hierarchical structure

GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks

no code implementations25 Jul 2021 Lucie Charlotte Magister, Dmitry Kazhdan, Vikash Singh, Pietro Liò

Motivated by the aim of providing global explanations, we adapt the well-known Automated Concept-based Explanation approach (Ghorbani et al., 2019) to GNN node and graph classification, and propose GCExplainer.

Classification Graph Classification +1

High Frequency EEG Artifact Detection with Uncertainty via Early Exit Paradigm

no code implementations21 Jul 2021 Lorena Qendro, Alexander Campbell, Pietro Liò, Cecilia Mascolo

Moreover, these pipelines are deterministic in nature, making them unable to capture predictive uncertainty.


Algorithmic Concept-based Explainable Reasoning

no code implementations15 Jul 2021 Dobrik Georgiev, Pietro Barbiero, Dmitry Kazhdan, Petar Veličković, Pietro Liò

Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems.

Attentional meta-learners are polythetic classifiers

1 code implementation9 Jun 2021 Ben Day, Ramon Viñas, Nikola Simidjievski, Pietro Liò

In contrast, attentional classifiers are polythetic by default and able to solve these problems with a linear embedding dimension.

Feature Selection Few-Shot Learning

Neural message passing for joint paratope-epitope prediction

no code implementations31 May 2021 Alice Del Vecchio, Andreea Deac, Pietro Liò, Petar Veličković

Antibodies are proteins in the immune system which bind to antigens to detect and neutralise them.

Meta-learning using privileged information for dynamics

1 code implementation29 Apr 2021 Ben Day, Alexander Norcliffe, Jacob Moss, Pietro Liò

Neural ODE Processes approach the problem of meta-learning for dynamics using a latent variable model, which permits a flexible aggregation of contextual information.


Is Disentanglement all you need? Comparing Concept-based & Disentanglement Approaches

1 code implementation14 Apr 2021 Dmitry Kazhdan, Botty Dimanov, Helena Andres Terre, Mateja Jamnik, Pietro Liò, Adrian Weller

Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models.

Adaptive Filters and Aggregator Fusion for Efficient Graph Convolutions

1 code implementation3 Apr 2021 Shyam A. Tailor, Felix L. Opolka, Pietro Liò, Nicholas D. Lane

Training and deploying graph neural networks (GNNs) remains difficult due to their high memory consumption and inference latency.

Neural ODE Processes

2 code implementations ICLR 2021 Alexander Norcliffe, Cristian Bodnar, Ben Day, Jacob Moss, Pietro Liò

To address these problems, we introduce Neural ODE Processes (NDPs), a new class of stochastic processes determined by a distribution over Neural ODEs.

Time Series

Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks

1 code implementation4 Mar 2021 Cristian Bodnar, Fabrizio Frasca, Yu Guang Wang, Nina Otter, Guido Montúfar, Pietro Liò, Michael Bronstein

The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems.

Predicting Patient Outcomes with Graph Representation Learning

1 code implementation11 Jan 2021 Emma Rocheteau, Catherine Tong, Petar Veličković, Nicholas Lane, Pietro Liò

Recent work on predicting patient outcomes in the Intensive Care Unit (ICU) has focused heavily on the physiological time series data, largely ignoring sparse data such as diagnoses and medications.

Graph Representation Learning Length-of-Stay prediction +2

Using ontology embeddings for structural inductive bias in gene expression data analysis

no code implementations22 Nov 2020 Maja Trębacz, Zohreh Shams, Mateja Jamnik, Paul Scherer, Nikola Simidjievski, Helena Andres Terre, Pietro Liò

Stratifying cancer patients based on their gene expression levels allows improving diagnosis, survival analysis and treatment planning.

Survival Analysis

Now You See Me (CME): Concept-based Model Extraction

2 code implementations25 Oct 2020 Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik, Pietro Liò, Adrian Weller

Deep Neural Networks (DNNs) have achieved remarkable performance on a range of tasks.

Model extraction

The Role of Isomorphism Classes in Multi-Relational Datasets

no code implementations30 Sep 2020 Vijja Wichitwechkarn, Ben Day, Cristian Bodnar, Matthew Wales, Pietro Liò

The current training and evaluation procedures for these models through the use of synthetic multi-relational datasets however are agnostic to interaction network isomorphism classes, which produce identical dynamics up to initial conditions.

Incorporating network based protein complex discovery into automated model construction

no code implementations29 Sep 2020 Paul Scherer, Maja Trȩbacz, Nikola Simidjievski, Zohreh Shams, Helena Andres Terre, Pietro Liò, Mateja Jamnik

We propose a method for gene expression based analysis of cancer phenotypes incorporating network biology knowledge through unsupervised construction of computational graphs.

Message Passing Neural Processes

no code implementations29 Sep 2020 Ben Day, Cătălina Cangea, Arian R. Jamasb, Pietro Liò

Neural Processes (NPs) are powerful and flexible models able to incorporate uncertainty when representing stochastic processes, while maintaining a linear time complexity.

Few-Shot Learning

Signal metrics analysis of oscillatory patterns in bacterial multi-omic networks

1 code implementation1 Aug 2020 Francesco Bardozzo, Pietro Liò, Roberto Tagliaferri

Results: Network multi-omic integration has led to the discovery of interesting oscillatory signals.

Molecular Networks Computational Engineering, Finance, and Science I.5.2

Temporal Pointwise Convolutional Networks for Length of Stay Prediction in the Intensive Care Unit

1 code implementation18 Jul 2020 Emma Rocheteau, Pietro Liò, Stephanie Hyland

In this work, we propose a new deep learning model based on the combination of temporal convolution and pointwise (1x1) convolution, to solve the length of stay prediction task on the eICU and MIMIC-IV critical care datasets.

Mortality Prediction Predicting Patient Outcomes +1

RicciNets: Curvature-guided Pruning of High-performance Neural Networks Using Ricci Flow

1 code implementation8 Jul 2020 Samuel Glass, Simeon Spasov, Pietro Liò

A novel method to identify salient computational paths within randomly wired neural networks before training is proposed.

Predicting Length of Stay in the Intensive Care Unit with Temporal Pointwise Convolutional Networks

1 code implementation29 Jun 2020 Emma Rocheteau, Pietro Liò, Stephanie Hyland

The pressure of ever-increasing patient demand and budget restrictions make hospital bed management a daily challenge for clinical staff.

Length-of-Stay prediction

Uncertainty in Neural Relational Inference Trajectory Reconstruction

1 code implementation24 Jun 2020 Vasileios Karavias, Ben Day, Pietro Liò

Neural networks used for multi-interaction trajectory reconstruction lack the ability to estimate the uncertainty in their outputs, which would be useful to better analyse and understand the systems they model.

A Multiscale Graph Convolutional Network Using Hierarchical Clustering

no code implementations22 Jun 2020 Alex Lipov, Pietro Liò

The information contained in hierarchical topology, intrinsic to many networks, is currently underutilised.

Molecular Property Prediction Protein Interface Prediction

On Second Order Behaviour in Augmented Neural ODEs

no code implementations NeurIPS 2020 Alexander Norcliffe, Cristian Bodnar, Ben Day, Nikola Simidjievski, Pietro Liò

Neural Ordinary Differential Equations (NODEs) are a new class of models that transform data continuously through infinite-depth architectures.

tvGP-VAE: Tensor-variate Gaussian Process Prior Variational Autoencoder

no code implementations8 Jun 2020 Alex Campbell, Pietro Liò

Using spatiotemporally correlated image time series as an example, we show that the choice of which correlation structures to explicitly represent in the latent space has a significant impact on model performance in terms of reconstruction.

Gaussian Processes Time Series +1

Investigating Estimated Kolmogorov Complexity as a Means of Regularization for Link Prediction

no code implementations7 Jun 2020 Paris D. L. Flood, Ramon Viñas, Pietro Liò

We investigate a flexible means of regularization for link prediction based on an approximation of the Kolmogorov complexity of graphs that is differentiable and compatible with recent advances in link prediction algorithms.

Link Prediction

Neural Bipartite Matching

no code implementations22 May 2020 Dobrik Georgiev, Pietro Liò

Graph neural networks (GNNs) have found application for learning in the space of algorithms.

MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library

1 code implementation16 Apr 2020 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.

Model extraction Multi-agent Reinforcement Learning

Adaptive Prediction Timing for Electronic Health Records

1 code implementation5 Mar 2020 Jacob Deasy, Ari Ercole, Pietro Liò

In realistic scenarios, multivariate timeseries evolve over case-by-case time-scales.

Towards a predictive spatio-temporal representation of brain data

1 code implementation29 Feb 2020 Tiago Azevedo, Luca Passamonti, Pietro Liò, Nicola Toschi

The characterisation of the brain as a "connectome", in which the connections are represented by correlational values across timeseries and as summary measures derived from graph theory analyses, has been very popular in the last years.

Deep Graph Mapper: Seeing Graphs through the Neural Lens

1 code implementation10 Feb 2020 Cristian Bodnar, Cătălina Cangea, Pietro Liò

Recent advancements in graph representation learning have led to the emergence of condensed encodings that capture the main properties of a graph.

Graph Classification Graph Representation Learning +1

Impact of novel aggregation methods for flexible, time-sensitive EHR prediction without variable selection or cleaning

no code implementations17 Sep 2019 Jacob Deasy, Ari Ercole, Pietro Liò

Dynamic assessment of patient status (e. g. by an automated, continuously updated assessment of outcome) in the Intensive Care Unit (ICU) is of paramount importance for early alerting, decision support and resource allocation.

Variable Selection

Dynamic survival prediction in intensive care units from heterogeneous time series without the need for variable selection or pre-processing

no code implementations13 Sep 2019 Jacob Deasy, Pietro Liò, Ari Ercole

Recordings in the first few hours of a patient's stay were found to be strongly predictive of mortality, outperforming models using SAPS II and OASIS scores within just 2 hours and achieving a state of the art Area Under the Receiver Operating Characteristic (AUROC) value of 0. 80 (95% CI 0. 79-0. 80) at 12 hours vs 0. 70 and 0. 66 for SAPS II and OASIS at 24 hours respectively.

Decision Making Feature Engineering +4

Co-Attentive Cross-Modal Deep Learning for Medical Evidence Synthesis and Decision Making

1 code implementation13 Sep 2019 Devin Taylor, Simeon Spasov, Pietro Liò

Modern medicine requires generalised approaches to the synthesis and integration of multimodal data, often at different biological scales, that can be applied to a variety of evidence structures, such as complex disease analyses and epidemiological models.

Decision Making

VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering

1 code implementation14 Aug 2019 Cătălina Cangea, Eugene Belilovsky, Pietro Liò, Aaron Courville

The goal of this dataset is to assess question-answering performance from nearly-ideal navigation paths, while considering a much more complete variety of questions than current instantiations of the EQA task.

Embodied Question Answering Question Answering +1

ncRNA Classification with Graph Convolutional Networks

1 code implementation16 May 2019 Emanuele Rossi, Federico Monti, Michael Bronstein, Pietro Liò

Non-coding RNA (ncRNA) are RNA sequences which don't code for a gene but instead carry important biological functions.

Classification General Classification

On Graph Classification Networks, Datasets and Baselines

no code implementations12 May 2019 Enxhell Luzhnica, Ben Day, Pietro Liò

Graph classification receives a great deal of attention from the non-Euclidean machine learning community.

Classification General Classification +1

Drug-Drug Adverse Effect Prediction with Graph Co-Attention

no code implementations2 May 2019 Andreea Deac, Yu-Hsiang Huang, Petar Veličković, Pietro Liò, Jian Tang

Complex or co-existing diseases are commonly treated using drug combinations, which can lead to higher risk of adverse side effects.

Spatio-Temporal Deep Graph Infomax

no code implementations12 Apr 2019 Felix L. Opolka, Aaron Solomon, Cătălina Cangea, Petar Veličković, Pietro Liò, R. Devon Hjelm

Spatio-temporal graphs such as traffic networks or gene regulatory systems present challenges for the existing deep learning methods due to the complexity of structural changes over time.

Representation Learning Traffic Prediction

ChronoMID - Cross-Modal Neural Networks for 3-D Temporal Medical Imaging Data

no code implementations12 Jan 2019 Alexander G. Rakowski, Petar Veličković, Enrico Dall'Ara, Pietro Liò

ChronoMID builds on the success of cross-modal convolutional neural networks (X-CNNs), making the novel application of the technique to medical imaging data.

General Classification

Modelling trait dependent speciation with Approximate Bayesian Computation

no code implementations10 Dec 2018 Krzysztof Bartoszek, Pietro Liò

The user is not restricted to a predefined set of models and can specify a variety of evolutionary and branching models.

Structure-Based Networks for Drug Validation

no code implementations21 Nov 2018 Cătălina Cangea, Arturas Grauslys, Pietro Liò, Francesco Falciani

Classifying chemicals according to putative modes of action (MOAs) is of paramount importance in the context of risk assessment.

Towards Sparse Hierarchical Graph Classifiers

1 code implementation3 Nov 2018 Cătălina Cangea, Petar Veličković, Nikola Jovanović, Thomas Kipf, Pietro Liò

Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks.

Classification General Classification +4

Introducing Curvature to the Label Space

no code implementations22 Oct 2018 Conor Sheehan, Ben Day, Pietro Liò

One-hot encoding is a labelling system that embeds classes as standard basis vectors in a label space.

General Classification

Deep Graph Infomax

8 code implementations ICLR 2019 Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R. Devon Hjelm

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner.

General Classification Node Classification

Automatic Inference of Cross-modal Connection Topologies for X-CNNs

1 code implementation2 May 2018 Laurynas Karazija, Petar Veličković, Pietro Liò

The base approach learns the topology in a data-driven manner, by using measurements performed on the base CNN and supplied data.

Quantifying the Effects of Enforcing Disentanglement on Variational Autoencoders

1 code implementation24 Nov 2017 Momchil Peychev, Petar Veličković, Pietro Liò

In this paper we quantify the effects of the parameter $\beta$ on the model performance and disentanglement.

Graph Attention Networks

61 code implementations ICLR 2018 Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations.

Document Classification Graph Attention +7

XFlow: Cross-modal Deep Neural Networks for Audiovisual Classification

1 code implementation2 Sep 2017 Cătălina Cangea, Petar Veličković, Pietro Liò

Our work improves on existing multimodal deep learning algorithms in two essential ways: (1) it presents a novel method for performing cross-modality (before features are learned from individual modalities) and (2) extends the previously proposed cross-connections which only transfer information between streams that process compatible data.

Classification General Classification +2

X-CNN: Cross-modal Convolutional Neural Networks for Sparse Datasets

no code implementations1 Oct 2016 Petar Veličković, Duo Wang, Nicholas D. Lane, Pietro Liò

In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing between analogous hidden layers of the network---thus generalising the already well-established concept of neural network ensembles (where information typically may flow only between the output layers of the individual networks).

Data Augmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.