Search Results for author: Pietro Liò

Found 134 papers, 66 papers with code

SynFlowNet: Towards Molecule Design with Guaranteed Synthesis Pathways

1 code implementation2 May 2024 Miruna Cretu, Charles Harris, Julien Roy, Emmanuel Bengio, Pietro Liò

Recent breakthroughs in generative modelling have led to a number of works proposing molecular generation models for drug discovery.

Drug Discovery Retrosynthesis

Sphere Neural-Networks for Rational Reasoning

no code implementations22 Mar 2024 Tiansi Dong, Mateja Jamnik, Pietro Liò

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).

Hallucination Logical Reasoning +2

Wet TinyML: Chemical Neural Network Using Gene Regulation and Cell Plasticity

no code implementations13 Mar 2024 Samitha Somathilaka, Adrian Ratwatte, Sasitharan Balasubramaniam, Mehmet Can Vuran, Witawas Srisa-an, Pietro Liò

This study advances this concept by incorporating cell plasticity, to further exploit natural cell's adaptability, in order to diversify the GRNN search that can match larger spectrum as well as dynamic computing tasks.

Optimizing Polynomial Graph Filters: A Novel Adaptive Krylov Subspace Approach

1 code implementation12 Mar 2024 Keke Huang, Wencai Cao, Hoang Ta, Xiaokui Xiao, Pietro Liò

To bypass eigendecomposition, polynomial graph filters are proposed to approximate graph filters by leveraging various polynomial bases for filter training.

Understanding Biology in the Age of Artificial Intelligence

no code implementations6 Mar 2024 Elsa Lawrence, Adham El-Shazly, Srijit Seal, Chaitanya K Joshi, Pietro Liò, Shantanu Singh, Andreas Bender, Pietro Sormanni, Matthew Greenig

Modern life sciences research is increasingly relying on artificial intelligence approaches to model biological systems, primarily centered around the use of machine learning (ML) models.

Protein Structure Prediction

Enhancing Real-World Complex Network Representations with Hyperedge Augmentation

no code implementations20 Feb 2024 Xiangyu Zhao, Zehui Li, Mingzhu Shen, Guy-Bart Stan, Pietro Liò, Yiren Zhao

These methods cannot fully address the complexities of real-world large-scale networks that often involve higher-order node relations beyond only being pairwise.

HyperBERT: Mixing Hypergraph-Aware Layers with Language Models for Node Classification on Text-Attributed Hypergraphs

1 code implementation11 Feb 2024 Adrián Bazaga, Pietro Liò, Gos Micklem

In this paper, we propose a new architecture, HyperBERT, a mixed text-hypergraph model which simultaneously models hypergraph relational structure while maintaining the high-quality text encoding capabilities of a pre-trained BERT.

Inductive Bias Language Modelling +1

The Deep Equilibrium Algorithmic Reasoner

no code implementations9 Feb 2024 Dobrik Georgiev, Pietro Liò, Davide Buffelli

Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms.

A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems

1 code implementation12 Dec 2023 Alexandre Duval, Simon V. Mathis, Chaitanya K. Joshi, Victor Schmidt, Santiago Miret, Fragkiskos D. Malliaros, Taco Cohen, Pietro Liò, Yoshua Bengio, Michael Bronstein

In these graphs, the geometric attributes transform according to the inherent physical symmetries of 3D atomic systems, including rotations and translations in Euclidean space, as well as node permutations.

Protein Structure Prediction Specificity

Language Model Knowledge Distillation for Efficient Question Answering in Spanish

1 code implementation7 Dec 2023 Adrián Bazaga, Pietro Liò, Gos Micklem

Recent advances in the development of pre-trained Spanish language models has led to significant progress in many Natural Language Processing (NLP) tasks, such as question answering.

Knowledge Distillation Language Modelling +2

Digital Histopathology with Graph Neural Networks: Concepts and Explanations for Clinicians

no code implementations4 Dec 2023 Alessandro Farace di Villaforesta, Lucie Charlotte Magister, Pietro Barbiero, Pietro Liò

To address the challenge of the ``black-box" nature of deep learning in medical settings, we combine GCExplainer - an automated concept discovery solution - along with Logic Explained Networks to provide global explanations for Graph Neural Networks.

graph construction Panoptic Segmentation

Dual-Domain Multi-Contrast MRI Reconstruction with Synthesis-based Fusion Network

no code implementations1 Dec 2023 Junwei Yang, Pietro Liò

We also compare the reconstruction performance with existing deep learning-based methods using a dataset of brain MRI scans.

MRI Reconstruction

Unsupervised Adaptive Implicit Neural Representation Learning for Scan-Specific MRI Reconstruction

no code implementations1 Dec 2023 Junwei Yang, Pietro Liò

In recent studies on MRI reconstruction, advances have shown significant promise for further accelerating the MRI acquisition.

MRI Reconstruction Representation Learning

An Effective Universal Polynomial Basis for Spectral Graph Neural Networks

no code implementations30 Nov 2023 Keke Huang, Pietro Liò

Afterward, we develop an adaptive heterophily basis by incorporating graph heterophily degrees.

TrafficMOT: A Challenging Dataset for Multi-Object Tracking in Complex Traffic Scenarios

no code implementations30 Nov 2023 Lihao Liu, Yanqi Cheng, Zhongying Deng, Shujun Wang, Dongdong Chen, Xiaowei Hu, Pietro Liò, Carola-Bibiane Schönlieb, Angelica Aviles-Rivero

Multi-object tracking in traffic videos is a crucial research area, offering immense potential for enhancing traffic monitoring accuracy and promoting road safety measures through the utilisation of advanced machine learning algorithms.

Multi-Object Tracking Object

Fourier Neural Differential Equations for learning Quantum Field Theories

1 code implementation28 Nov 2023 Isaac Brant, Alexander Norcliffe, Pietro Liò

A Quantum Field Theory is defined by its interaction Hamiltonian, and linked to experimental data by the scattering matrix.

Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts

1 code implementation25 Nov 2023 Jonas Jürß, Lucie Charlotte Magister, Pietro Barbiero, Pietro Liò, Nikola Simidjievski

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.

Drug Discovery Travel Time Estimation

TRIDENT: The Nonlinear Trilogy for Implicit Neural Representations

no code implementations21 Nov 2023 Zhenda Shen, Yanqi Cheng, Raymond H. Chan, Pietro Liò, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero

Implicit neural representations (INRs) have garnered significant interest recently for their ability to model complex, high-dimensional data without explicit parameterisation.

AMES: A Differentiable Embedding Space Selection Framework for Latent Graph Inference

no code implementations20 Nov 2023 Yuan Lu, Haitz Sáez de Ocáriz Borde, Pietro Liò

More importantly, our interpretability framework provides a general approach for quantitatively comparing embedding spaces across different tasks based on their contributions, a dimension that has been overlooked in previous literature on latent graph inference.

Traffic Video Object Detection using Motion Prior

no code implementations16 Nov 2023 Lihao Liu, Yanqi Cheng, Dongdong Chen, Jing He, Pietro Liò, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero

In this work, we propose two innovative methods to exploit the motion prior and boost the performance of both fully-supervised and semi-supervised traffic video object detection.

Object object-detection +1

From Charts to Atlas: Merging Latent Spaces into One

no code implementations11 Nov 2023 Donato Crisostomi, Irene Cannistraci, Luca Moschella, Pietro Barbiero, Marco Ciccone, Pietro Liò, Emanuele Rodolà

Models trained on semantically related datasets and tasks exhibit comparable inter-sample relations within their latent spaces.

SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation

1 code implementation27 Oct 2023 Adrián Bazaga, Pietro Liò, Gos Micklem

However, some of its key hurdles include domain generalisation, which is the ability to adapt to previously unseen databases, and alignment of natural language questions with the corresponding SQL queries.

Decoder Graph Generation +3

Score-Based Generative Models for Designing Binding Peptide Backbones

1 code implementation10 Oct 2023 John D Boom, Matthew Greenig, Pietro Sormanni, Pietro Liò

We apply our framework to design antibody binding loop structures conditional on a target epitope and evaluate a variety of modelling choices in SGM-based protein design.

Protein Design

Graph Neural Stochastic Differential Equations

no code implementations23 Aug 2023 Richard Bergna, Felix Opolka, Pietro Liò, Jose Miguel Hernandez-Lobato

We present a novel model Graph Neural Stochastic Differential Equations (Graph Neural SDEs).

Out-of-Distribution Detection

Will More Expressive Graph Neural Networks do Better on Generative Tasks?

no code implementations23 Aug 2023 Xiandong Zou, Xiangyu Zhao, Pietro Liò, Yiren Zhao

Moreover, we show that GCPN and GraphAF with advanced GNNs can achieve state-of-the-art results across 17 other non-GNN-based graph generative approaches, such as variational autoencoders and Bayesian optimisation models, on the proposed molecular generative objectives (DRD2, Median1, Median2), which are impor- tant metrics for de-novo molecular design.

Bayesian Optimisation Graph Generation +1

Topological Graph Signal Compression

no code implementations21 Aug 2023 Guillermo Bernárdez, Lev Telyatnikov, Eduard Alarcón, Albert Cabellos-Aparicio, Pere Barlet-Ros, Pietro Liò

Recently emerged Topological Deep Learning (TDL) methods aim to extend current Graph Neural Networks (GNN) by naturally processing higher-order interactions, going beyond the pairwise relations and local neighborhoods defined by graph representations.

Neural Priority Queues for Graph Neural Networks

no code implementations18 Jul 2023 Rishabh Jain, Petar Veličković, Pietro Liò

Graph Neural Networks (GNNs) have shown considerable success in neural algorithmic reasoning.

Graph Regression

SHARCS: Shared Concept Space for Explainable Multimodal Learning

1 code implementation1 Jul 2023 Gabriele Dominici, Pietro Barbiero, Lucie Charlotte Magister, Pietro Liò, Nikola Simidjievski

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.

Retrieval

Graph Denoising Diffusion for Inverse Protein Folding

1 code implementation NeurIPS 2023 Kai Yi, Bingxin Zhou, Yiqing Shen, Pietro Liò, Yu Guang Wang

In contrast, diffusion probabilistic models, as an emerging genre of generative approaches, offer the potential to generate a diverse set of sequence candidates for determined protein backbones.

Denoising Protein Folding

Hybrid Graph: A Unified Graph Representation with Datasets and Benchmarks for Complex Graphs

no code implementations8 Jun 2023 Zehui Li, Xiangyu Zhao, Mingzhu Shen, Guy-Bart Stan, Pietro Liò, Yiren Zhao

Additionally, though many Graph Neural Networks (GNNs) have been proposed for representation learning on higher-order graphs, they are usually only evaluated on simple graph datasets.

Graph Learning Representation Learning

Neural Embeddings for Protein Graphs

no code implementations7 Jun 2023 Francesco Ceccarelli, Lorenzo Giusti, Sean B. Holden, Pietro Liò

Proteins perform much of the work in living organisms, and consequently the development of efficient computational methods for protein representation is essential for advancing large-scale biological research.

CIN++: Enhancing Topological Message Passing

1 code implementation6 Jun 2023 Lorenzo Giusti, Teodora Reu, Francesco Ceccarelli, Cristian Bodnar, Pietro Liò

Our message passing scheme accounts for the aforementioned limitations by letting the cells to receive also lower messages within each layer.

Graph Classification Graph Regression

Renormalized Graph Neural Networks

no code implementations1 Jun 2023 Francesco Caso, Giovanni Trappolini, Andrea Bacciu, Pietro Liò, Fabrizio Silvestri

It is recognized as the preferred lens through which to study complex systems, offering a framework that can untangle their intricate dynamics.

Group Invariant Global Pooling

no code implementations30 May 2023 Kamil Bujel, Yonatan Gideoni, Chaitanya K. Joshi, Pietro Liò

Much work has been devoted to devising architectures that build group-equivariant representations, while invariance is often induced using simple global pooling mechanisms.

Rotated MNIST

gRNAde: Geometric Deep Learning for 3D RNA inverse design

1 code implementation24 May 2023 Chaitanya K. Joshi, Arian R. Jamasb, Ramon Viñas, Charles Harris, Simon Mathis, Alex Morehead, Pietro Liò

Computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D geometry and conformational diversity.

Neural Algorithmic Reasoning for Combinatorial Optimisation

1 code implementation18 May 2023 Dobrik Georgiev, Danilo Numeroso, Davide Bacciu, Pietro Liò

Solving NP-hard/complete combinatorial problems with neural networks is a challenging research area that aims to surpass classical approximate algorithms.

Deep Multiple Instance Learning with Distance-Aware Self-Attention

no code implementations17 May 2023 Georg Wölflein, Lucie Charlotte Magister, Pietro Liò, David J. Harrison, Ognjen Arandjelović

We evaluate our model on a custom MNIST-based MIL dataset that requires the consideration of relative spatial information, as well as on CAMELYON16, a publicly available cancer metastasis detection dataset, where we achieve a test AUROC score of 0. 91.

Cancer Metastasis Detection Multiple Instance Learning +1

Learning Linear Embeddings for Non-Linear Network Dynamics with Koopman Message Passing

no code implementations15 May 2023 King Fai Yeh, Paris Flood, William Redman, Pietro Liò

Recently, Koopman operator theory has become a powerful tool for developing linear representations of non-linear dynamical systems.

valid

Assisting clinical practice with fuzzy probabilistic decision trees

no code implementations16 Apr 2023 Emma L. Ambags, Giulia Capitoli, Vincenzo L' Imperio, Michele Provenzano, Marco S. Nobile, Pietro Liò

In this work, we propose FPT, (MedFP), a novel method that combines probabilistic trees and fuzzy logic to assist clinical practice.

Decision Making

Sheaf4Rec: Sheaf Neural Networks for Graph-based Recommender Systems

1 code implementation7 Apr 2023 Antonio Purificato, Giulia Cassarà, Federico Siciliano, Pietro Liò, Fabrizio Silvestri

GNNs have proven to be effective in addressing the challenges posed by recommendation systems by efficiently modeling graphs in which nodes represent users or items and edges denote preference relationships.

Collaborative Filtering Link Prediction +1

ElegansNet: a brief scientific report and initial experiments

no code implementations6 Apr 2023 Francesco Bardozzo, Andrea Terlizzi, Pietro Liò, Roberto Tagliaferri

The performance of the models is demonstrated against randomly wired networks and compared to artificial networks ranked on global benchmarks.

Image Classification Tensor Networks

Task-Agnostic Graph Neural Network Evaluation via Adversarial Collaboration

1 code implementation27 Jan 2023 Xiangyu Zhao, Hannes Stärk, Dominique Beaini, Yiren Zhao, Pietro Liò

Existing GNN benchmarking methods for molecular representation learning focus on comparing the GNNs' performances on some node/graph classification/regression tasks on certain datasets.

Benchmarking Graph Classification +3

On the Expressive Power of Geometric Graph Neural Networks

1 code implementation23 Jan 2023 Chaitanya K. Joshi, Cristian Bodnar, Simon V. Mathis, Taco Cohen, Pietro Liò

The expressive power of Graph Neural Networks (GNNs) has been studied extensively through the Weisfeiler-Leman (WL) graph isomorphism test.

State of the Art and Potentialities of Graph-level Learning

no code implementations14 Jan 2023 Zhenyu Yang, Ge Zhang, Jia Wu, Jian Yang, Quan Z. Sheng, Shan Xue, Chuan Zhou, Charu Aggarwal, Hao Peng, Wenbin Hu, Edwin Hancock, Pietro Liò

Traditional approaches to learning a set of graphs heavily rely on hand-crafted features, such as substructures.

Graph Learning

Learning Graph Search Heuristics

no code implementations Learning on Graphs 2022 Michal Pándy, Weikang Qiu, Gabriele Corso, Petar Veličković, Rex Ying, Jure Leskovec, Pietro Liò

At training time, we aggregate datasets of search trajectories and ground-truth shortest path distances, which we use to train a specialized graph neural network-based heuristic function using backpropagation through steps of the pathfinding process.

Graph Representation Learning Imitation Learning

A physics-informed search for metric solutions to Ricci flow, their embeddings, and visualisation

no code implementations30 Nov 2022 Aarjav Jain, Challenger Mishra, Pietro Liò

Neural networks with PDEs embedded in their loss functions (physics-informed neural networks) are employed as a function approximators to find solutions to the Ricci flow (a curvature based evolution) of Riemannian metrics.

Continuous Neural Algorithmic Planners

no code implementations29 Nov 2022 Yu He, Petar Veličković, Pietro Liò, Andreea Deac

Neural algorithmic reasoning studies the problem of learning algorithms with neural networks, especially with graph architectures.

Continuous Control

Transductive Kernels for Gaussian Processes on Graphs

no code implementations28 Nov 2022 Yin-Cong Zhi, Felix L. Opolka, Yin Cheng Ng, Pietro Liò, Xiaowen Dong

To address this, we present a novel, generalized kernel for graphs with node feature data for semi-supervised learning.

Gaussian Processes

Latent Graph Inference using Product Manifolds

no code implementations26 Nov 2022 Haitz Sáez de Ocáriz Borde, Anees Kazi, Federico Barbero, Pietro Liò

The original dDGM architecture used the Euclidean plane to encode latent features based on which the latent graphs were generated.

Graph Learning

Learning Feynman Diagrams using Graph Neural Networks

no code implementations25 Nov 2022 Harrison Mitchell, Alexander Norcliffe, Pietro Liò

In the wake of the growing popularity of machine learning in particle physics, this work finds a new application of geometric deep learning on Feynman diagrams to make accurate and fast matrix element predictions with the potential to be used in analysis of quantum field theory.

Graph Attention

Discrete Lagrangian Neural Networks with Automatic Symmetry Discovery

1 code implementation20 Nov 2022 Yana Lishkova, Paul Scherer, Steffen Ridderbusch, Mateja Jamnik, Pietro Liò, Sina Ober-Blöbaum, Christian Offen

By one of the most fundamental principles in physics, a dynamical system will exhibit those motions which extremise an action functional.

Goal-Conditioned Reinforcement Learning in the Presence of an Adversary

no code implementations13 Nov 2022 Carlos Purves, Pietro Liò, Cătălina Cangea

Finally, we unify the two threads and introduce IGOAL: a novel framework for goal-conditioned learning in the presence of an adversary.

reinforcement-learning Reinforcement Learning (RL)

Graph Neural Networks with Adaptive Readouts

1 code implementation9 Nov 2022 David Buterez, Jon Paul Janet, Steven J. Kiddle, Dino Oglic, Pietro Liò

We argue that in some problems such as binding affinity prediction where molecules are typically presented in a canonical form it might be possible to relax the constraints on permutation invariance of the hypothesis space and learn a more effective model of the affinity by employing an adaptive readout function.

Explaining the Explainers in Graph Neural Networks: a Comparative Study

2 code implementations27 Oct 2022 Antonio Longa, Steve Azzolin, Gabriele Santin, Giulia Cencetti, Pietro Liò, Bruno Lepri, Andrea Passerini

Following a fast initial breakthrough in graph based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting the need for methods to understand their decision process.

Node Classification

Global Explainability of GNNs via Logic Combination of Learned Concepts

1 code implementation13 Oct 2022 Steve Azzolin, Antonio Longa, Pietro Barbiero, Pietro Liò, Andrea Passerini

While instance-level explanation of GNN is a well-studied problem with plenty of approaches being developed, providing a global explanation for the behaviour of a GNN is much less explored, despite its potential in interpretability and debugging.

Distributed representations of graphs for drug pair scoring

1 code implementation19 Sep 2022 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.

Transductive Learning

SizeShiftReg: a Regularization Method for Improving Size-Generalization in Graph Neural Networks

1 code implementation16 Jul 2022 Davide Buffelli, Pietro Liò, Fabio Vandin

Previous works have tried to tackle this issue in graph classification by providing the model with inductive biases derived from assumptions on the generative process of the graphs, or by requiring access to graphs from the test domain.

Graph Classification

Approximate Equivariance SO(3) Needlet Convolution

no code implementations17 Jun 2022 Kai Yi, Jialin Chen, Yu Guang Wang, Bingxin Zhou, Pietro Liò, Yanan Fan, Jan Hamann

This paper develops a rotation-invariant needlet convolution for rotation group SO(3) to distill multiscale information of spherical signals.

Quantum Chemistry Regression

Sheaf Neural Networks with Connection Laplacians

1 code implementation17 Jun 2022 Federico Barbero, Cristian Bodnar, Haitz Sáez de Ocáriz Borde, Michael Bronstein, Petar Veličković, Pietro Liò

A Sheaf Neural Network (SNN) is a type of Graph Neural Network (GNN) that operates on a sheaf, an object that equips a graph with vector spaces over its nodes and edges and linear maps between these spaces.

Node Classification

Simplicial Attention Networks

1 code implementation20 Apr 2022 Christopher Wei Jin Goh, Cristian Bodnar, Pietro Liò

Leveraging the success of attention mechanisms in structured domains, we propose Simplicial Attention Networks (SAT), a new type of simplicial network that dynamically weighs the interactions between neighbouring simplicies and can readily adapt to novel structures.

Graph Representation Learning

Modular multi-source prediction of drug side-effects with DruGNN

no code implementations15 Feb 2022 Pietro Bongini, Franco Scarselli, Monica Bianchini, Giovanna Maria Dimitri, Niccolò Pancino, Pietro Liò

Drug Side-Effects (DSEs) have a high impact on public health, care system costs, and drug discovery processes.

Drug Discovery

AI-based Reconstruction for Fast MRI -- A Systematic Review and Meta-analysis

no code implementations23 Dec 2021 Yutong Chen, Carola-Bibiane Schönlieb, Pietro Liò, Tim Leiner, Pier Luigi Dragotti, Ge Wang, Daniel Rueckert, David Firmin, Guang Yang

Compressed sensing (CS) has been playing a key role in accelerating the magnetic resonance imaging (MRI) acquisition process.

Heavy-tailed denoising score matching

1 code implementation17 Dec 2021 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).

Denoising

Spectral Transform Forms Scalable Transformer

1 code implementation15 Nov 2021 Bingxin Zhou, Xinliang Liu, Yuehua Liu, Yunying Huang, Pietro Liò, Yuguang Wang

The architecture is assembled with a few simple effective computational blocks that constitute randomized SVD, MLP, and graph Framelet convolution.

Graph Learning Philosophy

Structure-aware generation of drug-like molecules

no code implementations7 Nov 2021 Pavol Drotár, Arian Rokkum Jamasb, Ben Day, Cătălina Cangea, Pietro Liò

Molecules are built atom-by-atom inside pockets, guided by structural information from crystallographic data.

Adaptive Gaussian Processes on Graphs via Spectral Graph Wavelets

no code implementations25 Oct 2021 Felix L. Opolka, Yin-Cong Zhi, Pietro Liò, Xiaowen Dong

Graph-based models require aggregating information in the graph from neighbourhoods of different sizes.

Gaussian Processes

An investigation of pre-upsampling generative modelling and Generative Adversarial Networks in audio super resolution

no code implementations30 Sep 2021 James King, Ramon Viñas Torné, Alexander Campbell, Pietro Liò

Our paper compares the pre-upsampling AudioUNet to a new generative model that upsamples the signal before using deep learning to transform it into a more believable signal.

Audio Super-Resolution Image Super-Resolution

Neural Distance Embeddings for Biological Sequences

1 code implementation NeurIPS 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.

Multiple Sequence Alignment

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.

Graph Classification Node Classification

Algorithmic Concept-based Explainable Reasoning

1 code implementation15 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 for Few-shot Polythetic Classification

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

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.

Classification feature selection +1

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 implementation ICLR Workshop Learning_to_Learn 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.

Meta-Learning

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.

Disentanglement

Do We Need Anisotropic Graph Neural Networks?

2 code implementations3 Apr 2021 Shyam A. Tailor, Felix L. Opolka, Pietro Liò, Nicholas D. Lane

We demonstrate that EGC outperforms existing approaches across 6 large and diverse benchmark datasets, and conclude by discussing questions that our work raise for the community going forward.

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 Time Series Analysis

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 +3

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

1 code implementation25 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.

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

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.

Clustering

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.

Management Mortality Prediction +2

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

no code implementations8 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 Management

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.

Clustering Molecular Property Prediction +2

On Second Order Behaviour in Augmented Neural ODEs

1 code implementation 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.

Image Classification

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 Representation Learning +2

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 +2

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.

Binary Classification

Deep Graph Mapper: Seeing Graphs through the Neural Lens

1 code implementation NeurIPS Workshop TDA_and_Beyond 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 +5

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.

BIG-bench Machine Learning General Classification +1

Drug-Drug Adverse Effect Prediction with Graph Co-Attention

1 code implementation2 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.

Drug–drug Interaction Extraction

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.

General Classification Graph Classification +3

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

11 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.

Disentanglement

Graph Attention Networks

90 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.

 Ranked #1 on Node Classification on Pubmed (Validation metric)

Document Classification Graph Attention +8

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.