no code implementations • 22 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).
no code implementations • 13 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.
no code implementations • 12 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.
no code implementations • 6 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.
no code implementations • 20 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.
no code implementations • 14 Feb 2024 • Theodore Papamarkou, Tolga Birdal, Michael Bronstein, Gunnar Carlsson, Justin Curry, Yue Gao, Mustafa Hajij, Roland Kwitt, Pietro Liò, Paolo Di Lorenzo, Vasileios Maroulas, Nina Miolane, Farzana Nasrin, Karthikeyan Natesan Ramamurthy, Bastian Rieck, Simone Scardapane, Michael T. Schaub, Petar Veličković, Bei Wang, Yusu Wang, Guo-Wei Wei, Ghada Zamzmi
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models.
1 code implementation • 11 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.
no code implementations • 9 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.
1 code implementation • 12 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.
1 code implementation • 7 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.
no code implementations • 4 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.
no code implementations • 1 Dec 2023 • Junwei Yang, Pietro Liò
In recent studies on MRI reconstruction, advances have shown significant promise for further accelerating the MRI acquisition.
no code implementations • 1 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.
no code implementations • 30 Nov 2023 • Keke Huang, Pietro Liò
Afterward, we develop an adaptive heterophily basis by incorporating graph heterophily degrees.
no code implementations • 30 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.
1 code implementation • 28 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.
1 code implementation • 25 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.
no code implementations • 21 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.
no code implementations • 20 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.
no code implementations • 16 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.
no code implementations • 11 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.
1 code implementation • 27 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.
1 code implementation • 10 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.
1 code implementation • 28 Sep 2023 • Adrián Bazaga, Pietro Liò, Gos Micklem
Fact verification aims to verify a claim using evidence from a trustworthy knowledge base.
no code implementations • 23 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.
no code implementations • 23 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).
no code implementations • 21 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.
no code implementations • 18 Jul 2023 • Rishabh Jain, Petar Veličković, Pietro Liò
Graph Neural Networks (GNNs) have shown considerable success in neural algorithmic reasoning.
Ranked #20 on Graph Regression on Peptides-struct
1 code implementation • 17 Jul 2023 • Xuan Zhang, Limei Wang, Jacob Helwig, Youzhi Luo, Cong Fu, Yaochen Xie, Meng Liu, Yuchao Lin, Zhao Xu, Keqiang Yan, Keir Adams, Maurice Weiler, Xiner Li, Tianfan Fu, Yucheng Wang, Haiyang Yu, Yuqing Xie, Xiang Fu, Alex Strasser, Shenglong Xu, Yi Liu, Yuanqi Du, Alexandra Saxton, Hongyi Ling, Hannah Lawrence, Hannes Stärk, Shurui Gui, Carl Edwards, Nicholas Gao, Adriana Ladera, Tailin Wu, Elyssa F. Hofgard, Aria Mansouri Tehrani, Rui Wang, Ameya Daigavane, Montgomery Bohde, Jerry Kurtin, Qian Huang, Tuong Phung, Minkai Xu, Chaitanya K. Joshi, Simon V. Mathis, Kamyar Azizzadenesheli, Ada Fang, Alán Aspuru-Guzik, Erik Bekkers, Michael Bronstein, Marinka Zitnik, Anima Anandkumar, Stefano Ermon, Pietro Liò, Rose Yu, Stephan Günnemann, Jure Leskovec, Heng Ji, Jimeng Sun, Regina Barzilay, Tommi Jaakkola, Connor W. Coley, Xiaoning Qian, Xiaofeng Qian, Tess Smidt, Shuiwang Ji
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
1 code implementation • 1 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.
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.
no code implementations • 8 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.
no code implementations • 7 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.
no code implementations • 6 Jun 2023 • Felix L. Opolka, Yin-Cong Zhi, Pietro Liò, Xiaowen Dong
Graph classification aims to categorise graphs based on their structure and node attributes.
1 code implementation • 6 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.
Ranked #1 on Graph Classification on HIV dataset
no code implementations • 1 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.
no code implementations • 30 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.
1 code implementation • 24 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.
1 code implementation • 18 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.
no code implementations • 17 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.
no code implementations • 15 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.
no code implementations • 16 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.
1 code implementation • 7 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.
no code implementations • 6 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.
1 code implementation • 27 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.
1 code implementation • 23 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.
no code implementations • 14 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.
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.
no code implementations • 30 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.
no code implementations • 29 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.
no code implementations • 28 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.
no code implementations • 26 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.
no code implementations • 25 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.
1 code implementation • 20 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.
no code implementations • 13 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.
no code implementations • CVPR 2023 • Lihao Liu, Jean Prost, Lei Zhu, Nicolas Papadakis, Pietro Liò, Carola-Bibiane Schönlieb, Angelica I Aviles-Rivero
In this work, we argue that accounting for shadow deformation is essential when designing a video shadow detection method.
1 code implementation • 9 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.
2 code implementations • 27 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.
1 code implementation • 13 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.
1 code implementation • 19 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.
1 code implementation • 16 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.
1 code implementation • 17 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.
Ranked #6 on Node Classification on Wisconsin
no code implementations • 17 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.
1 code implementation • 20 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.
no code implementations • 10 Mar 2022 • Lihao Liu, Zhening Huang, Pietro Liò, Carola-Bibiane Schönlieb, Angelica I. Aviles-Rivero
The core of our framework is two patch-based strategies, where we demonstrate that patch representation is key for performance gain.
no code implementations • 15 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.
1 code implementation • 9 Feb 2022 • Cristian Bodnar, Francesco Di Giovanni, Benjamin Paul Chamberlain, Pietro Liò, Michael M. Bronstein
In this paper, we use cellular sheaf theory to show that the underlying geometry of the graph is deeply linked with the performance of GNNs in heterophilic settings and their oversmoothing behaviour.
no code implementations • 23 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.
1 code implementation • 17 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).
1 code implementation • 15 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.
no code implementations • 7 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.
no code implementations • 25 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.
1 code implementation • NeurIPS Workshop AI4Scien 2021 • Hannes Stärk, Dominique Beaini, Gabriele Corso, Prudencio Tossou, Christian Dallago, Stephan Günnemann, Pietro Liò
Molecular property prediction is one of the fastest-growing applications of deep learning with critical real-world impacts.
no code implementations • 30 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.
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.
no code implementations • 25 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.
no code implementations • 21 Jul 2021 • Lorena Qendro, Alexander Campbell, Pietro Liò, Cecilia Mascolo
Moreover, these pipelines are deterministic in nature, making them unable to capture predictive uncertainty.
1 code implementation • 15 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.
1 code implementation • NeurIPS 2021 • Cristian Bodnar, Fabrizio Frasca, Nina Otter, Yu Guang Wang, Pietro Liò, Guido Montúfar, Michael Bronstein
Nevertheless, these models can be severely constrained by the rigid combinatorial structure of Simplicial Complexes (SCs).
Ranked #1 on Graph Regression on ZINC 100k
1 code implementation • 9 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.
no code implementations • 31 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.
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.
1 code implementation • 14 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.
2 code implementations • 3 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.
Ranked #11 on Graph Property Prediction on ogbg-code2
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.
1 code implementation • 5 Mar 2021 • Nikola Zubić, Pietro Liò
Then we use Poisson Surface Reconstruction to transform the reconstructed point cloud into a 3D mesh.
Ranked #2 on Single-View 3D Reconstruction on ShapeNet
1 code implementation • ICLR Workshop GTRL 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.
1 code implementation • 11 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.
1 code implementation • 13 Dec 2020 • Dmitry Kazhdan, Botty Dimanov, Mateja Jamnik, Pietro Liò
Recurrent Neural Networks (RNNs) have achieved remarkable performance on a range of tasks.
no code implementations • 22 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.
1 code implementation • 25 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.
2 code implementations • 6 Oct 2020 • Dominique Beaini, Saro Passaro, Vincent Létourneau, William L. Hamilton, Gabriele Corso, Pietro Liò
Then, we propose the use of the Laplacian eigenvectors as such vector field.
Ranked #2 on Node Classification on PATTERN 100k
no code implementations • 30 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.
no code implementations • 29 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.
no code implementations • 29 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.
1 code implementation • 1 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
1 code implementation • 18 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.
no code implementations • 8 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.
1 code implementation • 29 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.
1 code implementation • 24 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.
no code implementations • 22 Jun 2020 • Alex Lipov, Pietro Liò
The information contained in hierarchical topology, intrinsic to many networks, is currently underutilised.
1 code implementation • NeurIPS 2020 • Jacob Deasy, Nikola Simidjievski, Pietro Liò
We examine the problem of controlling divergences for latent space regularisation in variational autoencoders.
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.
Ranked #21 on Image Classification on MNIST
no code implementations • 8 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.
no code implementations • 7 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.
no code implementations • 22 May 2020 • Dobrik Georgiev, Pietro Liò
Graph neural networks (GNNs) have found application for learning in the space of algorithms.
1 code implementation • 16 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.
8 code implementations • NeurIPS 2020 • Gabriele Corso, Luca Cavalleri, Dominique Beaini, Pietro Liò, Petar Veličković
Graph Neural Networks (GNNs) have been shown to be effective models for different predictive tasks on graph-structured data.
Ranked #4 on Node Classification on PATTERN 100k
1 code implementation • 5 Mar 2020 • Jacob Deasy, Ari Ercole, Pietro Liò
In realistic scenarios, multivariate timeseries evolve over case-by-case time-scales.
1 code implementation • 29 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.
no code implementations • 11 Feb 2020 • Felix L. Opolka, Pietro Liò
Link prediction aims to reveal missing edges in a graph.
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.
no code implementations • 17 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.
no code implementations • 13 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.
1 code implementation • 13 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.
1 code implementation • 14 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.
1 code implementation • 16 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.
no code implementations • 12 May 2019 • Enxhell Luzhnica, Ben Day, Pietro Liò
Graph classification receives a great deal of attention from the non-Euclidean machine learning community.
1 code implementation • 2 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.
no code implementations • 12 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.
no code implementations • 12 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.
no code implementations • 10 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.
no code implementations • 21 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.
1 code implementation • 3 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.
no code implementations • 22 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.
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.
Ranked #49 on Node Classification on Citeseer
1 code implementation • 2 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.
1 code implementation • 24 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.
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)
no code implementations • 23 Sep 2017 • Petar Veličković, Laurynas Karazija, Nicholas D. Lane, Sourav Bhattacharya, Edgar Liberis, Pietro Liò, Angela Chieh, Otmane Bellahsen, Matthieu Vegreville
We analyse multimodal time-series data corresponding to weight, sleep and steps measurements.
1 code implementation • 2 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.
no code implementations • 1 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).