The expressive power of Graph Neural Networks (GNNs) has been studied extensively through the Weisfeiler-Leman (WL) graph isomorphism test.
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.
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.
To address this, we present a novel, generalized kernel for graphs with node feature data for semi-supervised learning.
The original dDGM architecture used the Euclidean plane to encode latent features based on which the latent graphs were generated.
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.
By one of the most fundamental principles in physics, a dynamical system will exhibit those motions which extremise an action functional.
Shadows in videos are difficult to detect because of the large shadow deformation between frames.
Finally, we unify the two threads and introduce IGOAL: a novel framework for goal-conditioned learning in the presence of an adversary.
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.
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.
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.
In this paper we study the practicality and usefulness of incorporating distributed representations of graphs into models within the context of drug pair scoring.
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.
This paper develops a rotation-invariant needlet convolution for rotation group SO(3) to distill multiscale information of spherical signals.
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 #3 on Node Classification on Wisconsin
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.
The core of our framework is two patch-based strategies, where we demonstrate that patch representation is key for performance gain.
Drug Side-Effects (DSEs) have a high impact on public health, care system costs, and drug discovery processes.
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.
Ranked #1 on Node Classification on Wisconsin
Compressed sensing (CS) has been playing a key role in accelerating the magnetic resonance imaging (MRI) acquisition process.
The architecture is assembled with a few simple effective computational blocks that constitute randomized SVD, MLP, and graph Framelet convolution.
Molecular property prediction is one of the fastest-growing applications of deep learning with critical real-world impacts.
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.
The development of data-dependent heuristics and representations for biological sequences that reflect their evolutionary distance is critical for large-scale biological research.
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.
Moreover, these pipelines are deterministic in nature, making them unable to capture predictive uncertainty.
Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems.
Nevertheless, these models can be severely constrained by the rigid combinatorial structure of Simplicial Complexes (SCs).
Ranked #1 on Graph Regression on ZINC 100k
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.
Neural ODE Processes approach the problem of meta-learning for dynamics using a latent variable model, which permits a flexible aggregation of contextual information.
Concept-based explanations have emerged as a popular way of extracting human-interpretable representations from deep discriminative models.
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 #10 on Graph Property Prediction on ogbg-code2
Then we use Poisson Surface Reconstruction to transform the reconstructed point cloud into a 3D mesh.
Ranked #1 on 3D Reconstruction on ShapeNet (Mean metric)
The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems.
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.
Stratifying cancer patients based on their gene expression levels allows improving diagnosis, survival analysis and treatment planning.
Then, we propose the use of the Laplacian eigenvectors as such vector field.
Ranked #2 on Graph Classification on CIFAR10 100k
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.
Neural Processes (NPs) are powerful and flexible models able to incorporate uncertainty when representing stochastic processes, while maintaining a linear time complexity.
We propose a method for gene expression based analysis of cancer phenotypes incorporating network biology knowledge through unsupervised construction of computational graphs.
Results: Network multi-omic integration has led to the discovery of interesting oscillatory signals.
Molecular Networks Computational Engineering, Finance, and Science I.5.2
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.
A novel method to identify salient computational paths within randomly wired neural networks before training is proposed.
The pressure of ever-increasing patient demand and budget restrictions make hospital bed management a daily challenge for clinical staff.
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.
The information contained in hierarchical topology, intrinsic to many networks, is currently underutilised.
Neural Ordinary Differential Equations (NODEs) are a new class of models that transform data continuously through infinite-depth architectures.
Ranked #23 on Image Classification on MNIST
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.
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.
Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields.
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
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.
Recent advancements in graph representation learning have led to the emergence of condensed encodings that capture the main properties of a graph.
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.
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.
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.
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.
Non-coding RNA (ncRNA) are RNA sequences which don't code for a gene but instead carry important biological functions.
Graph classification receives a great deal of attention from the non-Euclidean machine learning community.
Complex or co-existing diseases are commonly treated using drug combinations, which can lead to higher risk of adverse side effects.
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.
ChronoMID builds on the success of cross-modal convolutional neural networks (X-CNNs), making the novel application of the technique to medical imaging data.
Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks.
We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised manner.
Ranked #45 on Node Classification on Citeseer
In this paper we quantify the effects of the parameter $\beta$ on the model performance and disentanglement.
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 Property Prediction on ogbn-proteins
We analyse multimodal time-series data corresponding to weight, sleep and steps measurements.
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.
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).