Search Results for author:
Found 51 papers, 27 papers with code
The Average Mixing Kernel Signature
We introduce the Average Mixing Kernel Signature (AMKS), a novel signature for points on non-rigid three-dimensional shapes based on the average mixing kernel and continuous-time quantum walks.
Position Paper: Challenges and Opportunities in Topological Deep Learning
Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models.
Homomorphism Counts for Graph Neural Networks: All About That Basis
In this work, we show that both of these approaches are sub-optimal in a certain sense and argue for a more fine-grained approach, which incorporates the homomorphism counts of all structures in the "basis" of the target pattern.
Future Directions in Foundations of Graph Machine Learning
Machine learning on graphs, especially using graph neural networks (GNNs), has seen a surge in interest due to the wide availability of graph data across a broad spectrum of disciplines, from life to social and engineering sciences.
A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems
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.
Can strong structural encoding reduce the importance of Message Passing?
This suggests that the importance of message passing is limited when the model can construct strong structural encodings.
Advective Diffusion Transformers for Topological Generalization in Graph Learning
Graph diffusion equations are intimately related to graph neural networks (GNNs) and have recently attracted attention as a principled framework for analyzing GNN dynamics, formalizing their expressive power, and justifying architectural choices.
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly.
Locality-Aware Graph-Rewiring in GNNs
Graph Neural Networks (GNNs) are popular models for machine learning on graphs that typically follow the message-passing paradigm, whereby the feature of a node is updated recursively upon aggregating information over its neighbors.
Cooperative Graph Neural Networks
Graph neural networks are popular architectures for graph machine learning, based on iterative computation of node representations of an input graph through a series of invariant transformations.
GraphText: Graph Reasoning in Text Space
Furthermore, GraphText paves the way for interactive graph reasoning, allowing both humans and LLMs to communicate with the model seamlessly using natural language.
RetroBridge: Modeling Retrosynthesis with Markov Bridges
Retrosynthesis planning is a fundamental challenge in chemistry which aims at designing reaction pathways from commercially available starting materials to a target molecule.
Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
Temporal Graph Benchmark for Machine Learning on Temporal Graphs
We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning models on temporal graphs.
On the Impact of Sample Size in Reconstructing Graph Signals
We show that under the setting of noisy observation and least-squares reconstruction this is not always the case, characterising the behaviour both theoretically and experimentally.
From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
Latent Graph Inference (LGI) relaxed the reliance of Graph Neural Networks (GNNs) on a given graph topology by dynamically learning it.
Edge Directionality Improves Learning on Heterophilic Graphs
Graph Neural Networks (GNNs) have become the de-facto standard tool for modeling relational data.
DRew: Dynamically Rewired Message Passing with Delay
Message passing neural networks (MPNNs) have been shown to suffer from the phenomenon of over-squashing that causes poor performance for tasks relying on long-range interactions.
Ranked #1 on
Graph Classification
on Peptides-func
On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology
Our analysis provides a unified framework to study different recent methods introduced to cope with over-squashing and serves as a justification for a class of methods that fall under graph rewiring.
Curvature Filtrations for Graph Generative Model Evaluation
Graph generative model evaluation necessitates understanding differences between graphs on the distributional level.
Structure-based Drug Design with Equivariant Diffusion Models
Structure-based drug design (SBDD) aims to design small-molecule ligands that bind with high affinity and specificity to pre-determined protein targets.
Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design
Additionally, the model automatically determines the number of atoms in the linker and its attachment points to the input fragments.
Hyperbolic Deep Reinforcement Learning
We propose a new class of deep reinforcement learning (RL) algorithms that model latent representations in hyperbolic space.
Sheaf Neural Networks with Connection Laplacians
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
Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization
In this setting, the agent can take a finite amount of reward-free interactions from a subset of these environments.
Heterogeneous manifolds for curvature-aware graph embedding
Graph embeddings, wherein the nodes of the graph are represented by points in a continuous space, are used in a broad range of Graph ML applications.
Graph Kernel Neural Networks
The convolution operator at the core of many modern neural architectures can effectively be seen as performing a dot product between an input matrix and a filter.
On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
While Graph Neural Networks (GNNs) have recently become the de facto standard for modeling relational data, they impose a strong assumption on the availability of the node or edge features of the graph.
Unsupervised Diffeomorphic Surface Registration and Non-Linear Modelling
The one-step registration model is benchmarked against iterative techniques, trading in a slightly lower performance in terms of shape fit for a higher compactness.
Weisfeiler and Lehman Go Cellular: CW Networks
Nevertheless, these models can be severely constrained by the rigid combinatorial structure of Simplicial Complexes (SCs).
Ranked #1 on
Graph Regression
on ZINC 100k
Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
The pairwise interaction paradigm of graph machine learning has predominantly governed the modelling of relational systems.
Fast geometric learning with symbolic matrices
Geometric methods rely on tensors that can be encoded using a symbolic formula and data arrays, such as kernel and distance matrices.
Non-Rigid Puzzles
We assume to be given a reference shape and its multiple parts undergoing a non-rigid deformation.
3D Facial Matching by Spiral Convolutional Metric Learning and a Biometric Fusion-Net of Demographic Properties
Since embeddings are accepted as an input, there is no need to train classifiers for the different properties and available data can be used more efficiently.
Graph signal processing for machine learning: A review and new perspectives
The effective representation, processing, analysis, and visualization of large-scale structured data, especially those related to complex domains such as networks and graphs, are one of the key questions in modern machine learning.
Temporal Graph Networks for Deep Learning on Dynamic Graphs
Graph Neural Networks (GNNs) have recently become increasingly popular due to their ability to learn complex systems of relations or interactions arising in a broad spectrum of problems ranging from biology and particle physics to social networks and recommendation systems.
Privacy-Aware Recommender Systems Challenge on Twitter's Home Timeline
Recommender systems constitute the core engine of most social network platforms nowadays, aiming to maximize user satisfaction along with other key business objectives.
SIGN: Scalable Inception Graph Neural Networks
Graph representation learning has recently been applied to a broad spectrum of problems ranging from computer graphics and chemistry to high energy physics and social media.
Ranked #5 on
Node Classification
on AMZ Comp
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a direct 3D hand mesh reconstruction loss.
Latent-Graph Learning for Disease Prediction
Recently, Graph Convolutional Networks (GCNs) have proven to be a powerful machine learning tool for Computer-Aided Diagnosis (CADx) and disease prediction.
Differentiable Graph Module (DGM) for Graph Convolutional Networks
We provide an extensive evaluation of applications from the domains of healthcare (disease prediction), brain imaging (age prediction), computer graphics (3D point cloud segmentation), and computer vision (zero-shot learning).
Graph Attentional Autoencoder for Anticancer Hyperfood Prediction
Recent research efforts have shown the possibility to discover anticancer drug-like molecules in food from their effect on protein-protein interaction networks, opening a potential pathway to disease-beating diet design.
SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator
Intrinsic graph convolution operators with differentiable kernel functions play a crucial role in analyzing 3D shape meshes.
ncRNA Classification with Graph Convolutional Networks
Non-coding RNA (ncRNA) are RNA sequences which don't code for a gene but instead carry important biological functions.
Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation
Generative models for 3D geometric data arise in many important applications in 3D computer vision and graphics.
Single Image 3D Hand Reconstruction with Mesh Convolutions
In this paper, we demonstrate an alternative solution that is based on the idea of encoding images into a latent non-linear representation of meshes.
MeshGAN: Non-linear 3D Morphable Models of Faces
Generative Adversarial Networks (GANs) are currently the method of choice for generating visual data.
Deformable Shape Completion with Graph Convolutional Autoencoders
In this work, we propose a novel learning-based method for the completion of partial shapes.
Efficient Deformable Shape Correspondence via Kernel Matching
We present a method to match three dimensional shapes under non-isometric deformations, topology changes and partiality.
Robust Principal Component Analysis on Graphs
Principal Component Analysis (PCA) is the most widely used tool for linear dimensionality reduction and clustering.
Matrix Completion on Graphs
Our main goal is thus to find a low-rank solution that is structured by the proximities of rows and columns encoded by graphs.
Ranked #15 on
Recommendation Systems
on MovieLens 100K
(using extra training data)
