Search Results for author:
Found 44 papers, 22 papers with code
GRANOLA: Adaptive Normalization for Graph Neural Networks
In recent years, significant efforts have been made to refine the design of Graph Neural Network (GNN) layers, aiming to overcome diverse challenges, such as limited expressive power and oversmoothing.
Learning Priors for Non Rigid SfM from Casual Videos
We tackle the long-standing challenge of reconstructing 3D structures and camera positions from videos.
Subgraphormer: Unifying Subgraph GNNs and Graph Transformers via Graph Products
In the realm of Graph Neural Networks (GNNs), two exciting research directions have recently emerged: Subgraph GNNs and Graph Transformers.
Improved Generalization of Weight Space Networks via Augmentations
Learning in deep weight spaces (DWS), where neural networks process the weights of other neural networks, is an emerging research direction, with applications to 2D and 3D neural fields (INRs, NeRFs), as well as making inferences about other types of neural networks.
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.
Graph Metanetworks for Processing Diverse Neural Architectures
However, those works developed architectures tailored to specific networks such as MLPs and CNNs without normalization layers, and generalizing such architectures to other types of networks can be challenging.
Expressive Sign Equivariant Networks for Spectral Geometric Learning
In this work, we demonstrate the benefits of sign equivariance for these tasks.
Data Augmentations in Deep Weight Spaces
Learning in weight spaces, where neural networks process the weights of other deep neural networks, has emerged as a promising research direction with applications in various fields, from analyzing and editing neural fields and implicit neural representations, to network pruning and quantization.
Efficient Subgraph GNNs by Learning Effective Selection Policies
Subgraph GNNs are provably expressive neural architectures that learn graph representations from sets of subgraphs.
Equivariant Deep Weight Space Alignment
To accelerate the alignment process and improve its quality, we propose a novel framework aimed at learning to solve the weight alignment problem, which we name Deep-Align.
Norm-guided latent space exploration for text-to-image generation
Text-to-image diffusion models show great potential in synthesizing a large variety of concepts in new compositions and scenarios.
Hierarchical Graph Neural Network with Cross-Attention for Cross-Device User Matching
Cross-device user matching is a critical problem in numerous domains, including advertising, recommender systems, and cybersecurity.
Graph Positional Encoding via Random Feature Propagation
Two main families of node feature augmentation schemes have been explored for enhancing GNNs: random features and spectral positional encoding.
Equivariant Polynomials for Graph Neural Networks
This paper introduces an alternative expressive power hierarchy based on the ability of GNNs to calculate equivariant polynomials of a certain degree.
Equivariant Architectures for Learning in Deep Weight Spaces
Designing machine learning architectures for processing neural networks in their raw weight matrix form is a newly introduced research direction.
Generalized Laplacian Positional Encoding for Graph Representation Learning
Graph neural networks (GNNs) are the primary tool for processing graph-structured data.
Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries
Subgraph GNNs are a recent class of expressive Graph Neural Networks (GNNs) which model graphs as collections of subgraphs.
Optimizing Tensor Network Contraction Using Reinforcement Learning
Quantum Computing (QC) stands to revolutionize computing, but is currently still limited.
A Simple and Universal Rotation Equivariant Point-cloud Network
Equivariance to permutations and rigid motions is an important inductive bias for various 3D learning problems.
Sign and Basis Invariant Networks for Spectral Graph Representation Learning
We introduce SignNet and BasisNet -- new neural architectures that are invariant to two key symmetries displayed by eigenvectors: (i) sign flips, since if $v$ is an eigenvector then so is $-v$; and (ii) more general basis symmetries, which occur in higher dimensional eigenspaces with infinitely many choices of basis eigenvectors.
Ranked #10 on
Graph Regression
on ZINC-500k
Multi-Task Learning as a Bargaining Game
In this paper, we propose viewing the gradients combination step as a bargaining game, where tasks negotiate to reach an agreement on a joint direction of parameter update.
Ranked #1 on
Multi-Task Learning
on Cityscapes test
Federated Learning with Heterogeneous Architectures using Graph HyperNetworks
Standard Federated Learning (FL) techniques are limited to clients with identical network architectures.
Weisfeiler and Leman go Machine Learning: The Story so far
In recent years, algorithms and neural architectures based on the Weisfeiler--Leman algorithm, a well-known heuristic for the graph isomorphism problem, have emerged as a powerful tool for machine learning with graphs and relational data.
Equivariant Subgraph Aggregation Networks
Thus, we propose to represent each graph as a set of subgraphs derived by some predefined policy, and to process it using a suitable equivariant architecture.
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
Can a generative model be trained to produce images from a specific domain, guided by a text prompt only, without seeing any image?
Deep Permutation Equivariant Structure from Motion
Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i. e., when cameras are both internally and externally calibrated.
Scene-Agnostic Multi-Microphone Speech Dereverberation
We use noisy and noiseless versions of a simulated reverberant dataset to test the proposed architecture.
From Local Structures to Size Generalization in Graph Neural Networks
In this paper, we identify an important type of data where generalization from small to large graphs is challenging: graph distributions for which the local structure depends on the graph size.
Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks
We consider the problem of controlling a partially-observed dynamic process on a graph by a limited number of interventions.
On the Universality of Rotation Equivariant Point Cloud Networks
We first derive two sufficient conditions for an equivariant architecture to have the universal approximation property, based on a novel characterization of the space of equivariant polynomials.
On Size Generalization in Graph Neural Networks
We further demonstrate on several tasks, that training GNNs on small graphs results in solutions which do not generalize to larger graphs.
Secondary Vertex Finding in Jets with Neural Networks
Jet classification is an important ingredient in measurements and searches for new physics at particle coliders, and secondary vertex reconstruction is a key intermediate step in building powerful jet classifiers.
High Energy Physics - Experiment High Energy Physics - Phenomenology
Auxiliary Learning by Implicit Differentiation
Two main challenges arise in this multi-task learning setting: (i) designing useful auxiliary tasks; and (ii) combining auxiliary tasks into a single coherent loss.
Self-Supervised Learning for Domain Adaptation on Point-Clouds
Self-supervised learning (SSL) is a technique for learning useful representations from unlabeled data.
Learning Algebraic Multigrid Using Graph Neural Networks
Efficient numerical solvers for sparse linear systems are crucial in science and engineering.
Set2Graph: Learning Graphs From Sets
Many problems in machine learning can be cast as learning functions from sets to graphs, or more generally to hypergraphs; in short, Set2Graph functions.
On Learning Sets of Symmetric Elements
We first characterize the space of linear layers that are equivariant both to element reordering and to the inherent symmetries of elements, like translation in the case of images.
Controlling Neural Level Sets
In turn, the sample network can be used to incorporate the level set samples into a loss function of interest.
Provably Powerful Graph Networks
It was shown that the popular message passing GNN cannot distinguish between graphs that are indistinguishable by the 1-WL test (Morris et al. 2018; Xu et al. 2019).
Ranked #6 on
Graph Classification
on COLLAB
On the Universality of Invariant Networks
We conclude the paper by proving a necessary condition for the universality of $G$-invariant networks that incorporate only first-order tensors.
Surface Networks via General Covers
Specifically, for the use case of learning spherical signals, our representation provides a low distortion alternative to several popular spherical parameterizations used in deep learning.
Invariant and Equivariant Graph Networks
In this paper we provide a characterization of all permutation invariant and equivariant linear layers for (hyper-)graph data, and show that their dimension, in case of edge-value graph data, is 2 and 15, respectively.
Multi-chart Generative Surface Modeling
The new tensor data representation is used as input to Generative Adversarial Networks for the task of 3D shape generation.
Point Convolutional Neural Networks by Extension Operators
This paper presents Point Convolutional Neural Networks (PCNN): a novel framework for applying convolutional neural networks to point clouds.
Ranked #81 on
3D Point Cloud Classification
on ModelNet40
