Search Results for author:
Found 14 papers, 8 papers with code
On the Completeness of Invariant Geometric Deep Learning Models
Our results fill the gap in the theoretical power of invariant models, contributing to a rigorous and comprehensive understanding of their capabilities.
Latent Graph Diffusion: A Unified Framework for Generation and Prediction on Graphs
We first propose Latent Graph Diffusion (LGD), a generative model that can generate node, edge, and graph-level features of all categories simultaneously.
PyTorch Geometric High Order: A Unified Library for High Order Graph Neural Network
We introduce PyTorch Geometric High Order (PyGHO), a library for High Order Graph Neural Networks (HOGNNs) that extends PyTorch Geometric (PyG).
Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes
Second, on $1$-simplices or edge level, we bridge edge-level random walk and Hodge $1$-Laplacians and design corresponding edge PE respectively.
Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power
Many of the proposed GNN models with provable cycle counting power are based on subgraph GNNs, i. e., extracting a bag of subgraphs from the input graph, generating representations for each subgraph, and using them to augment the representation of the input graph.
P-vectors: A Parallel-Coupled TDNN/Transformer Network for Speaker Verification
Typically, the Time-Delay Neural Network (TDNN) and Transformer can serve as a backbone for Speaker Verification (SV).
From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks
Relational pooling is a framework for building more expressive and permutation-invariant graph neural networks.
Improving Graph Neural Networks on Multi-node Tasks with Labeling Tricks
When we want to learn a node-set representation involving multiple nodes, a common practice in previous works is to directly aggregate the single-node representations obtained by a GNN.
Neural Common Neighbor with Completion for Link Prediction
Despite its outstanding performance in various graph tasks, vanilla Message Passing Neural Network (MPNN) usually fails in link prediction tasks, as it only uses representations of two individual target nodes and ignores the pairwise relation between them.
Ranked #1 on
Link Property Prediction
on ogbl-ddi
Graph Neural Network with Local Frame for Molecular Potential Energy Surface
Projected onto a frame, equivariant features like 3D coordinates are converted to invariant features, so that we can capture geometric information with these projections and decouple the symmetry requirement from GNN design.
Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction
As pointed out by previous works, this two-step procedure results in low discriminating power, as 1-WL-GNNs by nature learn node-level representations instead of link-level.
How Powerful are Spectral Graph Neural Networks
We also establish a connection between the expressive power of spectral GNNs and Graph Isomorphism (GI) testing, the latter of which is often used to characterize spatial GNNs' expressive power.
GLASS: GNN with Labeling Tricks for Subgraph Representation Learning
And training a GLASS model only takes 28% time needed for a SubGNN on average.
Decentralized Baseband Processing with Gaussian Message Passing Detection for Uplink Massive MU-MIMO Systems
Decentralized baseband processing (DBP) architecture, which partitions the base station antennas into multiple antenna clusters, has been recently proposed to alleviate the excessively high interconnect bandwidth, chip input/output data rates, and detection complexity for massive multi-user multiple-input multiple-output (MU-MIMO) systems.
