Search Results for author:
Found 10 papers, 5 papers with code
On Size and Hardness Generalization in Unsupervised Learning for the Travelling Salesman Problem
Our investigation explores how different training instance sizes, embedding dimensions, and distributions influence the outcomes of Unsupervised Learning methods.
Unsupervised Learning for Solving the Travelling Salesman Problem
Our loss function consists of two parts: one pushes the model to find the shortest path and the other serves as a surrogate for the constraint that the route should form a Hamiltonian Cycle.
Can Hybrid Geometric Scattering Networks Help Solve the Maximum Clique Problem?
We propose a geometric scattering-based graph neural network (GNN) for approximating solutions of the NP-hard maximum clique (MC) problem.
Overcoming Oversmoothness in Graph Convolutional Networks via Hybrid Scattering Networks
We further introduce an attention framework that allows the model to locally attend over combined information from different filters at the node level.
Approximating Excited States using Neural Networks
Recently developed neural network-based wave function methods are capable of achieving state-of-the-art results for finding the ground state in real space.
Computational Physics Disordered Systems and Neural Networks
Geometric Scattering Attention Networks
Geometric scattering has recently gained recognition in graph representation learning, and recent work has shown that integrating scattering features in graph convolution networks (GCNs) can alleviate the typical oversmoothing of features in node representation learning.
Persistent Neurons
More precisely, we utilize the end of trajectories and let the parameters explore new landscapes by penalizing the model from converging to the previous solutions under the same initialization.
Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks
Graph convolutional networks (GCNs) have shown promising results in processing graph data by extracting structure-aware features.
Predicting ice flow using machine learning
Though machine learning has achieved notable success in modeling sequential and spatial data for speech recognition and in computer vision, applications to remote sensing and climate science problems are seldom considered.
Beyond Classical Diffusion: Ballistic Graph Neural Network
The filters propagate exponentially faster($\sigma^2 \sim T^2$) comparing to traditional graph neural network($\sigma^2 \sim T$).
