no code implementations • 22 Oct 2024 • Yimeng Min

This paper proposes a framework that formulates a wide range of graph combinatorial optimization problems using permutation-based representations.

1 code implementation • 11 Jun 2024 • Yimeng Min

We identify two major issues in the SoftDist paper (Xia et al.): (1) the failure to run all steps of different baselines on the same hardware environment, and (2) the use of inconsistent time measurements when comparing to other baselines.

no code implementations • 29 Mar 2024 • Yimeng Min, Carla P. Gomes

Our investigation explores how different training instance sizes, embedding dimensions, and distributions influence the outcomes of Unsupervised Learning methods.

1 code implementation • NeurIPS 2023 • Yimeng Min, Yiwei Bai, Carla P. Gomes

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.

1 code implementation • 3 Jun 2022 • Yimeng Min, Frederik Wenkel, Michael Perlmutter, Guy Wolf

We propose a geometric scattering-based graph neural network (GNN) for approximating solutions of the NP-hard maximum clique (MC) problem.

no code implementations • 22 Jan 2022 • Frederik Wenkel, Yimeng Min, Matthew Hirn, Michael Perlmutter, Guy Wolf

We further introduce an attention framework that allows the model to locally attend over combined information from different filters at the node level.

1 code implementation • 24 Dec 2020 • Yimeng Min

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

1 code implementation • 28 Oct 2020 • Yimeng Min, Frederik Wenkel, Guy Wolf

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.

no code implementations • 2 Jul 2020 • Yimeng Min

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.

1 code implementation • NeurIPS 2020 • Yimeng Min, Frederik Wenkel, Guy Wolf

Graph convolutional networks (GCNs) have shown promising results in processing graph data by extracting structure-aware features.

no code implementations • 20 Oct 2019 • Yimeng Min, S. Karthik Mukkavilli, Yoshua Bengio

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.

no code implementations • 25 Sep 2019 • Yimeng Min

The filters propagate exponentially faster($\sigma^2 \sim T^2$) comparing to traditional graph neural network($\sigma^2 \sim T$).

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.