paper-with-me

Papers

Maximum Independent Set: Self-Training through Dynamic Programming

2023-10-28 · NeurIPS 2023 11

This work presents a graph neural network (GNN) framework for solving the maximum independent set (MIS) problem, inspired by dynamic programming (DP). Specifically, given a graph, we propose a DP-like recursive algorithm based on GNNs that firstly constructs two smaller sub-graphs, predicts the one with the larger MIS, and then uses it in the next recursive call. To train our algorithm, we require annotated comparisons of different graphs concerning their MIS size. Annotating the comparisons with the output of our algorithm leads to a self-training process that results in more accurate self-annotation of the comparisons and vice versa. We provide numerical evidence showing the superiority of our method vs prior methods in multiple synthetic and real-world datasets.

📄 PDF Abstract BibTeX arXiv:2310.18672

Code (1)

LIONS-EPFL/dynamic-MIS 공식 구현 pytorch

Tasks

Graph Neural Network

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Graph Neural Network 설명 없음

Similar Papers 제목 키워드 기반

Learning for Dynamic Combinatorial Optimization without Training Data

2025-05-26 · Yiqiao Liao, Farinaz Koushanfar, Parinaz Naghizadeh

We introduce DyCO-GNN, a novel unsupervised learning framework for Dynamic Combinatorial Optimization that requires no training data beyond the problem instance itself. DyCO-GNN leverages structural similarities across t…

Combinatorial OptimizationTraveling Salesman Problem

EBMs Trained with Maximum Likelihood are Generator Models Trained with a Self-adverserial Loss

2021-02-23 · ICLR Workshop EBM 2021 5 · Zhisheng Xiao, Qing Yan, Yali Amit

Maximum likelihood estimation is widely used in training Energy-based models (EBMs). Training requires samples from an unnormalized distribution, which is usually intractable, and in practice, these are obtained by MCMC …

Self-supervised Low Light Image Enhancement and Denoising

2021-03-01 · Yu Zhang, Xiaoguang Di, Bin Zhang, Qingyan Li 외

This paper proposes a self-supervised low light image enhancement method based on deep learning, which can improve the image contrast and reduce noise at the same time to avoid the blur caused by pre-/post-denoising. The…

DenoisingImage EnhancementLow-Light Image Enhancement

Multimodal Functional Maximum Correlation for Emotion Recognition

2025-12-28 · Deyang Zheng, Tianyi Zhang, Wenming Zheng, Shujian Yu arxiv

Emotional states manifest as coordinated yet heterogeneous physiological responses across central and autonomic systems, posing a fundamental challenge for multimodal representation learning in affective computing. Learn…

Self-Supervised LearningRepresentation LearningEmotion Recognition

Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination

2021-12-22 · Rui Zhao, Jinming Song, Yufeng Yuan, Hu Haifeng 외

We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data. Although such agents can be obtained through self-play training, they can suffer signif…

DiversityReinforcement Learning (RL)