paper-with-me

Papers

Micro and Macro Level Graph Modeling for Graph Variational Auto-Encoders

2022-10-30 · Kiarash Zahirnia, Oliver Schulte, Parmis Naddaf, Ke Li

Generative models for graph data are an important research topic in machine learning. Graph data comprise two levels that are typically analyzed separately: node-level properties such as the existence of a link between a pair of nodes, and global aggregate graph-level statistics, such as motif counts. This paper proposes a new multi-level framework that jointly models node-level properties and graph-level statistics, as mutually reinforcing sources of information. We introduce a new micro-macro training objective for graph generation that combines node-level and graph-level losses. We utilize the micro-macro objective to improve graph generation with a GraphVAE, a well-established model based on graph-level latent variables, that provides fast training and generation time for medium-sized graphs. Our experiments show that adding micro-macro modeling to the GraphVAE model improves graph quality scores up to 2 orders of magnitude on five benchmark datasets, while maintaining the GraphVAE generation speed advantage.

📄 PDF Abstract BibTeX arXiv:2210.16844

Code (1)

kiarashza/graphvae-mm 공식 구현 pytorch

Tasks

Graph Generation

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning

2020-12-29 · Le Yu, Leilei Sun, Bowen Du, Chuanren Liu 외

Heterogeneous graphs are pervasive in practical scenarios, where each graph consists of multiple types of nodes and edges. Representation learning on heterogeneous graphs aims to obtain low-dimensional node representatio…

Graph LearningNode Property PredictionRepresentation Learning

Hierarchically Modeling Micro and Macro Behaviors via Multi-Task Learning for Conversion Rate Prediction

2021-04-20 · Hong Wen, Jing Zhang, Fuyu Lv, Wentian Bao 외

Conversion Rate (\emph{CVR}) prediction in modern industrial e-commerce platforms is becoming increasingly important, which directly contributes to the final revenue. In order to address the well-known sample selection b…

Multi-Task LearningPredictionSelection bias

A Microstructure-based Graph Neural Network for Accelerating Multiscale Simulations

2024-02-20 · J. Storm, I. B. C. M. Rocha, F. P. van der Meer

Simulating the mechanical response of advanced materials can be done more accurately using concurrent multiscale models than with single-scale simulations. However, the computational costs stand in the way of the practic…

Graph Neural Network

DualG-MRAG: Decoupling Macro-Reasoning and Micro-Matching for Multimodal Retrieval-Augmented Generation

2026-07-30 · Jiacheng Tao, Qingyun Sun, Haonan Yuan, Ziwei Zhang 외 arxiv

While Multimodal Retrieval-Augmented Generation (MM-RAG) has shown promising results, it still struggles with complex multi-hop reasoning tasks. Existing methods primarily focus on independent instance-level matching, wh…

Automatic Graph Topology-Aware Transformer

2024-05-30 · Chao Wang, Jiaxuan Zhao, Lingling Li, Licheng Jiao 외

Existing efforts are dedicated to designing many topologies and graph-aware strategies for the graph Transformer, which greatly improve the model's representation capabilities. However, manually determining the suitable …