graphs-4

Graph Reconstruction

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in graph-reconstruction-4

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find graph-reconstruction-4 models and implementations

houchengbin/GloDyNE

2 papers 62

Datasets

Netzschleuder

NBA player performance prediction dataset

Subtasks

No subtasks available.

Most implemented papers

Learning the Graphical Structure of Electronic Health Records with Graph Convolutional Transformer

Yujia Li, Andrew M. Dai, Gerardo Flores, Michael W. Dusenberry, E. Choi, Zhen Xu, Yuan Xue•Mon Jun 10 2019

The proposed model consistently outperformed previous approaches empirically, on both synthetic data and publicly available EHR data, for various prediction tasks such as graph reconstruction and readmission prediction, indicating that it can serve as an effective general-purpose representation learning algorithm for E HR data.

Content

houchengbin/DynWalks

2 papers 62

279

0

Paper Graph

Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference

Yasutaka Furukawa, Nelson Nauata•Tue Dec 10 2019

A 2D architecture vectorization problem, whose task is to infer an outdoor building architecture as a 2D planar graph from a single RGB image, and a novel algorithm utilizing convolutional neural networks that detects geometric primitives and infers their relationships.

37 0

Paper Graph

DynWalks: Global Topology and Recent Changes Awareness Dynamic Network Embedding

Chengbin Hou, Han Zhang, Ke Tang, Shan He•Fri Jul 26 2019

The empirical studies on six real-world dynamic networks under three different slicing ways show that DynWalks significantly outperforms the state-of-the-art methods in graph reconstruction tasks, and obtains comparable results in link prediction tasks.

7 0

Paper Graph

GloDyNE: Global Topology Preserving Dynamic Network Embedding

Chengbin Hou, Ke Tang, Shan He•Tue Aug 04 2020

A novel node selecting strategy to diversely select the representative nodes over a network, coordinated with a new incremental learning paradigm of Skip-Gram based embedding approach is proposed, which significantly outperforms other methods in the graph reconstruction task, which demonstrates its ability of global topology preservation.

35 0

Paper Graph

Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approach

M. Strube, F. L'opez, Beatrice Pozzetti, Steve J. Trettel, Anna Wienhard•Tue Jun 08 2021

A new method, the use of Finsler metrics integrated in a Riemannian optimization scheme, that better adapts to dissimilar structures in the graph is introduced, and a tool to analyze the embeddings and infer structural properties of the data sets is developed.

28 0

Paper Graph

Local2Global: Scaling global representation learning on graphs via local training

Xiaowen Dong, Giovanni Colavizza, Marya Bazzi, Mihai Cucuringu, Lucas G. S. Jeub•Sun Jul 25 2021

A decentralised approach to graph representation learning, that one can a-priori use to scale any embedding technique, that allows local2global to scale to large-scale industrial applications, where the input graph may not even fit into memory and may be stored in a distributed manner.

2 0

Paper Graph

TranSG: Transformer-Based Skeleton Graph Prototype Contrastive Learning with Structure-Trajectory Prompted Reconstruction for Person Re-Identification

Chun Miao, Haocong Rao•Sun Mar 12 2023

A generic Transformer-based Skeleton Graph prototype contrastive learning (TranSG) approach with structure-trajectory prompted reconstruction to fully capture skeletal relations and valuable spatial-temporal semantics from skeleton graphs for person re-ID is proposed.

41 0

Paper Graph

Information Recovery-Driven Deep Incomplete Multiview Clustering Network

Chengliang Liu, Jie Wen, Xiaoling Luo, Chao Huang, Zhihao Wu, Yong Xu•Sat Apr 01 2023

A two-stage autoencoder network with self-attention structure is built to synchronously extract high-level semantic representations of multiple views and recover the missing data, and a recurrent graph reconstruction mechanism is developed that cleverly leverages the restored views to promote representation learning and further data reconstruction.

88 0

Paper Graph

DynamicGEM: A Library for Dynamic Graph Embedding Methods

Ninareh Mehrabi, Emilio Ferrara, Sujit Rokka Chhetri, Palash Goyal, A. Canedo•Sun Nov 25 2018

This work has implemented various metrics to evaluate the state-of-the-art methods, and examples of evolving networks from various domains, and provides a template to add new algorithms with ease to facilitate further research on the topic.

30 0

Paper Graph

Adding a benchmark result helps the community track progress.