graphs-7

Link Property Prediction

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 link-property-prediction-7

Trend

Dataset

Best Model

Actions

ogbl-collab

ogbl-wikikg2

ogbl-ddi

Libraries

i

Use these libraries to find link-property-prediction-7 models and implementations

Datasets

OGB

Subtasks

No subtasks available.

Most implemented papers

Inductive Representation Learning on Large Graphs

J. Leskovec, William L. Hamilton, Z. Ying•Tue Jun 06 2017

GraphSAGE is presented, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data and outperforms strong baselines on three inductive node-classification benchmarks.

18308

Content

ogbl-ppa

ogbl-citation2

ogbl-biokg

0

Paper Graph

AutoSF: Searching Scoring Functions for Knowledge Graph Embedding

Quanming Yao, Yongqi Zhang, Lei Chen, Wenyuan Dai•Thu Apr 25 2019

Results on link prediction and triplets classification show that the searched SFs by AutoSF, are KG dependent, new to the literature, and outperform the state-of- the-art SFs designed by humans.

91 0

Paper Graph

Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning

Yinglong Xia, Muhan Zhang, Pan Li, Kai Wang, Long Jin•Thu Oct 29 2020

It is proved that with labeling trick a sufficiently expressive GNN learns the most expressive node set representations, thus in principle solves any joint learning tasks over node sets.

237 0

Paper Graph

Pairwise Learning for Neural Link Prediction

Zhitao Wang, Yong Zhou, L. Hong, Yuanhang Zou, Hanjing Su, Shouzhi Chen•Sun Dec 05 2021

The framework treats link prediction as a pairwise learning to rank problem and consists of four main components, i.e., neighborhood encoder, link predictor, negative sampler and objective function, which is flexible that any generic graph neural convolution or link prediction specific neural architecture could be employed as neighborhood encoding.

34 0

Paper Graph

Distance-Enhanced Graph Neural Network for Link Prediction

Tao Qin, Lijun Wu, Shufang Xie, Yingce Xia, Boning Li•Thu Dec 31 2020

An anchor-based distance is proposed that brings significant improvement for link prediction with few additional parameters and achieved state-of-the-art result on the drug-drug-interaction and protein-protein-association tasks of OGB.

12 0

Paper Graph

Embedding Knowledge Graphs Attentive to Positional and Centrality Qualities

Jens Lehmann, Afshin Sadeghi, D. Collarana, D. Graux•Thu Dec 31 2020

This work proposes a novel KGE method named Graph Feature Attentive Neural Network (GFA-NN) that computes graphical features of entities that achieves on-par or better results than state-of-the-art KGE solutions.

9 0

Paper Graph

Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction

Zhaocheng Zhu, Jian Tang, Zuobai Zhang, Louis-Pascal Xhonneux•Sat Jun 12 2021

The Neural Bellman-Ford Network (NBFNet) is proposed, a general graph neural network framework that solves the path formulation with learned operators in the generalized Bell man-Ford algorithm, and outperforms existing methods by a large margin in both transductive and inductive settings.

440 0

Paper Graph

Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations

Pontus Stenetorp, Sebastian Riedel, Pasquale Minervini, Yihong Chen•Tue Oct 05 2021

A new self-supervised training objective for multi-relational graph representation learning is proposed, via simply incorporating relation prediction into the commonly used 1vsAll objective, which is especially effective on highly multi- Relational datasets, i.e. datasets with a large number of predicates.

56 0

Paper Graph

VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization

John P. Dickerson, T. Goldstein, Chen Zhu, Mucong Ding, Kezhi Kong, Jingling Li, Furong Huang•Tue Oct 26 2021

VQ-GNN, a universal framework to scale up any convolution-based GNNs using Vector Quantization (VQ) without compromising the performance, is proposed and it is shown that such a compact low-rank version of the gigantic convolution matrix is sufficient both theoretically and experimentally.

60 0

Paper Graph

D-HYPR: Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learning

Gerard de Melo, Samuel S. Sohn, M. Kapadia, Zuohui Fu, Honglu Zhou, Advith Chegu•Tue Dec 21 2021

The resulting formalism, Digraph Hyperbolic Networks (D-HYPR) -- albeit conceptually simple -- generalizes to digraphs where cycles and non-transitive relations are common, and is applicable to multiple downstream tasks including node classification, link presence prediction, and link property prediction.

8 0

Paper Graph

Adding a benchmark result helps the community track progress.