daima2017

Geo-ER

Code for 'Geospatial Entity Resolution' paper (WWW 2022)

REFORM

Graphormer

This is the official implementation for "Do Transformers Really Perform Bad for Graph Representation?".

TKBC

An Interpretable Multi-hop Reasoning (IMR) model for temporal KG forecasting.

entity-matchers

Source code for "A Critical Re-evaluation of Neural Methods for Entity Alignment"

graph-adversarial-learning-literature

A curated list of adversarial attacks and defenses papers on graph-structured data.

EMGCN

This is an implementation of the paper Entity Alignment for Knowledge Graphs with Multi-order Convolutional Networks

CAFE

Knowledge Graph Completion using Neighborhood-Aware Features (published in EAAI)

multihop-knowledge-graph-reasoning

awesome-graph-attack-papers

Adversarial attacks and defenses on Graph Neural Networks.

ActiveEA

ActiveEA: Active Learning for Neural Entity Alignment

Time2Box

KG_Curation

Studies on "Knowledge Graph Curation with Deep Learning and Semantic Reasoning"

TITer

multimodal-deep-learning

This repository contains various models targetting multimodal representation learning, multimodal fusion for downstream tasks such as multimodal sentiment analysis.

RE-GCN

This is the official code release of the following paper: Zixuan Li, Xiaolong Jin, Wei Li, Saiping Guan, Jiafeng Guo, Huawei Shen, Yuanzhuo Wang and Xueqi Cheng. Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning

kiez

Hubness reduced nearest neighbor search for entity alignment with knowledge graph embeddings

SANE

The released code for the paper: Search to aggregate neighborhood for graph neural network, in ICDE 2021.

MELBench

Multimodal entity linking (MEL) aims to utilize multimodal information to map mentions to corresponding entities defined in knowledge bases. We release three MEL datasets: Weibo-MEL, Wikidata-MEL and Richpedia-MEL, containing 25,602, 18,880 and 17,806 samples from social media, encyclopedia and multimodal knowledge graphs respectively. A MEL dataset construction approach is proposed, including five stages: multimodal information extraction, mention extraction, entity extraction, triple construction and dataset construction. Experiment results demonstrate the usability of the datasets and the distinguishability between baseline models.

MEL-GHMF

lcn

Locally corrected Nyström (LCN), as proposed in "Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More" (ICML 2021)

InferenceAttack

Code repository for ACL-IJCNLP 2021 paper 'Poisoning Knowledge Graph Embeddings via Relation Inference Patterns'

KDDCup2021_WikiKG90M_GraphMIRAcles

ZHEClean

Code for the paper "ZHEClean: Cleaning Dirty Knowledge Graphs using Zero Human-labeled Examples"

GAL

[ICML 2021] Information Obfuscation of Graph Neural Networks

DAEM

Deep Entity Matching with Adversarial Active Learning

LIME

source codes

NCA-OSM-to-KGs

This repository provides the code for implementing the class alignments between OpenStreetMap and Knowledge Graphs using an auxiliary neural classification model based on linked entities between OSM and KG

Geocoding

地址标准化

awesome-multimodal-ml

Reading list for research topics in multimodal machine learning