zengjian29

pytorch_geometric

Graph Neural Network Library for PyTorch

openspg

OpenSPG is a Knowledge Graph Engine developed by Ant Group in collaboration with OpenKG, based on the SPG (Semantic-enhanced Programmable Graph) framework. Core Capabilities: 1) domain model constrained knowledge modeling, 2) facts and logic fused representation, 3) KAG will be natively supported soon, so please stay tuned...

TrOCR-Seal-Recognition

基于transformer的ocr识别，在公章(印章识别, seal recognition）拓展应用

C-OCR

C-OCR是携程自研的OCR项目，主要包括身份证、护照、火车票、签证等旅游相关证件、材料的识别。 项目包含4个部分，拒识、检测、识别、后处理。

MorsE

[Paper][SIGIR2022] Meta-Knowledge Transfer for Inductive Knowledge Graph Embedding

pypop

PyPop7: A Pure-Python Library for POPulation-based Black-Box Optimization (BBO), especially their *Large-Scale* versions/variants (evolutionary algorithms/swarm-based optimizers/pattern search/...). [https://pypop.rtfd.io/]

grail

Inductive relation prediction by subgraph reasoning, ICML'20

graph-generator

Generate Labeled graphs

ldbc_snb_datagen_spark

Synthetic graph generator for the LDBC Social Network Benchmark, running on Spark

Time-Series-Works-Conferences

Time-Series Work Summary in CS Top Conferences (NIPS, ICML, ICLR, KDD, AAAI, WWW, IJCAI, CIKM, ICDM, ICDE, etc.)

KPLEX

This project includes the source code and the complete experimental results of the paper "A Fast Algorithm to Compute Maximum k-Plexes in Social Network Analysis".

KnapsackFX

Solving Knapsack 0/1 problem with various Local Search algorithms like Hill Climbing, Genetic Algorithms, Simulated Annealing, Tabu Search

knapsack-problem-ga-java

Solves the knapsack problem using genetic algorithm in Java

cord19-kg-importer

A collection of scripts for loading Covid-19 Knowledge Graph into Neo4j

hypdp

graphipedia

Creates a Neo4j graph of Wikipedia links.

Semantic-Similarity

Finding Semantic Similarity using Wikipedia and DbPedia

dbpediaNeo4j

Python script for importing DBpedia nodes and relationships into Neo4j

ReSuM

Pattern Mining in Multi-weighted Graphs

GraMi

GraMi is a novel framework for frequent subgraph mining in a single large graph, GraMi outperforms existing techniques by 2 orders of magnitudes. GraMi supports finding frequent subgraphs as well as frequent patterns, Compared to subgraphs, patterns offer a more powerful version of matching that captures transitive interactions between graph nodes (like friend of a friend) which are very common in modern applications. Also, GraMi supports user-defined structural and semantic constraints over the results, as well as approximate results. For more details, check our paper: Mohammed Elseidy, Ehab Abdelhamid, Spiros Skiadopoulos, and Panos Kalnis. GRAMI: Frequent Subgraph and Pattern Mining in a Single Large Graph. PVLDB, 7(7):517-528, 2014.

gAnswer

A KBQA system based on DBpedia.

neo4j-python-pandas-py2neo-v3

利用pandas将excel中数据抽取，以三元组形式加载到neo4j数据库中构建相关知识图谱

awesome-graph-classification

A collection of important graph embedding, classification and representation learning papers with implementations.

KnowGraphSum

dataflow-join

An implementation of Ngo et al's GenericJoin in timely dataflow.

VoG_Graph_Summarization

Summarization of static graphs using the Minimum Description Length principle

Ngram-Graphs

:mortar_board:RESEARCH [NLP] Analysis of N-gram Graphs and their applications in the domain of Text Classification and Extraction based Summarization

graph_summarization_for_query_evaluation

Compress large graphs and evaluating queries on the large graph

CCKS2018Summary

self summary after attending 2018全国知识图谱与语义计算大会，China Conference on Knowledge Graph and Semantic Computing

KB2E

Knowledge Graph Embeddings including TransE, TransH, TransR and PTransE