Giter Club home page Giter Club logo

metap's Introduction

MetaP

Source code of MetaP

Method Overview

Overview

Dataset

Requirements

  • PyTorch==1.6.0
  • Python==3.7.10

Pre-Trained Embeddings

Training

  • With random initialized embeddings for COVID19-One: python main.py --fine_tune --data_form Discard
  • With pre-trained embeddings for NELL-One: python main.py --fine_tune --data_form Pre-Train

Reference

@inproceedings{jiang2021metap,
  title={MetaP: Meta Pattern Learning for One-Shot Knowledge Graph Completion},
  author={Jiang, Zhiyi and Gao, Jianliang and Lv, Xinqi},
  booktitle={Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval},
  pages={2232--2236},
  year={2021}
}

metap's People

Contributors

jzystc avatar

Stargazers

CurryaNa avatar Wang Zhe avatar Yvette avatar LingZhi WiseMed 瓴智医学人工智能 avatar Wendy Mak avatar githubcode9527 avatar avatar Liyyy avatar Jiyao avatar

Watchers

James Cloos avatar avatar

metap's Issues

Hi there, could you plz share the parameters from your experiment?

Hi there, thanks for the code :)
I failed to reproduced the similar result as ones in your paper with parameters below:
dataset: NELL-One
data_form: Pre-Train
few: 1
num_query: 3
metric: Hits@10
learning_rate: 0.001
step: train
mask_ratio: 0
fine_tune: True
rum: True
vbm: True
aggregator: max

The best results I can reproduced right now are(which were way lower than what you posted):
Hit@10 | Hit@5 | Hit@1 | MRR
0.308 | 0.237 | 0.118 | 0.181

So I wonder if there were something wrong with my parameter settings. Could you plz share the parameters you used for your best results? It would help A LOT.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.