Pairwise learning neural link prediction for ogb link prediction

Related tags

Deep Learning PLNLP
Overview

Pairwise Learning for Neural Link Prediction for OGB (PLNLP-OGB)

This repository provides evaluation codes of PLNLP for OGB link property prediction task. The idea of PLNLP is described in the following article:

Pairwise Learning for Neural Link Prediction (https://arxiv.org/pdf/2112.02936.pdf)

The performance of PLNLP on OGB link prediction tasks is listed as the following tables:

ogbl-ddi (Hits@20) ogbl-collab (Hits@50) ogbl-citation2 (MRR)
Validation 82.42 ± 2.53 100.00 ± 0.00 84.90 ± 0.31
Test 90.88 ± 3.13 68.72 ± 0.52 84.92 ± 0.29

Only with basic graph neural layers (GraphSAGE or GCN), PLNLP achieves Top-1 performance on ogbl-ddi, and Top-2 on both ogbl-collab and ogbl-citation2 in current OGB Link Property Prediction Leader Board, which demonstrates the effectiveness of the proposed framework. We beielve that the performance will be further improved with link prediction specific neural architecure, such as proposed ones in our previous work [2][3]. We leave this part in the future work.

Environment

The code is implemented with PyTorch and PyTorch Geometric. Requirments:
 1. python=3.6
 2. pytorch=1.7.1
 3. ogb=1.3.2
 4. pyg=2.0.1

Reproduction of performance on OGBL

ogbl-ddi:

python main.py --data_name=ogbl-ddi --emb_hidden_channels=512 --gnn_hidden_channels=512 --mlp_hidden_channels=512 --num_neg=3 --epochs=500 --neg_sampler=global --dropout=0.3

ogbl-collab:

Validation set is allowed to be used for training in this dataset. Meanwhile, following the trick of HOP-REC, we only use training edges after year 2010 with validation edges, and train the model on this subgraph.

python main.py --data_name=ogbl-collab --predictor=DOT --use_valedges_as_input=True --year=2010 --train_on_subgraph=True --num_neg=1 --epochs=800 --eval_last_best=True --neg_sampler=global --dropout=0.3

ogbl-citation2:

python main.py --data_name=ogbl-citation2 --use_node_feat=True --encoder=GCN --emb_hidden_channels=50 --mlp_hidden_channels=200 --gnn_hidden_channels=200 --grad_clip_norm=1 --eval_steps=1 --num_neg=3 --eval_metric=mrr --epochs=100 --neg_sampler=local --dropout=0

Reference

This work is based on our previous work as listed below:

[1] Zhitao Wang, Chengyao Chen, Wenjie Li. "Predictive Network Representation Learning for Link Prediction" (SIGIR'17) [Paper]

[2] Zhitao Wang, Yu Lei and Wenjie Li. "Neighborhood Interaction Attention Network for Link Prediction" (CIKM'19) [Paper]

[3] Zhitao Wang, Yu Lei and Wenjie Li. "Neighborhood Attention Networks with Adversarial Learning for Link Prediction " (TNNLS) [Paper]

You might also like...
[CIKM 2019] Code and dataset for "Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction"

FiGNN for CTR prediction The code and data for our paper in CIKM2019: Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Predicti

Big Data and Multi-modal Computing Group, CRIPAC 75 Dec 30, 2022
OHLC Average Prediction of Apple Inc. Using LSTM Recurrent Neural Network
OHLC Average Prediction of Apple Inc. Using LSTM Recurrent Neural Network

Stock Price Prediction of Apple Inc. Using Recurrent Neural Network OHLC Average Prediction of Apple Inc. Using LSTM Recurrent Neural Network Dataset:

Nouroz Rahman 410 Jan 5, 2023
Fast and scalable uncertainty quantification for neural molecular property prediction, accelerated optimization, and guided virtual screening.
Fast and scalable uncertainty quantification for neural molecular property prediction, accelerated optimization, and guided virtual screening.

Evidential Deep Learning for Guided Molecular Property Prediction and Discovery Ava Soleimany*, Alexander Amini*, Samuel Goldman*, Daniela Rus, Sangee

Alexander Amini 75 Dec 15, 2022
Homepage of paper: Paint Transformer: Feed Forward Neural Painting with Stroke Prediction, ICCV 2021.
Homepage of paper: Paint Transformer: Feed Forward Neural Painting with Stroke Prediction, ICCV 2021.

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction [Paper] [PaddlePaddle Implementation] Homepage of paper: Paint Transformer: Fee

null 442 Dec 16, 2022
Neural network for stock price prediction

neural_network_for_stock_price_prediction Neural networks for stock price predic

null 2 Feb 4, 2022
A hybrid framework (neural mass model + ML) for SC-to-FC prediction

The current workflow simulates brain functional connectivity (FC) from structural connectivity (SC) with a neural mass model. Gradient descent is applied to optimize the parameters in the neural mass model.

Yilin Liu 1 Jan 26, 2022
[Link]mareteutral - pars tradg wth M []

pairs-trading-with-ML Jonathan Larkin, August 2017 One popular strategy classification is Pairs Trading. Though this category of strategies can exhibi

Jonathan Larkin 134 Jan 6, 2023
[Link]deep_portfolo - Use Reforcemet earg ad Supervsed learg to Optmze portfolo allocato []

rl_portfolio This Repository uses Reinforcement Learning and Supervised learning to Optimize portfolio allocation. The goal is to make profitable agen

Deepender Singla 165 Dec 2, 2022
Springer Link Download Module for Python
Springer Link Download Module for Python

♞ pupalink A simple Python module to search and download books from SpringerLink. 🧪 This project is still in an early stage of development. Expect br

Pupa Corp. 18 Nov 21, 2022
Comments
  • Questions about use_valedges_as_input and train_on_subgraph on collab

    Questions about use_valedges_as_input and train_on_subgraph on collab

    Thanks for your excellent work on link prediction with GNNs. I have two questions about used tricks on ogbl-collab dataset.

    For trick 'use_valedges_as_input': I note that this trick in original OGB example script contains additional operations: During testing, to obtain scores on training and validation nodes, only raw training edges are used:

    https://github.com/snap-stanford/ogb/blob/c8f0d2aca80a4f885bfd6ad5258ecf1c2d0ac2d9/examples/linkproppred/collab/gnn.py#L140

    Then augmented training edges including validation edges are used to obtain test scores:

    https://github.com/snap-stanford/ogb/blob/c8f0d2aca80a4f885bfd6ad5258ecf1c2d0ac2d9/examples/linkproppred/collab/gnn.py#L166

    But in PLNLP implementation, the raw training edges have been replaced by augmented version including validation edges, which means that training, validation and test scores are all based on augmented training edges. The very 'high' reported validation scores (100%@50) seem over-fitted, which are supposed to be close to test scores (~70%@50).

    For trick 'train_on_subgraph': This trick limits the time range of training edges and validation edges to achieve better performance on test edges. However, it seems that test edges are also filtered (>=2010) in PLNLP. It is a bit confusing for me, since the test set is 'modified'.

    opened by skepsun 4
  • Question about

    Question about "Node-Pair Neighborhood Encoder"

    Thanks for your brilliant work about PLNLP. In the paper "Pairwise Learning for Neural Link Prediction", there exists the application of "Node-Pair Neighborhood Encoder" module, which is used to encode the subgraph corresponding to the target link. It seems that the project does not implement this module, is it because its effect is not obvious? Or is it too inefficient to run? Thank you.

    opened by Walker-ZD 1
Owner
Zhitao WANG
Researcher at WeChat Pay, Tencent
Zhitao WANG
GitHub
Drslmarkov - Distributionally Robust Structure Learning for Discrete Pairwise Markov Networks

Distributionally Robust Structure Learning for Discrete Pairwise Markov Networks

null 1 Nov 24, 2022
Repo for CVPR2021 paper "QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information"

QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information by Masato Tamura, Hiroki Ohashi, and Tomoaki Yosh

null 105 Dec 23, 2022
graph-theoretic framework for robust pairwise data association

CLIPPER: A Graph-Theoretic Framework for Robust Data Association Data association is a fundamental problem in robotics and autonomy. CLIPPER provides

MIT Aerospace Controls Laboratory 118 Dec 28, 2022
Pairwise model for commonlit competition

Pairwise model for commonlit competition To run: - install requirements - create input directory with train_folds.csv and other competition data - cd

abhishek thakur 45 Aug 31, 2022
This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

The Neural Process Family This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CN

DeepMind 892 Dec 28, 2022
"Inductive Entity Representations from Text via Link Prediction" @ The Web Conference 2021

Inductive entity representations from text via link prediction This repository contains the code used for the experiments in the paper "Inductive enti

Daniel Daza 45 Jan 9, 2023
MVGCN: a novel multi-view graph convolutional network (MVGCN) framework for link prediction in biomedical bipartite networks.

MVGCN MVGCN: a novel multi-view graph convolutional network (MVGCN) framework for link prediction in biomedical bipartite networks. Developer: Fu Hait

null 13 Dec 1, 2022
Price-Prediction-For-a-Dream-Home - A machine learning based linear regression trained model for house price prediction.

Price-Prediction-For-a-Dream-Home ROADMAP TO THIS LINEAR REGRESSION BASED HOUSE PRICE PREDICTION PREDICTION MODEL Import all the dependencies of the p

DIKSHA DESWAL 1 Dec 29, 2021
Doge-Prediction - Coding Club prediction ig

Doge-Prediction Coding Club prediction ig Basically: Create an application that

null 1 Jan 10, 2022
Codes and models for the paper "Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction".

GNN_PPI Codes and models for the paper "Learning Unknown from Correlations: Graph Neural Network for Inter-novel-protein Interaction Prediction". Lear

Ursa Zrimsek 2 Dec 14, 2022