Continuous Query Decomposition for Complex Query Answering in Incomplete Knowledge Graphs

Last update: Dec 29, 2022

Related tags

Overview

Continuous Query Decomposition

This repository contains the official implementation for our ICLR 2021 (Oral) paper, Complex Query Answering with Neural Link Predictors:

@inproceedings{
    arakelyan2021complex,
    title={Complex Query Answering with Neural Link Predictors},
    author={Erik Arakelyan and Daniel Daza and Pasquale Minervini and Michael Cochez},
    booktitle={International Conference on Learning Representations},
    year={2021},
    url={https://openreview.net/forum?id=Mos9F9kDwkz}
}

In this work we present CQD, a method that reuses a pretrained link predictor to answer complex queries, by scoring atom predicates independently and aggregating the scores via t-norms and t-conorms.

Our code is based on an implementation of ComplEx-N3 available here.

Please follow the instructions next to reproduce the results in our experiments.

1. Install the requirements

We recommend creating a new environment:

% conda create --name cqd python=3.8 && conda activate cqd
% pip install -r requirements.txt

2. Download the data

We use 3 knowledge graphs: FB15k, FB15k-237, and NELL. From the root of the repository, download and extract the files to obtain the folder data, containing the sets of triples and queries for each graph.

% wget http://data.neuralnoise.com/cqd-data.tgz
% tar xvf cqd-data.tgz

3. Download the models

Then you need neural link prediction models -- one for each of the datasets. Our pre-trained neural link prediction models are available here:

% wget http://data.neuralnoise.com/cqd-models.tgz
% tar xvf cqd-data.tgz

3. Alternative -- Train your own models

To obtain entity and relation embeddings, we use ComplEx. Use the next commands to train the embeddings for each dataset.

FB15k

% python -m kbc.learn data/FB15k --rank 1000 --reg 0.01 --max_epochs 100  --batch_size 100

FB15k-237

% python -m kbc.learn data/FB15k-237 --rank 1000 --reg 0.05 --max_epochs 100  --batch_size 1000

NELL

% python -m kbc.learn data/NELL --rank 1000 --reg 0.05 --max_epochs 100  --batch_size 1000

Once training is done, the models will be saved in the models directory.

4. Answering queries with CQD

CQD can answer complex queries via continuous (CQD-CO) or combinatorial optimisation (CQD-Beam).

CQD-Beam

Use the kbc.cqd_beam script to answer queries, providing the path to the dataset, and the saved link predictor trained in the previous step. For example,

% python -m kbc.cqd_beam --model_path models/[model_filename].pt

Example:

% PYTHONPATH=. python3 kbc/cqd_beam.py \
  --model_path models/FB15k-model-rank-1000-epoch-100-*.pt \
  --dataset FB15K --mode test --t_norm product --candidates 64 \
  --scores_normalize 0 data/FB15k

models/FB15k-model-rank-1000-epoch-100-1602520745.pt FB15k product 64
ComplEx(
  (embeddings): ModuleList(
    (0): Embedding(14951, 2000, sparse=True)
    (1): Embedding(2690, 2000, sparse=True)
  )
)

[..]

This will save a series of JSON fils with results, e.g.

% cat "topk_d=FB15k_t=product_e=2_2_rank=1000_k=64_sn=0.json"
{
  "MRRm_new": 0.7542805715523118,
  "MRm_new": 50.71081983144581,
  "[email protected]_new": 0.6896709378392843,
  "[email protected]_new": 0.7955001359095913,
  "[email protected]_new": 0.8676865172456019
}

CQD-CO

Use the kbc.cqd_co script to answer queries, providing the path to the dataset, and the saved link predictor trained in the previous step. For example,

% python -m kbc.cqd_co data/FB15k --model_path models/[model_filename].pt --chain_type 1_2

Final Results

All results from the paper can be produced as follows:

% cd results/topk
% ../topk-parse.py *.json | grep rank=1000
d=FB15K rank=1000 & 0.779 & 0.584 & 0.796 & 0.837 & 0.377 & 0.658 & 0.839 & 0.355
d=FB237 rank=1000 & 0.279 & 0.219 & 0.352 & 0.457 & 0.129 & 0.249 & 0.284 & 0.128
d=NELL rank=1000 & 0.343 & 0.297 & 0.410 & 0.529 & 0.168 & 0.283 & 0.536 & 0.157
% cd ../cont
% ../cont-parse.py *.json | grep rank=1000
d=FB15k rank=1000 & 0.454 & 0.191 & 0.796 & 0.837 & 0.336 & 0.513 & 0.816 & 0.319
d=FB15k-237 rank=1000 & 0.213 & 0.131 & 0.352 & 0.457 & 0.146 & 0.222 & 0.281 & 0.132
d=NELL rank=1000 & 0.265 & 0.220 & 0.410 & 0.529 & 0.196 & 0.302 & 0.531 & 0.194

Continuous Query Decomposition for Complex Query Answering in Incomplete Knowledge Graphs

Related tags

Overview

Continuous Query Decomposition

1. Install the requirements

2. Download the data

3. Download the models

3. Alternative -- Train your own models

FB15k

FB15k-237

NELL

4. Answering queries with CQD

CQD-Beam

CQD-CO

Final Results

Owner

UCL Natural Language Processing

audioLIME: Listenable Explanations Using Source Separation

The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color

A collection of SOTA Image Classification Models in PyTorch

Extract MNIST handwritten digits dataset binary file into bmp images

On the Limits of Pseudo Ground Truth in Visual Camera Re-Localization

Pytorch implementation for "Density-aware Chamfer Distance as a Comprehensive Metric for Point Cloud Completion" (NeurIPS 2021)

CC-GENERATOR - A python script for generating CC

Deep Structured Instance Graph for Distilling Object Detectors (ICCV 2021)

Code and Resources for the Transformer Encoder Reasoning Network (TERN)

Dense Prediction Transformers

Tensorflow Implementation of the paper "Spectral Normalization for Generative Adversarial Networks" (ICML 2017 workshop)

Model Agnostic Interpretability for Multiple Instance Learning

EncT5: Fine-tuning T5 Encoder for Non-autoregressive Tasks

Code for the paper "Improved Techniques for Training GANs"

Benchmark library for high-dimensional HPO of black-box models based on Weighted Lasso regression

Industrial knn-based anomaly detection for images. Visit streamlit link to check out the demo.

내가 보려고 정리한 <프로그래밍 기초 Ⅰ> / organized for me

10x faster matrix and vector operations

Prometheus exporter for Cisco Unified Computing System (UCS) Manager

YOLOX-Paddle - A reproduction of YOLOX by PaddlePaddle