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
390 Dec 31, 2022
545 Dec 28, 2022
3 Oct 07, 2022
10 Jul 16, 2022
1.6k Dec 27, 2022
1 Nov 01, 2021
34 Dec 13, 2022
67 Dec 21, 2022
64 Nov 22, 2022
29 Sep 24, 2022
12 Nov 11, 2022
1.5k Jan 01, 2023
21 Nov 05, 2022
90 Dec 27, 2022
14 Dec 19, 2022
7 Apr 13, 2022
2 Jan 03, 2022
5 Aug 14, 2022
2 Mar 12, 2022
2 Dec 20, 2021