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

A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo

This is the codebase for Diffusion Models Beat GANS on Image Synthesis.

git《Commonsense Knowledge Base Completion with Structural and Semantic Context》(AAAI 2020) GitHub: [fig1]

Deep functional residue identification

This repository provides data for the VAW dataset as described in the CVPR 2021 paper titled "Learning to Predict Visual Attributes in the Wild"

[Preprint] ConvMLP: Hierarchical Convolutional MLPs for Vision, 2021

ADGAN - The Implementation of paper Controllable Person Image Synthesis with Attribute-Decomposed GAN

PICARD - Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models

HybVIO visual-inertial odometry and SLAM system

9th place solution in "Santa 2020 - The Candy Cane Contest"

Multivariate Time Series Forecasting with efficient Transformers. Code for the paper "Long-Range Transformers for Dynamic Spatiotemporal Forecasting."

PyTorch code for the ICCV'21 paper: "Always Be Dreaming: A New Approach for Class-Incremental Learning"

An implementation of Equivariant e2 convolutional kernals into a convolutional self attention network, applied to radio astronomy data.

Implementation for "Seamless Manga Inpainting with Semantics Awareness" (SIGGRAPH 2021 issue)

Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

RuDOLPH: One Hyper-Modal Transformer can be creative as DALL-E and smart as CLIP

YoloAll is a collection of yolo all versions. you you use YoloAll to test yolov3/yolov5/yolox/yolo_fastest

HiPAL: A Deep Framework for Physician Burnout Prediction Using Activity Logs in Electronic Health Records

《Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching》(CVPR 2020)

LSTM-VAE Implementation and Relevant Evaluations