Awesome Open Source
Awesome Open Source


HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding

Source code and dataset for EMNLP 2018 paper: HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding.

Overview of HyTE (proposed method). a temporally aware KG embedding method which explicitly incorporates time in the entity-relation space by stitching each timestamp with a corresponding hyperplane. HyTE not only performs KG inference using temporal guidance, but also predicts temporal scopes for relational facts with missing time annotations. Please refer paper for more details.


  • Compatible with TensorFlow 1.x and Python 3.x.
  • Dependencies can be installed using requirements.txt.


  • Download the processed version of WikiData and YAGO datasets.
  • Unzip the .zip file in data directory.
  • Documents are originally taken from YAGO and Wikidata.


  • After installing python dependencies from requirements.txt.
  • contains TensorFlow (1.x) based implementation of HyTE (proposed method).
  • To start training:
    python -name yago_data_neg_sample_5_mar_10_l2_0.00 -margin 10 -l2 0.00 -neg_sample 5 -gpu 5 -epoch 2000 -data_type yago -version large -test_freq 5
  • Some of the important Available options include:
'-data_type' default ='yago', choices = ['yago','wiki_data'], help ='dataset to choose'
  '-version',  default = 'large', choices = ['large','small'], help = 'data version to choose'
  '-test_freq', 	 default = 25,   	type=int, 	help='testing frequency'
  '-neg_sample', 	 default = 5,   	type=int, 	help='negative samples for training'
  '-gpu', 	 dest="gpu", 		default='1',			help='GPU to use'
  '-name', 	 dest="name", 		help='Name of the run'
  '-lr',	 dest="lr", 		default=0.0001,  type=float,	help='Learning rate'
  '-margin', 	 dest="margin", 	default=1,   	type=float, 	help='margin'
  '-batch', 	 dest="batch_size", 	default= 50000,   	type=int, 	help='Batch size'
  '-epoch', 	 dest="max_epochs", 	default= 5000,   	type=int, 	help='Max epochs'
  '-l2', 	 dest="l2", 		default=0.0, 	type=float, 	help='L2 regularization'
  '-seed', 	 dest="seed", 		default=1234, 	type=int, 	help='Seed for randomization'
  '-inp_dim',  dest="inp_dim", 	default = 128,   	type=int, 	help='')
  '-L1_flag',  dest="L1_flag", 	action='store_false',   	 	help='Hidden state dimension of FC layer'


  • Validate after Training.
  • Use the same model name and test frequency used at training as arguments for the following evalutation--
  • For getting best validation MR and [email protected] for head and tail prediction:
   python -eval_mode valid -model yago_data_neg_sample_5_mar_10_l2_0.00 -test_freq 5
   python -eval_mode valid -model yago_data_neg_sample_5_mar_10_l2_0.00  -test_freq 5

The Evaluation run will output the Best Validation Rank and the corresponding Best Validation Epoch when it was achieved. Note them down for obtaining results on test set.


  • Test after validation using the best validation weights.
  • First run the script once to restore parameters and then dump the predictions corresponding the the test set.
 python -res_epoch `Best Validation Epoch` -onlyTest -restore -name yago_data_neg_sample_5_mar_10_l2_0.00 -margin 10 -l2 0.00 -neg_sample 5 -gpu 0 -data_type yago -version large
python -eval_mode test -test_freq `Best Validation Epoch` -model yago_data_neg_sample_5_mar_10_l2_0.00


  author = 	"Dasgupta, Shib Sankar
		and Ray, Swayambhu Nath
		and Talukdar, Partha",
  title = 	"HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding",
  booktitle = 	"Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing",
  year = 	"2018",
  publisher = 	"Association for Computational Linguistics",
  pages = 	"2001--2011",
  location = 	"Brussels, Belgium",
  url = 	""

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
python (52,051
machine-learning (3,537
tensorflow (2,131
knowledge-graph (121
representation-learning (70
knowledge-base (36
embedding (32
wikidata (27

Find Open Source By Browsing 7,000 Topics Across 59 Categories