TransE

TransE[NeurIPS 2013]

• paper: Translating Embeddings for Modeling Multi-relational Data

Basic Idea

• Entities and relations are embedded in a continuous low dimensional vector space.
• Judge whether triplet (entities, relationships, entities) can be considered as a fact by similarity based on distance.
• L1 or L2 normal form is used as the similarity calculation method, and the formula is as follows:

$$ f(\textbf{h},\textbf{r},\textbf{t}) = | \textbf{h}+\textbf{r}-\textbf{t} |_{1/2} $$

• The negative samples are constructed by destroying the fact triples to train the model.

$$ S' = \left { (h',r,t) \right |h'\in E } \cup \left { (h,r,t') \right |t'\in E } $$

• The loss calculation method is as follows:

$$ Loss = \sum_{(\textbf{h},\textbf{r},\textbf{t}) \in S}\sum_{(\textbf{h}',\textbf{r},\textbf{t}') \in S'}[\gamma - f(\textbf{h},\textbf{r},\textbf{t}) + f(\textbf{h}',\textbf{r},\textbf{t}')]_{+} $$

• Finally, use BP to update the model.

How to run

• Clone the Openhgnn-DGL

  # For link prediction task
  python main.py -m TransE -t link_prediction -d FB15k -g 0 --use_best_config

  If you do not have gpu, set -gpu -1.

  Supported dataset

  • FB15k

    • Number of entities and relations

      entities	relations
      14,951	1,345

    • Size of dataset

      set type	size
      train set	483,142
      validation set	50,000
      test set	59,071

  • WN18

    • Number of entities and relations

      entities	relations
      40,493	18

    • Size of dataset

      set type	size
      train set	141,442
      validation set	5,000
      test set	5,000

Performance

Task: Link Prediction

Evaluation metric: mrr

Dataset	Mean Rank	Hits@10
FB15k(raw)	188	49.8
FB15k(filt.)	68	66.9
WN18(raw)	319	50.3
WN18(filt.)	303	57.8

TrainerFlow: TransX flow

Hyper-parameter specific to the model

You can modify the parameters[TransE] in openhgnn/config.ini

More

Contirbutor

Xiaoke Yang

If you have any questions

Submit an issue or email to x.k.yang@qq.com.