Knowledge Graph Embedding by Translating on Hyperplanes

Authors: Zhen Wang, Jianwen Zhang, Jianlin Feng, Zheng Chen

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct extensive experiments on link prediction, triplet classification and fact extraction on benchmark datasets like Word Net and Freebase. Experiments show Trans H delivers significant improvements over Trans E on predictive accuracy with comparable capability to scale up.
Researcher Affiliation Collaboration 1Department of Information Science and Technology, Sun Yat-sen University, Guangzhou, China 2Microsoft Research, Beijing, China
Pseudocode No The paper describes the training process in text but does not provide any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statement or link for the open-source code of the described methodology.
Open Datasets Yes We use the same two data sets which are used in Trans E (Bordes et al. 2011; 2013b): WN18, a subset of Wordnet; FB15k, a relatively dense subgraph of Freebase where all entities are present in Wikilinks database 1. Both are released in (Bordes et al. 2013b).
Dataset Splits Yes Table 2: Data sets used in the experiments. Dataset #R #E #Trip. (Train / Valid / Test)
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models, or detailed computer specifications used for running the experiments.
Software Dependencies No The paper mentions models and tools like Trans E, NTN, and Sm2r but does not specify any software dependencies with version numbers (e.g., programming languages, libraries, or frameworks).
Experiment Setup Yes In training Trans H, we use learning rate α for SGD among {0.001, 0.005, 0.01}, the margin γ among {0.25, 0.5, 1, 2}, the embedding dimension k among {50, 75, 100}, the weight C among {0.015625, 0.0625, 0.25, 1.0}, and batch size B among {20, 75, 300, 1200, 4800}. The optimal parameters are determined by the validation set. ... For both datasets, we traverse all the training triplets for 500 rounds.