InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions
Authors: Shikhar Vashishth, Soumya Sanyal, Vikram Nitin, Nilesh Agrawal, Partha Talukdar3009-3016
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Through extensive experiments, we find that Interact E outperforms state-of-the-art convolutional link prediction baselines on FB15k-237.In our experiments, following (Dettmers et al. 2018; Sun et al. 2019a), we evaluate on the three most commonly used link prediction datasets. |
| Researcher Affiliation | Collaboration | Shikhar Vashishth,1 Soumya Sanyal,1 Vikram Nitin,2 Nilesh Agrawal,1 Partha Talukdar1 1Indian Institute of Science, 2Columbia University |
| Pseudocode | No | The paper describes the architecture and components of Interact E in text and diagrams (Figure 1), but does not provide pseudocode or a clearly labeled algorithm block. |
| Open Source Code | Yes | We make the source code of Interact E available to encourage reproducible research. The source code of Interact E and datasets used in the paper have been made available at http://github.com/malllabiisc/ Interact E. |
| Open Datasets | Yes | In our experiments, following (Dettmers et al. 2018; Sun et al. 2019a), we evaluate on the three most commonly used link prediction datasets. A summary statistics of the datasets is presented in Table 3. FB15k-237 (Toutanova and Chen 2015) is a improved version of FB15k... WN18RR (Dettmers et al. 2018) is a subset of WN18... YAGO3-10 is a subset of YAGO3 (Suchanek, Kasneci, and Weikum 2007)... Table 3: Details of the datasets used. Train Valid Test FB15k-237 272,115 17,535 20,466 |
| Dataset Splits | Yes | A summary statistics of the datasets is presented in Table 3. Dataset |E| |R| # Triples Train Valid Test FB15k-237 14,541 237 272,115 17,535 20,466 WN18RR 40,943 11 86,835 3,034 3,134 YAGO3-10 123,182 37 1,079,040 5,000 5,000 |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types with speeds, memory amounts) used for running its experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library or solver names with version numbers, needed to replicate the experiment. |
| Experiment Setup | No | The paper describes the datasets and evaluation protocol (Sections 7.1, 7.2) but does not provide specific experimental setup details such as concrete hyperparameter values (e.g., learning rate, batch size, number of epochs) or training configurations. |