Enhancing Multimodal Knowledge Graph Representation Learning through Triple Contrastive Learning

Authors: Yuxing Lu, Weichen Zhao, Nan Sun, Jinzhuo Wang

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conducted comprehensive comparisons with several knowledge graph embedding methods to validate the effectiveness of our KG-MRI model.
Researcher Affiliation Collaboration 1Department of Big Data and Biomedical AI, College of Future Technology, Peking University 2Tencent AI Lab 3School of Computer Science and Technology, Soochow University 4School of Computer Science and Technology, Huazhong University of Science & Technology
Pseudocode No The paper includes mathematical equations and a framework diagram (Figure 1), but no structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes We constructed a biomedical knowledge graph named HMKG from the Human Metabolome Database (HMDB, https://hmdb.ca/, [Wishart et al., 2022])
Dataset Splits Yes In our experiment, we meticulously partitioned the dataset into training, validation, and testing sets following an 8:1:1 ratio.
Hardware Specification Yes The training was conducted over 1000 epochs on a single Tesla A100 GPU.
Software Dependencies No The paper mentions specific models and optimizers like 'Chem BERTa-2', 'Sci BERT', 'Adam W', and 'Cosine Annealing LR', but does not provide version numbers for these or other software dependencies.
Experiment Setup Yes The hyperparameters were chosen to strike a balance between the model s efficiency and reliability. Both the entity and relation embeddings were initialized with a dimensionality of 128. The learning rate was established at 1.0 x 10^-3.