Multi-Vector Embedding on Networks with Taxonomies

Authors: Yue Fan, Xiuli Ma

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments reveal HIME s comprehensive advantages over existing methods on tasks such as proximity search, link prediction and hierarchical classification.
Researcher Affiliation Academia Key Laboratory of Machine Perception (MOE), School of Artificial Intelligence, Peking University, Beijing, China fanyue@pku.edu.cn, xlma@pku.edu.cn
Pseudocode Yes Algorithm 1 The LRU policy.
Open Source Code Yes Code and Appendix: https://github.com/Yue Fan1014/HIME.
Open Datasets Yes A human PPI network [Szklarczyk et al., 2021] with the Cellular Components domain of Gene Ontology [Ashburner et al., 2000] being the taxonomy. A human gene regulatory network [Liu et al., 2015] depicts regulations among genes, with each gene associated with several biological pathways given by CTD [Davis et al., 2020]. All the pathways are organized as a pathway ontology [Petri et al., 2014]. We extract a dense subset of the DBLP coauthorship network with ACM key word taxonomy.
Dataset Splits No We split the node-node links with the ratio of 7:3 and the node-label links with the ratio of 9:1 for training and testing. No explicit mention of a validation set or split was found.
Hardware Specification No No specific hardware details (e.g., GPU model, CPU type, memory) used for running the experiments were provided.
Software Dependencies No No specific software dependencies with version numbers (e.g., Python 3.8, PyTorch 1.9) were provided.
Experiment Setup Yes In the experiments, we set the embedding dimensions of all methods to 256. The branch vector dimensions are 128, 64, 32 for HIME 2, HIME 4 and HIME 8 respectively so as to ensure that a node s total dimension is no greater than 256. All methods are tuned to the best and trained for 100 epochs.