Abstract
Graph data has emerged in numerous scientific domains and machine learning techniques have been widely used for analysis and learning of diverse data for prediction and decision. Machine learning techniques can readily address complex problems by leveraging their structural information. But graphs cannot be directly used for existing machine learning algorithms unless encoded as vectors. The problem of efficient representation of graphs is a substantial challenge in graph machine learning. In this paper, we propose a novel two-stage framework for the representation of chemical molecule graphs based on the strengths of Graph Isomorphism Networks (GINs) and Siamese autoencoders. In the first stage, the GIN model is constructed and trained using the structural information of chemical molecule graphs. Node attributes, edge attributes, and edge indices are used as input data, while graph attributes are used as labels. The GIN model effectively captures the structural characteristics of graphs and can accurately predict graph attributes, i.e., molecular properties. It also generates Graph Embeddings, represented as vectors that encode the structural information of graphs. In the second stage, Graph Embedding vectors are further optimized for downstream similarity tasks while preserving the graph structural information. The Siamese autoencoder is constructed and trained, which reduces the dimensionality of the Graph Embedding vectors, while maximizing the preservation of structural information in the original high-dimensional vectors. The resulting low-dimensional Graph Embeddings can be effectively utilized for tasks such as approximate nearest neighbor search. The experimental results demonstrate the effectiveness of our proposed framework in accurately predicting graph similarity.
Original language | English |
---|---|
Title of host publication | Proceedings - 2023 IEEE 6th International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023 |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 113-120 |
Number of pages | 8 |
ISBN (Electronic) | 9798350331288 |
DOIs | |
State | Published - 2023 |
Event | 6th IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023 - Laguna Hills, United States Duration: Sep 25 2023 → Sep 27 2023 |
Publication series
Name | Proceedings - 2023 IEEE 6th International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023 |
---|
Conference
Conference | 6th IEEE International Conference on Artificial Intelligence and Knowledge Engineering, AIKE 2023 |
---|---|
Country/Territory | United States |
City | Laguna Hills |
Period | 09/25/23 → 09/27/23 |
Funding
This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The US government retains and the publisher, by accepting the article for publication, acknowledges that the US government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for US government purposes. DOE will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan).
Keywords
- Autoencoder
- Graph Neural Network
- Graph representation learning
- Similarity Learning