A Graph Neural Network Approach for Product Relationship Prediction
<jats:title>Abstract</jats:title> <jats:p>Graph representation learning has revolutionized many artificial intelligence and machine learning tasks in recent years, ranging from combinatorial optimization, drug discovery, recommendation systems, image classification,...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
ASME International
2023
|
| Online Access: | https://hdl.handle.net/1721.1/150663 |
| _version_ | 1811079215384100864 |
|---|---|
| author | Ahmed, Faez Cui, Yaxin Fu, Yan Chen, Wei |
| author2 | Massachusetts Institute of Technology. Department of Mechanical Engineering |
| author_facet | Massachusetts Institute of Technology. Department of Mechanical Engineering Ahmed, Faez Cui, Yaxin Fu, Yan Chen, Wei |
| author_sort | Ahmed, Faez |
| collection | MIT |
| description | <jats:title>Abstract</jats:title>
<jats:p>Graph representation learning has revolutionized many artificial intelligence and machine learning tasks in recent years, ranging from combinatorial optimization, drug discovery, recommendation systems, image classification, social network analysis to natural language understanding. This paper shows their efficacy in modeling relationships between products and making predictions for unseen product networks. By representing products as nodes and their relationships as edges of a graph, we show how an inductive graph neural network approach, named GraphSAGE, can efficiently learn continuous representations for nodes and edges. These representations also capture product feature information such as price, brand, and engineering attributes. They are combined with a classification model for predicting the existence of a relationship between any two products. Using a case study of the Chinese car market, we find that our method yields double the F-1 score compared to an Exponential Random Graph Model-based method for predicting the co-consideration relationship between cars. While a vanilla Graph-SAGE requires a partial network to make predictions, we augment it with an ‘adjacency prediction model’ to circumvent this limitation. This enables us to predict product relationships when no neighborhood information is known. Finally, we demonstrate how a permutation-based interpretability analysis can provide insights on how design attributes impact the predictions of relationships between products. Overall, this work provides a systematic method to predict the relationships between products in a complex engineering system.</jats:p> |
| first_indexed | 2024-09-23T11:11:41Z |
| format | Article |
| id | mit-1721.1/150663 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T11:11:41Z |
| publishDate | 2023 |
| publisher | ASME International |
| record_format | dspace |
| spelling | mit-1721.1/1506632023-05-12T03:34:09Z A Graph Neural Network Approach for Product Relationship Prediction Ahmed, Faez Cui, Yaxin Fu, Yan Chen, Wei Massachusetts Institute of Technology. Department of Mechanical Engineering <jats:title>Abstract</jats:title> <jats:p>Graph representation learning has revolutionized many artificial intelligence and machine learning tasks in recent years, ranging from combinatorial optimization, drug discovery, recommendation systems, image classification, social network analysis to natural language understanding. This paper shows their efficacy in modeling relationships between products and making predictions for unseen product networks. By representing products as nodes and their relationships as edges of a graph, we show how an inductive graph neural network approach, named GraphSAGE, can efficiently learn continuous representations for nodes and edges. These representations also capture product feature information such as price, brand, and engineering attributes. They are combined with a classification model for predicting the existence of a relationship between any two products. Using a case study of the Chinese car market, we find that our method yields double the F-1 score compared to an Exponential Random Graph Model-based method for predicting the co-consideration relationship between cars. While a vanilla Graph-SAGE requires a partial network to make predictions, we augment it with an ‘adjacency prediction model’ to circumvent this limitation. This enables us to predict product relationships when no neighborhood information is known. Finally, we demonstrate how a permutation-based interpretability analysis can provide insights on how design attributes impact the predictions of relationships between products. Overall, this work provides a systematic method to predict the relationships between products in a complex engineering system.</jats:p> 2023-05-11T17:53:13Z 2023-05-11T17:53:13Z 2021 2023-05-11T17:50:23Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/150663 Ahmed, Faez, Cui, Yaxin, Fu, Yan and Chen, Wei. 2021. "A Graph Neural Network Approach for Product Relationship Prediction." Volume 3A: 47th Design Automation Conference (DAC). en 10.1115/DETC2021-69462 Volume 3A: 47th Design Automation Conference (DAC) Creative Commons Attribution-Noncommercial-Share Alike https://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf ASME International arXiv |
| spellingShingle | Ahmed, Faez Cui, Yaxin Fu, Yan Chen, Wei A Graph Neural Network Approach for Product Relationship Prediction |
| title | A Graph Neural Network Approach for Product Relationship Prediction |
| title_full | A Graph Neural Network Approach for Product Relationship Prediction |
| title_fullStr | A Graph Neural Network Approach for Product Relationship Prediction |
| title_full_unstemmed | A Graph Neural Network Approach for Product Relationship Prediction |
| title_short | A Graph Neural Network Approach for Product Relationship Prediction |
| title_sort | graph neural network approach for product relationship prediction |
| url | https://hdl.handle.net/1721.1/150663 |
| work_keys_str_mv | AT ahmedfaez agraphneuralnetworkapproachforproductrelationshipprediction AT cuiyaxin agraphneuralnetworkapproachforproductrelationshipprediction AT fuyan agraphneuralnetworkapproachforproductrelationshipprediction AT chenwei agraphneuralnetworkapproachforproductrelationshipprediction AT ahmedfaez graphneuralnetworkapproachforproductrelationshipprediction AT cuiyaxin graphneuralnetworkapproachforproductrelationshipprediction AT fuyan graphneuralnetworkapproachforproductrelationshipprediction AT chenwei graphneuralnetworkapproachforproductrelationshipprediction |