Summary of Modeling Reference-dependent Choices with Graph Neural Networks, by Liang Zhang et al.
Modeling Reference-dependent Choices with Graph Neural Networks
by Liang Zhang, Guannan Liu, Junjie Wu, Yong Tan
First submitted to arxiv on: 21 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed Attributed Reference-dependent Choice Model for Recommendation (ArcRec) addresses the gap between Prospect Theory and data-driven preference quantification in recommender systems development. The model integrates reference-dependent preferences into a deep learning-based framework, featuring a reference network built from aggregated historical purchase records, decomposed into product attribute-specific sub-networks represented by Graph Neural Networks. ArcRec also introduces novel contributions to quantify consumers’ reference-dependent preferences using a deep neural network-based utility function that captures complex interaction effects between interest-inspired and price-inspired preferences. Empirical evaluations on synthetic and real-world online shopping datasets demonstrate superior performances over state-of-the-art baselines. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary ArcRec is a new model that helps recommend products based on how people make choices. It’s like a brain that understands how we decide what to buy or not. The model uses past purchases to create a reference point for each person, and then breaks it down into smaller pieces related to specific product features. This allows ArcRec to capture how different people value things differently. For example, someone might really want a certain feature in a product, but be less interested if the price is too high. The model also introduces a new way to measure how much someone is willing to pay for something based on their past purchases. Overall, ArcRec does a better job than other models at recommending products that people will like. |
Keywords
» Artificial intelligence » Deep learning » Neural network
