تقرير
Discrete Graph Auto-Encoder
العنوان: | Discrete Graph Auto-Encoder |
---|---|
المؤلفون: | Boget, Yoann, Gregorova, Magda, Kalousis, Alexandros |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning |
الوصف: | Despite advances in generative methods, accurately modeling the distribution of graphs remains a challenging task primarily because of the absence of predefined or inherent unique graph representation. Two main strategies have emerged to tackle this issue: 1) restricting the number of possible representations by sorting the nodes, or 2) using permutation-invariant/equivariant functions, specifically Graph Neural Networks (GNNs). In this paper, we introduce a new framework named Discrete Graph Auto-Encoder (DGAE), which leverages the strengths of both strategies and mitigate their respective limitations. In essence, we propose a strategy in 2 steps. We first use a permutation-equivariant auto-encoder to convert graphs into sets of discrete latent node representations, each node being represented by a sequence of quantized vectors. In the second step, we sort the sets of discrete latent representations and learn their distribution with a specifically designed auto-regressive model based on the Transformer architecture. Through multiple experimental evaluations, we demonstrate the competitive performances of our model in comparison to the existing state-of-the-art across various datasets. Various ablation studies support the interest of our method. Comment: Thoroughly revised the paper originally titled "Vector-Quantized Graph Auto-Encoder. Implemented comprehensive modifications across all sections. Incorporated additional experiments to enhance the study. Maintained the fundamental structure and essence of the original work, ensuring it remains a continuation of the same project |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2306.07735 |
رقم الأكسشن: | edsarx.2306.07735 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |