Node Embeddings via Neighbor Embeddings
This work addresses the need for simpler and more effective graph representation learning methods for researchers and practitioners in machine learning and data visualization.
The paper tackled the problem of unifying graph layout and node embedding paradigms by introducing a single coherent framework based on neighbor embedding methods, resulting in graph t-SNE and graph CNE that strongly outperform state-of-the-art algorithms in local structure preservation.
Graph layouts and node embeddings are two distinct paradigms for non-parametric graph representation learning. In the former, nodes are embedded into 2D space for visualization purposes. In the latter, nodes are embedded into a high-dimensional vector space for downstream processing. State-of-the-art algorithms for these two paradigms, force-directed layouts and random-walk-based contrastive learning (such as DeepWalk and node2vec), have little in common. In this work, we show that both paradigms can be approached with a single coherent framework based on established neighbor embedding methods. Specifically, we introduce graph t-SNE, a neighbor embedding method for two-dimensional graph layouts, and graph CNE, a contrastive neighbor embedding method that produces high-dimensional node representations by optimizing the InfoNCE objective. We show that both graph t-SNE and graph CNE strongly outperform state-of-the-art algorithms in terms of local structure preservation, while being conceptually simpler.