Plain Transformers are Surprisingly Powerful Link Predictors

ArXi:2602.01553v2 Announce Type: replace-cross Link prediction is a core challenge in graph machine learning, demanding models that capture rich and complex topological dependencies. While Graph Neural Networks (GNNs) are the standard solution, state-of-the-art pipelines often rely on explicit structural heuristics or memory-intensive node embeddings -- approaches that struggle to generalize or scale to massive graphs.