Graph Foundation Model
PulseAugur coverage of Graph Foundation Model — every cluster mentioning Graph Foundation Model across labs, papers, and developer communities, ranked by signal.
-
New generative model unifies network interpretability and inference
Researchers have developed a new generative model for complex networks that unifies mechanistic interpretability with amortized inference. This model utilizes a multifractal step graphon to compactly parameterize networ…
-
New PromptGFM model integrates LLMs and GNNs for text-attributed graphs
Researchers have introduced PromptGFM, a novel Graph Foundation Model (GFM) designed for Text-Attributed Graphs (TAGs). This model aims to improve the integration of Large Language Models (LLMs) and Graph Neural Network…
-
Graph Foundation Model adapts LLM paradigm for optimization problems
Researchers have introduced the Graph Foundation Model (GFM), a novel framework designed to solve distance-based optimization problems on graph structures. By adapting the self-supervised pre-training paradigm used in l…
-
New method uses learnable graph patches for universal pre-trained models
Researchers have introduced a novel approach to address feature heterogeneity in graph data, a challenge that has limited the transferability of graph models. The proposed method, termed learnable graph patches, breaks …
-
Mochi model aligns pre-training with inference for efficient graph foundation models
Researchers have introduced Mochi, a novel Graph Foundation Model that employs a meta-learning framework to enhance both task unification and training efficiency. Unlike previous methods that rely on separate alignment …