You do not have to train Graph Neural Networks at all on text-attributed graphs
This work addresses the computational inefficiency of gradient descent training for GNNs in semi-supervised node classification tasks, offering a more efficient alternative for researchers and practitioners.
The paper tackles the problem of training Graph Neural Networks (GNNs) for semi-supervised node classification on text-attributed graphs by eliminating iterative optimization processes. It introduces TrainlessGNN, a linear model that matches or surpasses conventionally trained GNNs in performance.
Graph structured data, specifically text-attributed graphs (TAG), effectively represent relationships among varied entities. Such graphs are essential for semi-supervised node classification tasks. Graph Neural Networks (GNNs) have emerged as a powerful tool for handling this graph-structured data. Although gradient descent is commonly utilized for training GNNs for node classification, this study ventures into alternative methods, eliminating the iterative optimization processes. We introduce TrainlessGNN, a linear GNN model capitalizing on the observation that text encodings from the same class often cluster together in a linear subspace. This model constructs a weight matrix to represent each class's node attribute subspace, offering an efficient approach to semi-supervised node classification on TAG. Extensive experiments reveal that our trainless models can either match or even surpass their conventionally trained counterparts, demonstrating the possibility of refraining from gradient descent in certain configurations.