Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns

• URL: http://arxiv.org/abs/2312.13583v1
• Date: Thu, 21 Dec 2023 05:17:10 GMT
• Title: Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns
• Authors: Yifei Sun, Qi Zhu, Yang Yang, Chunping Wang, Tianyu Fan, Jiajun Zhu, Lei Chen
• Abstract summary: We show that the structural divergence between pre-training and downstream graphs significantly limits the transferability when using the vanilla fine-tuning strategy. We propose G-Tuning to preserve the generative patterns of downstream graphs. G-Tuning demonstrates an average improvement of 0.5% and 2.6% on in-domain and out-of-domain transfer learning experiments.
• Score: 13.378277755978258
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, the paradigm of pre-training and fine-tuning graph neural networks has been intensively studied and applied in a wide range of graph mining tasks. Its success is generally attributed to the structural consistency between pre-training and downstream datasets, which, however, does not hold in many real-world scenarios. Existing works have shown that the structural divergence between pre-training and downstream graphs significantly limits the transferability when using the vanilla fine-tuning strategy. This divergence leads to model overfitting on pre-training graphs and causes difficulties in capturing the structural properties of the downstream graphs. In this paper, we identify the fundamental cause of structural divergence as the discrepancy of generative patterns between the pre-training and downstream graphs. Furthermore, we propose G-Tuning to preserve the generative patterns of downstream graphs. Given a downstream graph G, the core idea is to tune the pre-trained GNN so that it can reconstruct the generative patterns of G, the graphon W. However, the exact reconstruction of a graphon is known to be computationally expensive. To overcome this challenge, we provide a theoretical analysis that establishes the existence of a set of alternative graphons called graphon bases for any given graphon. By utilizing a linear combination of these graphon bases, we can efficiently approximate W. This theoretical finding forms the basis of our proposed model, as it enables effective learning of the graphon bases and their associated coefficients. Compared with existing algorithms, G-Tuning demonstrates an average improvement of 0.5% and 2.6% on in-domain and out-of-domain transfer learning experiments, respectively.

Related papers

• Scalable Implicit Graphon Learning [25.015678499211404]
  We propose a scalable method that combines implicit neural representations (INRs) and graph neural networks (GNNs) to estimate a graphon from observed graphs. We evaluate SIGL in synthetic and real-world graphs, showing that it outperforms existing methods and scales effectively to larger graphs.
  arXiv  Detail & Related papers  (2024-10-22T22:44:24Z)
• Does Graph Prompt Work? A Data Operation Perspective with Theoretical Analysis [7.309233340654514]
  This paper introduces a theoretical framework that rigorously analyzes graph prompting from a data operation perspective. We provide a formal guarantee theorem, demonstrating graph prompts capacity to approximate graph transformation operators. We derive upper bounds on the error of these data operations by graph prompts for a single graph and extend this discussion to batches of graphs.
  arXiv  Detail & Related papers  (2024-10-02T15:07:13Z)
• Graphon Pooling for Reducing Dimensionality of Signals and Convolutional Operators on Graphs [131.53471236405628]
  We present three methods that exploit the induced graphon representation of graphs and graph signals on partitions of [0, 1]2 in the graphon space. We prove that those low dimensional representations constitute a convergent sequence of graphs and graph signals. We observe that graphon pooling performs significantly better than other approaches proposed in the literature when dimensionality reduction ratios between layers are large.
  arXiv  Detail & Related papers  (2022-12-15T22:11:34Z)
• Latent Graph Inference using Product Manifolds [0.0]
  We generalize the discrete Differentiable Graph Module (dDGM) for latent graph learning. Our novel approach is tested on a wide range of datasets, and outperforms the original dDGM model.
  arXiv  Detail & Related papers  (2022-11-26T22:13:06Z)
• Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks [52.566735716983956]
  We propose a graph gradual pruning framework termed CGP to dynamically prune GNNs. Unlike LTH-based methods, the proposed CGP approach requires no re-training, which significantly reduces the computation costs. Our proposed strategy greatly improves both training and inference efficiency while matching or even exceeding the accuracy of existing methods.
  arXiv  Detail & Related papers  (2022-07-18T14:23:31Z)
• Learning Graph Structure from Convolutional Mixtures [119.45320143101381]
  We propose a graph convolutional relationship between the observed and latent graphs, and formulate the graph learning task as a network inverse (deconvolution) problem. In lieu of eigendecomposition-based spectral methods, we unroll and truncate proximal gradient iterations to arrive at a parameterized neural network architecture that we call a Graph Deconvolution Network (GDN) GDNs can learn a distribution of graphs in a supervised fashion, perform link prediction or edge-weight regression tasks by adapting the loss function, and they are inherently inductive.
  arXiv  Detail & Related papers  (2022-05-19T14:08:15Z)
• Towards Unsupervised Deep Graph Structure Learning [67.58720734177325]
  We propose an unsupervised graph structure learning paradigm, where the learned graph topology is optimized by data itself without any external guidance. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph.
  arXiv  Detail & Related papers  (2022-01-17T11:57:29Z)
• Graph and graphon neural network stability [122.06927400759021]
  Graph networks (GNNs) are learning architectures that rely on knowledge of the graph structure to generate meaningful representations of network data. We analyze GNN stability using kernel objects called graphons.
  arXiv  Detail & Related papers  (2020-10-23T16:55:56Z)
• The Power of Graph Convolutional Networks to Distinguish Random Graph Models: Short Version [27.544219236164764]
  Graph convolutional networks (GCNs) are a widely used method for graph representation learning. We investigate the power of GCNs to distinguish between different random graph models on the basis of the embeddings of their sample graphs.
  arXiv  Detail & Related papers  (2020-02-13T17:58:42Z)
• Graph Ordering: Towards the Optimal by Learning [69.72656588714155]
  Graph representation learning has achieved a remarkable success in many graph-based applications, such as node classification, prediction, and community detection. However, for some kind of graph applications, such as graph compression and edge partition, it is very hard to reduce them to some graph representation learning tasks. In this paper, we propose to attack the graph ordering problem behind such applications by a novel learning approach.
  arXiv  Detail & Related papers  (2020-01-18T09:14:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.