G-Mixup: Graph Data Augmentation for Graph Classification

Han, Xiaotian; Jiang, Zhimeng; Liu, Ninghao; Hu, Xia

doi:10.48550/arxiv.2202.07179

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graphon has been studied intensively as a mathematical object (Borgs et al 2008(Borgs et al , 2012Lovász and Szegedy 2006;Lovász 2012) and been applied broadly, like graph signal processing Ribeiro 2020b, 2021), game theory (Parise and Ozdaglar 2019), network science (Avella-Medina et al 2018;Vizuete, Garin, and Frasca 2021). Moreover, G-mixup (Han et al 2022) is proposed to conduct data augmentation for graph classification since a graphon can serve as a graph generator. From the another perspective of being the graph limit, (Ruiz, Chamon, and Ribeiro 2020a) leverage graphon to analyse the transferability of GNNs.…”

Section: Related Workmentioning

confidence: 99%

“…(1) where Ber(•) is the Bernoulli distribution. Since there is no available closed-form expression of graphon, existing works mainly employ a two-dimensional step function, which can be seen as a matrix, to represent a graphon (Xu et al 2021;Han et al 2022). In fact, the weak regularity lemma of graphon (Lovász 2012) indicates that an arbitrary graphon can be approximated well by a two-dimensional step function.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fine-Tuning Graph Neural Networks by Preserving Graph Generative Patterns

Sun,

Zhu,

Yang

et al. 2024

AAAI

View full text Add to dashboard Cite

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 model, as it enables effective learning of the graphon bases and their associated coefficients. Compared with existing algorithms, G-Tuning demonstrates consistent performance improvement in 7 in-domain and 7 out-of-domain transfer learning experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fine-Tuning Graph Neural Networks by Preserving Graph Generative Patterns

Sun,

Zhu,

Yang

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Mixup-Graph (Wang et al 2021) leverages a simple way to avoid dealing with the arbitrary structure in the input space for mixing a graph pair, through mixing the graph representation resulting from passing the graph through the GNNs. Similarly, a concurrent work G-Mixup (Han et al 2022) first interpolates represented graph generators (i.e., graphons) of different classes, and then leverages the mixed graphons for sampling to generate synthetic graphs.…”

Section: Related Workmentioning

confidence: 99%

Interpolating Graph Pair to Regularize Graph Classification

Guo

Mao

2023

AAAI

View full text Add to dashboard Cite

We present a simple and yet effective interpolation-based regularization technique, aiming to improve the generalization of Graph Neural Networks (GNNs) on supervised graph classification. We leverage Mixup, an effective regularizer for vision, where random sample pairs and their labels are interpolated to create synthetic images for training. Unlike images with grid-like coordinates, graphs have arbitrary structure and topology, which can be very sensitive to any modification that alters the graph's semantic meanings. This posts two unanswered questions for Mixup-like regularization schemes: Can we directly mix up a pair of graph inputs? If so, how well does such mixing strategy regularize the learning of GNNs? To answer these two questions, we propose ifMixup, which first adds dummy nodes to make two graphs have the same input size and then simultaneously performs linear interpolation between the aligned node feature vectors and the aligned edge representations of the two graphs. We empirically show that such simple mixing schema can effectively regularize the classification learning, resulting in superior predictive accuracy to popular graph augmentation and GNN methods.

show abstract

“…To achieve this manner for graphs, one work [46] modifies graph convolution to mix the graph parts within the receptive field. Another work [12] proposes to learn a graph generator to align the pair of graphs and interpolate the generated counterparts. However, these methods require extra deep modules to learn, making the generated graphs hard to interpret.…”

Section: Mix-up On Graphsmentioning

confidence: 99%

Few-shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning

Wang

Liu

et al. 2021

Proceedings of the 29th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Fine-grained action recognition is attracting increasing attention due to the emerging demand of specific action understanding in real-world applications, whereas the data of rare fine-grained categories is very limited. Therefore, we propose the few-shot finegrained action recognition problem, aiming to recognize novel fine-grained actions with only few samples given for each class. Although progress has been made in coarse-grained actions, existing few-shot recognition methods encounter two issues handling finegrained actions: the inability to capture subtle action details and the inadequacy in learning from data with low inter-class variance. To tackle the first issue, a human vision inspired bidirectional attention module (BAM) is proposed. Combining top-down task-driven signals with bottom-up salient stimuli, BAM captures subtle action details by accurately highlighting informative spatio-temporal regions. To address the second issue, we introduce contrastive metalearning (CML). Compared with the widely adopted ProtoNet-based method, CML generates more discriminative video representations for low inter-class variance data, since it makes full use of potential contrastive pairs in each training episode. Furthermore, to fairly compare different models, we establish specific benchmark protocols on two large-scale fine-grained action recognition datasets. Extensive experiments show that our method consistently achieves state-of-the-art performance across evaluated tasks. CCS CONCEPTS• Computing methodologies → Activity recognition and understanding.

show abstract

G-Mixup: Graph Data Augmentation for Graph Classification

Cited by 4 publications

References 0 publications

Fine-Tuning Graph Neural Networks by Preserving Graph Generative Patterns

Fine-Tuning Graph Neural Networks by Preserving Graph Generative Patterns

Interpolating Graph Pair to Regularize Graph Classification

Few-shot Fine-Grained Action Recognition via Bidirectional Attention and Contrastive Meta-Learning

Contact Info

Product

Resources

About