Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · 2022 · 41 citations · 11 references
ComputingComputer ScienceKnowledge RepresentationMachine LearningNatural Language ProcessingAdaptive LearningDeep LearningGraph MiningGraph-based LearningMeta-learningTransfer LearningFew-shot ClassificationFew-shot LearningGraph Neural NetworksMeta-testingMeta-trainingNode ClassificationTask AdaptationTask Variance
Node classification is of great importance among various graph mining tasks. In practice, real-world graphs generally follow the long-tail distribution, where a large number of classes only consist of limited labeled nodes. Although Graph Neural Networks (GNNs) have achieved significant improvements in node classification, their performance decreases substantially in such a few-shot scenario. The main reason can be attributed to the vast generalization gap between meta-training and meta-test due to the task variance caused by different node/class distributions in meta-tasks (i.e., node-level and class-level variance). Therefore, to effectively alleviate the impact of task variance, we propose a task-adaptive node classification framework under the few-shot learning setting. Specifically, we first accumulate meta-knowledge across classes with abundant labeled nodes. Then we transfer such knowledge to the classes with limited labeled nodes via our proposed task-adaptive modules. In particular, to accommodate the different node/class distributions among meta-tasks, we propose three essential modules to perform node-level, class-level, and task-level adaptations in each meta-task, respectively. In this way, our framework can conduct adaptations to different meta-tasks and thus advance the model generalization performance on meta-test tasks. Extensive experiments on four prevalent node classification datasets demonstrate the superiority of our framework over the state-of-the-art baselines. Our code is provided at https://github.com/SongW-SW/TENT https://github.com/SongW-SW/TENT.
11
Jie Tang, Jing Zhang, Limin Yao et al. · 2008 · 2.1K citations
Heterogeneous Network Embedding via Deep Architectures
Shiyu Chang, Wei Han, Jiliang Tang et al. · 2015 · 629 citations · Full text
Microsoft Academic Graph: When experts are not enough
Kuansan Wang, Z. Shen, Chiyuan Huang et al. · Quantitative Science Studies · 2020 · 505 citations · Full text