Topological Transduction for Hybrid Few-shot Learning
Topological Transduction for Hybrid Few-shot Learning
复制标题
DOI：
10.1145/3485447.3512033
复制
发表时间：
2022-04
期刊：
影响因子：
--
通讯作者：
Jiayi Chen;Aidong Zhang
中科院分区：
文献类型：
--
作者：
Jiayi Chen;Aidong Zhang
从互联网上挖掘信息知识和分析内容是一项具有挑战性的任务，因为网络数据可能包含缺乏足够标记数据的新概念，并且可能是多模式的。小样本学习（FSL）因处理几乎没有标记的概念而引起了广泛的研究关注。然而，现有的 FSL 算法假设了统一的任务设置，使得少数样本任务中的所有样本共享一个公共的特征空间。然而在实际的Web应用中，通常会出现这样的情况：由于源数据的异构性，一个任务可能涉及多个输入特征空间，即一个任务中的少数标记样本可能会被进一步划分并属于不同的特征空间，即混合少样本学习（hFSL）。 hFSL 设置会导致每个空间中每个类的混合镜头数量，并且随着每个空间中每个类的训练样本数量的减少而加剧数据稀缺的挑战。为了缓解这些挑战，我们提出了任务自适应拓扑转换网络，即 TopoNet，它训练一种基于异构图的转换元学习器，可以结合来自标记和未标记数据的信息，以丰富有关任务特定数据分布和多空间关系的知识。具体来说，我们在节点异构多关系图中对小样本任务的底层数据关系进行建模，然后元学习器通过边缘增强的异构图神经网络适应每个任务的多空间关系及其类间和类内数据关系。我们的实验与现有方法的比较证明了我们方法的有效性。
Digging informative knowledge and analyzing contents from the internet is a challenging task as web data may contain new concepts that are lack of sufficient labeled data as well as could be multimodal. Few-shot learning (FSL) has attracted significant research attention for dealing with scarcely labeled concepts. However, existing FSL algorithms have assumed a uniform task setting such that all samples in a few-shot task share a common feature space. Yet in the real web applications, it is usually the case that a task may involve multiple input feature spaces due to the heterogeneity of source data, that is, the few labeled samples in a task may be further divided and belong to different feature spaces, namely hybrid few-shot learning (hFSL). The hFSL setting results in a hybrid number of shots per class in each space and aggravates the data scarcity challenge as the number of training samples per class in each space is reduced. To alleviate these challenges, we propose the Task-adaptive Topological Transduction Network, namely TopoNet, which trains a heterogeneous graph-based transductive meta-learner that can combine information from both labeled and unlabeled data to enrich the knowledge about the task-specific data distribution and multi-space relationships. Specifically, we model the underlying data relationships of the few-shot task in a node-heterogeneous multi-relation graph, and then the meta-learner adapts to each task’s multi-space relationships as well as its inter- and intra-class data relationships, through an edge-enhanced heterogeneous graph neural network. Our experiments compared with existing approaches demonstrate the effectiveness of our method.