Few-Shot Electronic Health Record Coding through Graph Contrastive LearningComputer Science - Artificial IntelligenceEvangelos KanoulasHuasheng LiangMaarten de RijkePengjie RenQiang YanShanshan WangZhaochun RenZhumin ChenarXiv
In general, few-shot learning aims to leverage existing data to classify new tasks from similar domains. The basic workflow for few-shot learning is to pre-train an embedding network on a large dataset (e.g. ImageNet), then fine-tune the weights of this network, and finally apply it to...
A two-stage training paradigm consisting of sequential pre-training and meta-training stages has been widely used in current few-shot learning (FSL) research. Many of these methods use self-supervised learning and contrastive learning to achieve new stat
In this work, we propose a novel graph contrastive learning framework, named Accurate Difference-based Node-Level Graph Contrastive Learning (DNGCL), which helps the model distinguish similar graphs with slight differences by learning node-level differences between graphs. Specifically, we train the ...
Extensive analyses demonstrate that the performance of our CGDRE is contributed by the capture of the semantic knowledge enhanced graph relation representation. 展开 关键词: Heavily-tailed distribution Semantics Contrastive learning Bioinformatics 会议名称: 2024 IEEE International Conference on Bioinformatics ...
上图展示了Few-shot分类的测试效果,结论和Many-shot类似,也是BYOL、SwAV、DeepCluster-v2效果比较突出,但是大多数Few-shot分类任务,自监督模型效果不及有监督模型。 除了分类任务,它还测试了物体识别与实例分割等其它类型的任务,总体而言,在这些任务中,SimCLR-v2和BYOL模型相对效果比较突出。此处不一一列举,感兴趣同学...
Improved graph contrastive learning for short text classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(17): 18716-18724. GIFT模型的github网址 整体框架图 首先,构建一个由Gw、Ge和Gp三个分量图组成的异构图。 然后对每个分量图进行GCNs,分别得到更新后的节点嵌入Hw、...
【半监督】Adaptive Consistency Regularization for Semi-Supervised Transfer Learning 结发授长生 【ML4CO论文精读】Learning Combinatorial Optimization Algorithms over Graphs(Elias B. Khalil, 2017) stri... · 发表于【ML4CO】机器学习在组合优化中的应用 《Few-shot learning with graph neural networks》论文阅...
Zero-shot learning aims to identify unseen (novel) objects, using only labeled samples from seen (base) classes. Existing methods usually learn visual-sema
Han, S., Yoon, J., Arik, S.O., Pfister, T.: Large language models can automatically engineer features for few-shot tabular learning. In: Forty-first International Conference on Machine Learning (2024). https://openreview.net/forum?id=fRG45xL1WT Borisov, V., Sessler, K., Leemann, T...