Few-Shot Semantic Relation Prediction Across Heterogeneous Graphs
نویسندگان
چکیده
Semantic relation prediction aims to mine the implicit relationships between objects in heterogeneous graphs, which consist of different types and links. In real-world scenarios, new semantic relations constantly emerge they typically appear with only a few labeled data. Since variety exist multiple transferable knowledge can be mined from some existing help predict This inspires novel problem few-shot across graphs. However, methods cannot solve this because not require large number samples as input, but also focus on single graph fixed heterogeneity. Targeting challenging problem, paper, we propose Meta-learning based Graph neural network for prediction, named MetaGS. Firstly, MetaGS decomposes structure into normalized subgraphs, then adopts two-view capture local information global these subgraphs. Secondly, aggregates subgraphs hyper-prototypical network, learn adapt relations. Thirdly, using well-initialized effectively graphs while overcoming limitation Extensive experiments three datasets have demonstrated superior performance over state-of-the-art methods.
منابع مشابه
Zero-Shot Learning Across Heterogeneous Overlapping Domains
We present a zero-shot learning approach for text classification, predicting which natural language understanding domain can handle a given utterance. Our approach can predict domains at runtime that did not exist at training time. We achieve this extensibility by learning to project utterances and domains into the same embedding space while generating each domain-specific embedding from a set ...
متن کاملLearning to Compare: Relation Network for Few-Shot Learning
We present a conceptually simple, flexible, and general framework for few-shot learning, where a classifier must learn to recognise new classes given only few examples from each. Our method, called the Relation Network (RN), is trained end-to-end from scratch. During meta-learning, it learns to learn a deep distance metric to compare a small number of images within episodes, each of which is de...
متن کاملFew-shot Object Detection
In this paper, we study object detection using a large pool of unlabeled images and only a few labeled images per category, named “few-shot object detection”. The key challenge consists in generating trustworthy training samples as many as possible from the pool. Using few training examples as seeds, our method iterates between model training and high-confidence sample selection. In training, e...
متن کاملFew-shot Learning
Though deep neural networks have shown great success in the large data domain, they generally perform poorly on few-shot learning tasks, where a classifier has to quickly generalize after seeing very few examples from each class. The general belief is that gradient-based optimization in high capacity classifiers requires many iterative steps over many examples to perform well. Here, we propose ...
متن کاملEntity Type Recognition for Heterogeneous Semantic Graphs
We describe an approach to reducing the computational cost of identifying coreferent instances in heterogeneous semantic graphs where the underlying ontologies may not be informative or even known. The problem is similar to coreference resolution in unstructured text, where a variety of linguistic clues and contextual information is used to infer entity types and predict coreference. Semantic g...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Knowledge and Data Engineering
سال: 2023
ISSN: ['1558-2191', '1041-4347', '2326-3865']
DOI: https://doi.org/10.1109/tkde.2023.3251951