An End-to-End Multiplex Graph Neural Network for Graph Representation Learning
نویسندگان
چکیده
منابع مشابه
Learning Graph While Training: An Evolving Graph Convolutional Neural Network
Convolution Neural Networks on Graphs are important generalization and extension of classical CNNs. While previous works generally assumed that the graph structures of samples are regular with unified dimensions, in many applications, they are highly diverse or even not well defined. Under some circumstances, e.g. chemical molecular data, clustering or coarsening for simplifying the graphs is h...
متن کاملEnd-to-end learning of latent edge weights for Graph Convolutional Networks
We present Latent-Graph Convolutional Networks (L-GCN), an approach for machine learning on any kind of graph structure, including directed graphs, multi-graphs and knowledge graphs. Our approach extends Graph Convolutional Networks (Kipf and Welling, 2016) by allowing for end-to-end training and by supporting any kind of data available on the edges in the network, such as numerous transactions...
متن کاملAn End-to-end Approach to Learning Semantic Frames with Feedforward Neural Network
We present an end-to-end method for learning verb-specific semantic frames with feedforward neural network (FNN). Previous works in this area mainly adopt a multi-step procedure including part-of-speech tagging, dependency parsing and so on. On the contrary, our method uses a FNNmodel that maps verbspecific sentences directly to semantic frames. The simple model gets good results on annotated d...
متن کاملRevisiting End-to-End Trace Comparison with Graph Kernels
End-to-end tracing has emerged recently as a valuable tool to improve the dependability of distributed systems by performing dynamic verification and diagnosing correctness and performance problems. End-to-end traces are commonly represented as richly annotated directed acyclic graphs, with events as nodes and their causal dependencies as edges. Being able to automatically compare these graphs ...
متن کاملEnd-to-end Video-level Representation Learning for Action Recognition
From the frame/clip-level feature learning to the videolevel representation building, deep learning methods in action recognition have developed rapidly in recent years. However, current methods suffer from the confusion caused by partial observation training, or without end-to-end learning, or restricted to single temporal scale modeling and so on. In this paper, we build upon two-stream ConvN...
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 Access
سال: 2021
ISSN: 2169-3536
DOI: 10.1109/access.2021.3070690