Zero-shot graph embedding is a major challenge for supervised learning. Although recent method RECT has shown promising performance, its working mechanisms are not clear and still needs lots of training data. In this paper, we give deep insights into RECT, address fundamental limits. We show that core part GNN prototypical model in which class prototype described by mean feature vector. As such...

We introduce SketchGNN , a convolutional graph neural network for semantic segmentation and labeling of freehand vector sketches. treat an input stroke-based sketch as with nodes representing the sampled points along strokes edges encoding stroke structure information. To predict per-node labels, our uses convolution static-dynamic branching architecture to extract features at three levels, i.e...

We report a tool called Akshaya, which implements a framework to mine four types of “general knowledge semantics” (analytical semantics) from unstructured text. The semantics being mined are semantic siblings, topical anchors, topic expansion and topical markers. The framework provides options to embed more such general knowledge semantic mining algorithms into it. We use a term co-occurrence g...

Spectral Graph Transducer(SGT) is one of the superior graph-based transductive learning methods for classification. As for the Spectral Graph Transducer algorithm, a good graph representation for data to be processed is very important. In this paper, we try to incorporate Latent Semantic Indexing(LSI) into SGT for text classification. Firstly, we exploit LSI to represent documents as vectors in...