Graph Convolutional Networks (GCNs) and subsequent variants have been proposed to solve tasks on graphs, especially node classification tasks. In the literature, however, most tricks or techniques are either briefly mentioned as implementation details only visible in source code. this paper, we first summarize some existing effective used GCNs mini-batch training. Based this, two novel named GC...

We design and evaluate a novel layout fine-tuning technique for node-link diagrams that facilitates exemplar-based adjustment of group substructures in batching mode. The key idea is to transfer user modifications on local substructure other the entire graph are topologically similar exemplar. first precompute canonical representation each with node embedding techniques then use it on-the-fly r...

Dynamic networks are complex as their structures and node features change over time. However, they can better represent the real world, thus attracting interest of researchers. Although realistic dynamic often exhibit changes in patterns, existing network models tend to classify all snapshots having same pattern learn during embedding. These embedding ignore a large amount information about pat...

Multiscale community detection can be viewed from a dynamical perspective within the Markov Stability framework, which uses the diffusion of a Markov process on the graph to uncover intrinsic network substructures across all scales. Here we reformulate multiscale community detection as a max-sum length vector partitioning problem with respect to the set of time-dependent node vectors expressed ...

Network Virtualization is acclaimed to be a key component for the Future Internet by enabling the coexistence of heterogeneous (virtual) networks on the same physical infrastructure, providing the dynamic creation and support of different networks with different paradigms and mechanisms in the same physical network. A major challenge in the dynamic provision of virtual networks resides on the e...

Due to the flexibility in modelling data heterogeneity, heterogeneous information network (HIN) has been adopted to characterize complex and heterogeneous auxiliary data in recommender systems, called HIN based recommendation. It is challenging to develop effective methods for HIN based recommendation in both extraction and exploitation of the information from HINs. Most of HIN based recommenda...

Embedding social network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification, node clustering, link prediction and network visualization. However, the information contained in these vector embeddings remains abstract and hard to interpret. Methods for inspecting embeddings usually rely on visualization methods, w...

This thesis explores the problems of lossy source coding and information embedding. For lossy source coding, we analyze low density parity check (LDPC) codes and low density generator matrix (LDGM) codes for quantization under a Hamming distortion. We prove that LDPC codes can achieve the rate-distortion function. We also show that the variable node degree of any LDGM code must become unbounded...

We improve hardness results for the problem of embedding one finite metric into another with minimum distortion. This problem is equivalent to optimally embedding one weighted graph into another under the shortest path metric. We show that unless P = NP, the minimum distortion of embedding one such graph into another cannot be efficiently approximated within a factor less than 9/4 even when the...

Recently there has been a surge of interest in designing graph embedding methods. Few, if any, can scale to a large-sized graph with millions of nodes due to both computational complexity and memory requirements. In this paper, we relax this limitation by introducing the MultI-Level Embedding (MILE) framework – a generic methodology allowing contemporary graph embedding methods to scale to larg...