Network Embedding With Completely-Imbalanced Labels

Wang, Zheng; Yao, Xiaojun; Wang, Chaokun; Cui, Jian; Yu, Philip S.

doi:10.1109/tkde.2020.2971490

Cited by 43 publications

(41 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recommendation and one-click collection functions are also provided in the system. In the future, we will design more applications by incorporating other fields [34][35][36][37] based on the system.…”

Section: Discussionmentioning

confidence: 99%

ColorEmo: Color Hunt with Affective Words

Wang

Song

Chen

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Color is a main channel to express emotions of an image. Selecting a good color scheme with color harmony and proper emotional expression is very important in many fields, such as design. There are many color palette tools to help users search, create, edit, save, and share color themes, but few tools are from the perspective of emotional expression and explicitly address the emotional effects of colors. In this paper, a color hunt system with affective words called ColorEmo is developed. Multiple types of input, including affective words, affective categories in image-scale space, and main colors, are allowed for users with accurate emotional description. Based on the dataset with 428,924 color themes, the system provides rich candidates. The system is designed for user research experiments. The user-friendly interactions are offered for easy color modifications. The affective matching and color harmony are evaluated in real time while changing colors. This system can be used in many scenarios of designs and applications.

show abstract

Section: Discussionmentioning

confidence: 99%

ColorEmo: Color Hunt with Affective Words

Wang

Song

Chen

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…Another well-known work is LINE which preserves both first-order proximity (i.e., the similarity between linked nodes) and second-order proximity (i.e., the similarity between the nodes with shared neighbors) of a network. In addition, researchers have also proposed some deep learning-based embedding models, such as SDNE [12] and [17] and RECT [18] further consider the problem of zeroshot graph embedding, i.e., the completely imbalanced label setting.…”

Section: Related Workmentioning

confidence: 99%

Fusing Node Embeddings and Incomplete Attributes by Complement‐Based Concatenation

Wang

Yang

et al. 2021

Wireless Communications and Mobile Computing

Self Cite

View full text Add to dashboard Cite

Network embedding that learns representations of network nodes plays a critical role in network analysis, since it enables many downstream learning tasks. Although various network embedding methods have been proposed, they are mainly designed for a single network scenario. This paper considers a “multiple network” scenario by studying the problem of fusing the node embeddings and incomplete attributes from two different networks. To address this problem, we propose to complement the incomplete attributes, so as to conduct data fusion via concatenation. Specifically, we first propose a simple inductive method, in which attributes are defined as a parametric function of the given node embedding vectors. We then propose its transductive variant by adaptively learning an adjacency graph to approximate the original network structure. Additionally, we also provide a light version of this transductive variant. Experimental results on four datasets demonstrate the superiority of our methods.

show abstract

“…GG-NN [25] designs a gate mechanism-based aggregation function, which provides a weighted average of the messages from neighbors and the center node. Besides, there are some works [26,27] considering the imbalanced nodes in representation. Although these GNNs can characterize the node structure and learn the representations of nodes, most of them suffer from the over-smoothing problem.…”

Section: Related Workmentioning

confidence: 99%

Graph Dilated Network with Rejection Mechanism

2020

Self Cite

View full text Add to dashboard Cite

Recently, graph neural networks (GNNs) have achieved great success in dealing with graph-based data. The basic idea of GNNs is iteratively aggregating the information from neighbors, which is a special form of Laplacian smoothing. However, most of GNNs fall into the over-smoothing problem, i.e., when the model goes deeper, the learned representations become indistinguishable. This reflects the inability of the current GNNs to explore the global graph structure. In this paper, we propose a novel graph neural network to address this problem. A rejection mechanism is designed to address the over-smoothing problem, and a dilated graph convolution kernel is presented to capture the high-level graph structure. A number of experimental results demonstrate that the proposed model outperforms the state-of-the-art GNNs, and can effectively overcome the over-smoothing problem.

show abstract

Network Embedding With Completely-Imbalanced Labels

Cited by 43 publications

References 53 publications

ColorEmo: Color Hunt with Affective Words

ColorEmo: Color Hunt with Affective Words

Fusing Node Embeddings and Incomplete Attributes by Complement‐Based Concatenation

Graph Dilated Network with Rejection Mechanism

Contact Info

Product

Resources

About