NS Seminar

Date and Location

Mar 02, 2018 - 3:00pm to 4:00pm
Bldg 434, room 122

Abstract

Adversarial Network Embedding (presented by Sai Nikhil Maram, Computer Science)

Dai, Q., Li, Q., Tang, J., & Wang, D. (2017). Adversarial Network Embedding. arXiv preprint arXiv:1711.07838.

Learning low-dimensional representations of networks has proved effective in a variety of tasks such as node classification, link prediction and network visualization. Existing methods can effectively encode different structural properties into the representations, such as neighborhood connectivity patterns, global structural role similarities and other high-order proximities. However, except for objectives to capture network structural properties, most of them suffer from lack of additional constraints for enhancing the robustness of representations. In this paper, we aim to exploit the strengths of generative adversarial networks in capturing latent features, and investigate its contribution in learning stable and robust graph representations. Specifically, we propose an Adversarial Network Embedding (ANE) framework, which leverages the adversarial learning principle to regularize the representation learning. It consists of two components, i.e., a structure preserving component and an adversarial learning component. The former component aims to capture network structural properties, while the latter contributes to learning robust representations by matching the posterior distribution of the latent representations to given priors. As shown by the empirical results, our method is competitive with or superior to state-of-the-art approaches on benchmark network embedding tasks.

 

Revisiting Semi-supervised Learning with Graph Embeddings (presented by Yuning Shen, Chemistry)

Yang, Z., Cohen, W. W., & Salakhutdinov, R. (2016). Revisiting semi-supervised learning with graph embeddings. arXiv preprint arXiv:1603.08861.

We present a semi-supervised learning frame-work based on graph embeddings. Given a graph between instances, we train an embedding for each instance to jointly predict the class label and the neighborhood context in the graph. We develop both transductive and inductive variants of our method. In the transductive variant of our method, the class labels are determined by both the learned embeddings and input feature vectors, while in the inductive variant, the embeddings are defined as a parametric function of the feature vectors, so predictions can be made on instances not seen during training. On a large and diverse set of benchmark tasks, including text classification, distantly supervised entity extraction, and entity classification, we show improved performance over many of the existing models.

 

Multi-view Clustering with Graph Embedding for Connectome Analysis (presented by Taom Sakal, EEMB)

Ma, G., He, L., Lu, C. T., Shao, W., Yu, P. S., Leow, A. D., & Ragin, A. B. (2017, November). Multi-view clustering with graph embedding for connectome analysis. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (pp. 127-136). ACM.

Learning low-dimensional representations of networks has proved effective in a variety of tasks such as node classification, link prediction and network visualization. Existing methods can effectively encode different structural properties into the representations, such as neighborhood connectivity patterns, global structural role similarities and other high-order proximities. However, except for objectives to capture network structural properties, most of them suffer from lack of additional constraints for enhancing the robustness of representations. In this paper, we aim to exploit the strengths of generative adversarial networks in capturing latent features, and investigate its contribution in learning stable and robust graph representations. Specifically, we propose an Adversarial Network Embedding (ANE) framework, which leverages the adversarial learning principle to regularize the representation learning. It consists of two components, i.e., a structure preserving component and an adversarial learning component. The former component aims to capture network structural properties, while the latter contributes to learning robust representations by matching the posterior distribution of the latent representations to given priors. As shown by the empirical results, our method is competitive with or superior to state-of-the-art approaches on benchmark network embedding tasks.