NS Seminar

Date and Location

Feb 16, 2018 - 3:00pm to 4:00pm
NS Lab, Bldg 434, room 122

Abstract

Learning Node Embeddings in Interaction Graphs (presented by Roman Aguilera, Computer Science)

Zhang, Y., Xiong, Y., Kong, X., & Zhu, Y. (2017, November). Learning Node Embeddings in Interaction Graphs. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management (pp. 397-406). ACM.

Node embedding techniques have gained prominence since they produce continuous and low-dimensional features, which are effective for various tasks. Most existing approaches learn node embeddings by exploring the structure of networks and are mainly focused on static non-attributed graphs. However, many real-world applications, such as stock markets and public review websites, involve bipartite graphs with dynamic and attributed edges, called attributed interaction graphs. Different from conventional graph data, attributed interaction graphs involve two kinds of entities (e.g. investors/stocks and users/businesses) and edges of temporal interactions with attributes (e.g. transactions and reviews). In this paper, we study the problem of node embedding in attributed interaction graphs. Learning embeddings in interaction graphs is highly challenging due to the dynamics and heterogeneous attributes of edges. Different from conventional static graphs, in attributed interaction graphs, each edge can have totally different meanings when the interaction is at different times or associated with different attributes. We propose a deep node embedding method called IGE (Interaction Graph Embedding). IGE is composed of three neural networks: an encoding network is proposed to transform attributes into a fixed-length vector to deal with the heterogeneity of attributes; then encoded attribute vectors interact with nodes multiplicatively in two coupled prediction networks that investigate the temporal dependency by treating incident edges of a node as the analogy of a sentence in word embedding methods. The encoding network can be specifically designed for different datasets as long as it is differentiable, in which case it can be trained together with prediction networks by back-propagation. We evaluate our proposed method and various comparing methods on four realworld datasets. The experimental results prove the effectiveness of the learned embeddings by IGE on both node clustering and classification tasks.

 

Predicting multicellular function through multi-layer tissue networks (presented by Keenan Berry, EEMB)

Marinka Zitnik, Jure Leskovec; Predicting multicellular function through multi-layer tissue networks, Bioinformatics, Volume 33, Issue 14, 15 July 2017, Pages i190–i198,

Motivation: Understanding functions of proteins in specific human tissues is essential for insights into disease diagnostics and therapeutics, yet prediction of tissue-specific cellular function remains a critical challenge for biomedicine.

Results: Here, we present OhmNet, a hierarchy-aware unsupervised node feature learning approach for multi-layer networks. We build a multi-layer network, where each layer represents molecular interactions in a different human tissue. OhmNet then automatically learns a mapping of proteins, represented as nodes, to a neural embedding-based low-dimensional space of features. OhmNet encourages sharing of similar features among proteins with similar network neighborhoods and among proteins activated in similar tissues. The algorithm generalizes prior work, which generally ignores relationships between tissues, by modeling tissue organization with a rich multiscale tissue hierarchy. We use OhmNet to study multicellular function in a multi-layer protein interaction network of 107 human tissues. In 48 tissues with known tissue-specific cellular functions, OhmNetprovides more accurate predictions of cellular function than alternative approaches, and also generates more accurate hypotheses about tissue-specific protein actions. We show that taking into account the tissue hierarchy leads to improved predictive power. Remarkably, we also demonstrate that it is possible to leverage the tissue hierarchy in order to effectively transfer cellular functions to a functionally uncharacterized tissue. Overall, OhmNet moves from flat networks to multiscale models able to predict a range of phenotypes spanning cellular subsystems.

 

Decoding Time-Varying Functional Connectivity Networks via Linear Graph Embedding Methods (presented by Jacob Fisher, Communication)

Monti, R. P., Lorenz, R., Hellyer, P., Leech, R., Anagnostopoulos, C., & Montana, G. (2017). Decoding time-varying functional connectivity networks via linear graph embedding methods. Frontiers in computational neuroscience, 11, 14.

An exciting avenue of neuroscientific research involves quantifying the time-varying properties of functional connectivity networks. As a result, many methods have been proposed to estimate the dynamic properties of such networks. However, one of the challenges associated with such methods involves the interpretation and visualization of high-dimensional, dynamic networks. In this work, we employ graph embedding algorithms to provide low-dimensional vector representations of networks, thus facilitating traditional objectives such as visualization, interpretation and classification. We focus on linear graph embedding methods based on principal component analysis and regularized linear discriminant analysis. The proposed graph embedding methods are validated through a series of simulations and applied to fMRI data from the Human Connectome Project.