Winter 2018 Seminars

Seminar participants will take turns presenting papers of their choice, with two papers being presented each week. Unless otherwise noted, all seminars are held in the Network Science Lab (Bldg 434, room 122) at 3:00 pm on Fridays.

In Winter 2018, we will read recent literature on embedding of graphs/networks into vector spaces. Most of these methods that extend to attributed and dynamic graphs are based on deep learning. A list of sample papers can be found here: Participants should select a paper and be ready to present the findings, as well as areas where the authors could continue the research. 

Enrollment code (CMPSC 595J): 73502


Paper/Presentation Title


Jan 19

Seminar Overview Prof. Ambuj Singh
Network Representation Learning (NRL), an introduction Furkan Kocayusufoglu
Graph Embedding Techniques, Applications, and Performance: A Survey, by P. Goyal and E. Ferrara David Grimsman

Jan 26

Representation Learning on Graphs: Methods and Applications, by Hamilton, Ying, and Leskovec. Shayan Sadigh 
Attributed Signed Network Embedding, by Wang, et al. Rachel Redberg

Feb 2

Roundtable with Dr. Ananthram Swami  

Feb 9

Deep Neural Networks for Learning Graph Representations, by Cao, Lu, and Xu Ashwini Patil
metapath2vec: Scalable Representation Learning for Heterogeneous Networks, by Dong et al.

Isaac Mackey

Co-domain Embedding using Deep Quadruplet Networks for Unseen Traffic Sign Recognition, by Kim, et al.

James Bird

Feb 16

Learning Node Embeddings in Interaction Graphs, by Zhang, et al. Roman Aguilera
Predicting multicellular function through multi-layer tissue networks, by Zitnik and Lescovek  Keenan Berry
Decoding Time-Varying Functional Connectivity Networks via Linear Graph Embedding Methods, by Monti et al.  Jacob Fisher

Feb 23

Learning Latent Representations of Nodes for Classifying in Heterogeneous Social Networks, by Jacob, Denoyer, and Gallinar Vania Wang
struc2vec: Learning Node Representations from Structural Identity, by Ribeiro, Saverese, and Figueiredo  Su Burtner
Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change, by Hamilton, et al. Devin Cornell

Mar 2

Adversarial Network Embedding, by Quanyu Dai, Qiang Li, Jian Tang, Dan Wang Sai Nikhil Maram
Revisiting Semi-Supervised Learning with Graph Embeddings, by Yang, Cohen, and Salakhutdinov Yuning Shen
Multi-view Clustering with Graph Embedding for Connectome Analysis, by Ma, et al.  Taom Sakal

Mar 9

GraphGAN: Graph Respresentation Learning with Generative Adversarial Nets, by Wang et al.  Kevin Smith
HARP: Hierarchical Representation Learning for Networks, by Chen, et al.  Leonidas Eleftheriou
Bernoulli Embeddings for Graphs, by Misra and Bhatia. Pedro Cisneros

Mar 16

Chiarra Ravazzi invited seminar.   
Social influence estimation in Friedkin and Johnsen’s opinion dynamics over sparse networks