More Like this

1. Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings

   Wang, D. ; Guo, D. ; Zhao, H. ; Zheng, H. ; Tanwisuth, K. ; Chen, B. ; Zhou, M. ( April 2022 , International Conference on Learning Representations)
2. Embedding all contact 3-manifolds in a fixed contact 5-manifold: EMBEDDING CONTACT 3-MANIFOLDS

   https://doi.org/10.1112/jlms.12164  

   Etnyre, John B. ; Lekili, Yankı ( July 2018 , Journal of the London Mathematical Society)
3. GAGE: Geometry Preserving Attributed Graph Embeddings

   https://doi.org/10.1145/3488560.3498467  

   Kanatsoulis, Charilaos I. ; Sidiropoulos, Nicholas D. ( February 2022 , 15th ACM Conference on Web Search and Data Mining (WSDM))

   Node embedding is the task of extracting concise and informative representations of certain entities that are connected in a network. Various real-world networks include information about both node connectivity and certain node attributes, in the form of features or time-series data. Modern representation learning techniques employ both the connectivity and attribute information of the nodes to produce embeddings in an unsupervised manner. In this context, deriving embeddings that preserve the geometry of the network and the attribute vectors would be highly desirable, as they would reflect both the topological neighborhood structure and proximity in feature space. While this is fairly straightforward to maintain when only observing the connectivity or attribute information of the network, preserving the geometry of both types of information is challenging. A novel tensor factorization approach for node embedding in attributed networks is proposed in this paper, that preserves the distances of both the connections and the attributes. Furthermore, an effective and lightweight algorithm is developed to tackle the learning task and judicious experiments with multiple state-of-the-art baselines suggest that the proposed algorithm offers significant performance improvements in downstream tasks. 

   more » « less
4. Low Treewidth Embeddings of Planar and Minor-Free Metrics

   https://doi.org/10.1109/FOCS54457.2022.00105  

   Filtser, Arnold ; Le, Hung ( October 2022 , The 63rd Annual Symposium on Foundations of Computer Science (FOCS 2022))
5. Analysis of population functional connectivity data via multilayer network embeddings

   https://doi.org/10.1017/nws.2020.39  

   Wilson, James D. ; Baybay, Melanie ; Sankar, Rishi ; Stillman, Paul ; Popa, Abbie M. ( March 2021 , Network Science)

   null (Ed.)

   Abstract Population analyses of functional connectivity have provided a rich understanding of how brain function differs across time, individual, and cognitive task. An important but challenging task in such population analyses is the identification of reliable features that describe the function of the brain, while accounting for individual heterogeneity. Our work is motivated by two particularly important challenges in this area: first, how can one analyze functional connectivity data over populations of individuals, and second, how can one use these analyses to infer group similarities and differences. Motivated by these challenges, we model population connectivity data as a multilayer network and develop the multi-node2vec algorithm, an efficient and scalable embedding method that automatically learns continuous node feature representations from multilayer networks. We use multi-node2vec to analyze resting state fMRI scans over a group of 74 healthy individuals and 60 patients with schizophrenia. We demonstrate how multilayer network embeddings can be used to visualize, cluster, and classify functional regions of the brain for these individuals. We furthermore compare the multilayer network embeddings of the two groups. We identify significant differences between the groups in the default mode network and salience network—findings that are supported by the triple network model theory of cognitive organization. Our findings reveal that multi-node2vec is a powerful and reliable method for analyzing multilayer networks. Data and publicly available code are available at https://github.com/jdwilson4/multi-node2vec . 

   more » « less