Search

We introduce a new benchmark dataset, Placenta, for node classification in an underexplored domain: predicting microanatomical tissue structures from cell graphs in placenta histology whole slide images. This problem is uniquely challenging for graph learning for a few reasons. Cell graphs are large (>1 million nodes per image), node features are varied (64-dimensions of 11 types of cells), class labels are imbalanced (9 classes ranging from 0.21% of the data to 40.0%), and cellular communities cluster into heterogeneously distributed tissues of widely varying sizes (from 11 nodes to 44,671 nodes for a single structure). Here, we release a dataset consisting of two cell graphs from two placenta histology images totalling 2,395,747 nodes, 799,745 of which have ground truth labels. We present inductive benchmark results for 7 scalable models and show how the unique qualities of cell graphs can help drive the development of novel graph neural network architectures., Comment: Last two authors contributed equally. To be published at New Frontiers In Graph Learning, Neurips 2022

In the last few decades, data center architecture evolved from the traditional client-server to access-aggregation-core architectures. Recently there is a new shift in the data center architecture due to the increasing need for low latency and high throughput between server-to-server communications, load balancing and, loop-free environment. This new architecture, known as leaf and spine architecture, provides low latency and minimum packet loss by enabling the addition and deletion of network nodes on demand. Network nodes can be added or deleted from the network based on network statistics like link speed, packet loss, latency, and throughput. With the maturity of Open Virtual Switch (OvS) and OpenFlow based Software Defined Network (SDN) controllers, network automation through programmatic extensions has become possible based on network statistics. The separation of the control plane and data plane has enabled automated management of network and Machine Learning (ML) can be applied to learn and optimize the network. In this publication, we propose the design of an ML-based approach to gather network statistics and build a knowledge plane. We demonstrate that this knowledge plane enables data center optimization using southbound APIs and SDN controllers. We describe the design components of this approach - using a network simulator and show that it can maintain the historical patterns of network statistics to predict future growth or decline. We also provide an open-source software that can be utilized in a leaf and spine data center to provide elastic capacity based on load forecasts., Comment: 3 pages

In 1997, the Indiana Department of Education began implementing the Early Literacy Intervention Grant Program (ELIGP), designed to assist schools in their efforts to raise the reading proficiency of students most at risk for reading failures. This report summarizes a study of the impact of ELIGP on schools in the second year of funding, 1998-99. This impact study replicates the study completed in the first year of ELIGP funding (1997-98) and includes: an analysis of the impact of ELIGP, focusing on changes in early reading and literacy programs that resulted from the ELIGP funding; a select group of case studies that illustrate the role of ELIGP in the school improvement process; an analysis of the impact of funding on the numbers of students completing Reading Recovery, referred to special education, and retained; and a summary of findings (which were consistent with the first year impact study) and recommendations for enhancement of ongoing efforts to improve early reading and literacy in Indiana. The report notes that approximately $3.3 million was allocated in 1998-99 through competitive grants to districts or elementary schools and that funds supported early literacy programs in 289 schools across the state of Indiana. Appendixes list funded projects for 1998-99, present the survey instrument, and describe features of early literacy intervention. (Contains 19 references, 25 tables, and 5 figures.) (NKA)

The early literacy challenge in Indiana is to increase the literacy skills of students in Grades K-3 who are at risk for school failure. In 1997 the Indiana Department of Education began implementing the Early Literacy Intervention Grant Program (ELIGP)--close to half the ELIGP funding supported professional development for teachers and teacher trainers involved in Reading Recovery. The remaining schools had projects referred to in this impact study as Other Early Literacy Interventions (OELI). Examples of OELI projects funded included Four Blocks, Literacy Collaborative, Success for All, and other locally developed interventions. This impact study includes: a summary of the implementation study; an analysis of the impact of ELIGP, focusing on changes in early reading and literacy programs that resulted from ELIGP funding; an examination of a select group of case studies that illustrate the role of ELIGP in the school improvement process; an analysis of the impact of funding on the number of students completing Reading Recovery, special education referrals, and retention; and recommendations for enhancement of ongoing efforts to improve early reading and literacy in Indiana. Contains multiple tables of data and figures and 33 references. Appendices contain the survey instrument; outlined features of early literacy programs; lists of funded programs; summaries of early literacy intervention programs; policy news; and notes. (NKA)