CCNI Workshop

The 5th Workshop on Graph Techniques for Adversarial Activity Analytics (GTA³ 2021)

December 15, 2021 | Online Event

For past GTA3 workshops, please visit our archive page.

Theme & Purpose

Graphs are natural analytic tools for modeling adversarial activities across a wide range of domains and applications. Examples include sensing online influence campaigns through social networks, detecting threats and vulnerabilities in cyber-physical networks, preventing disease spreading, and combating covert illicit activities, such as smuggling and arms trafficking, that span across multiple networks (e.g., financial, communication, and transportation networks). The main purpose of this workshop is to provide a forum to discuss research problems and novel approaches on graphs, with emphasis on addressing the three fundamental problems for modeling adversarial activities - “Connecting the dots”, “Finding a needle in a haystack”, and “Defending against attacks”. Besides the traditional activity-centric networks that have been the main focus of this workshop, semantic networks (e.g., knowledge graphs) recently drawn significant attention in our research community. Thus, an important question is to extend existing graph computing capabilities to handle semantically rich networks to support the emerging research direction. The workshop (co-located with the 2021 IEEE Big Data) aims to bring together a community of researchers, from both academia and industry, to share their experiences and exchange perspectives for future research directions. We also hope the workshop will serve as a medium to facilitate future collaborations among interested audiences and researchers.

Topics of Interest

Including but not limited to:

Key Research Topics:

  • Network alignment and data integration from multiple heterogeneous domains
  • Sub-graph detection and matching algorithms for large networks
  • Attack and defense strategies on graph models (e.g., graph neural networks)
  • Deep generative models for synthesizing realistic networks (e.g., static, dynamic, etc.)

Fundamentals:

  • Representation learning on graphs
  • Multilayer and multiplex networks
  • Link prediction and recommendation
  • Limits of detectability and identifiability
  • Information diffusion and influence maximization
  • Clustering and ranking methods for graphs
  • High-performance graph computing
  • New methods and frontiers in spectral graph theory
  • Novel datasets and evaluation metrics for network analytics

Other related topics:

  • Knowledge graph creation, analysis and application
  • GNN and their application towards adversarial activity analytics
  • Complex anomaly (e.g., group anomaly) detection and interpretation
  • Visualization of very large networks
  • Interactive graph search and exploration
  • Topological analysis (e.g., motif analysis) on large graphs
  • Game-theoretic approach for adversarial modeling on graphs
  • Semi-supervised learning, active learning, and transfer learning in the graph context

Submission Instructions

Submissions to the workshop will be subject to a single-blind peer review process, with each submission reviewed by at least two program committee members in addition to an organizer. Accepted papers will be given either an oral or poster presentation slot, and will be published in the IEEE Big Data workshop proceedings.

Papers must be submitted in PDF format according to IEEE Computer Society Proceedings Manuscript Formatting Guidelines (Formatting Instructions) to fit within 10 pages (long papers), or 6 pages (short papers) including any diagrams, references and appendices. Submissions must be self-contained and in English. After uploading your submission, please double check the copy stored on the website.

Submissions should be made using the Online Submission System provided by IEEE BigData.

Important Dates

  • + Due date for full workshop papers submissionOctober 13, 2021 (extended)
  • + Notification of paper acceptance to authorsNovember 5, 2021
  • + Camera-ready of accepted papersNovember 21, 2021
  • + WorkshopsDecember 15, 2021

Keynote Speakers

We plan to invite speakers who are experts in relevant research areas.
Please see our past workshops for more information: https://ccni.hrl.com/workshop/archive


Dr. Sherry Li
Lawrence Berkeley

Accepted Papers

A Graph Embedding Approach to User Behavior Anomaly Detection

Alexander Modell, Jonathan Larson, Melissa Turcotte, and Anna Bertiger

An Analysis of COVID-19 Knowledge Graph Construction and Applications

Dominic Flocoo, Bryce Palmer-Toy, Ruixiao Wang, Hongyu Zhu, Rishi Sonthalia, Junyuan Lin, Andrea Bertozzi, and Jeffrey Brantingham

A Constraint Propagation Approach for Identifying Biological Pathways in COVID-19 Knowledge Graphs

Thomas Tu

Influence in Transient Populations

Dana Warmsley and Samuel Johnson

Active Learning for the Subgraph Matching Problem

Yurun Ge and Andrea Bertozzi

Evaluating the subgraph matching problem in the presence of categorical constraints

MChristopher Ebsch, Joseph Cottam, and George Chin

Characterizing Disease Spreading via Visibility Graph Embedding

Kangyu Ni, Jiejun Xu, Shane Roach, Tsai-Ching Lu, and Alexei Kopylov

Transactional Knowledge Graph Generation To Model Adversarial Activities

Sumit Purohit, Patrick Mackey, William Smith, Madelyn Dunning, Miquette J Orren, Trevor M Langlie-Miletich, Rahul D Deshmukh, Ankur Bohra, Tonya J Martin, Dan Aimone, and George Chin

Higher-order Structure Based Anomaly Detection on Attributed Networks

Xu Yuan, Na Zhou, Shuo Yu, Huafei Huang, Zhikui Chen, and Feng Xia

Semantic Property Graph for Scalable Knowledge Graph Analytics

Sumit Purohit, Nhuy Van, and George Chin

Schedule

All times are US EST (Eastern Standard Time)

01:00pm - 01:05pm | Opening Remarks
01:05pm - 01:50pm | Keynote 1 - Dr. Sherry Li
01:50pm - 02:35pm | Keynote 2 - Prof. Jon Kleinberg
02:35pm - 02:50pm | Transactional Knowledge Graph Generation to Model Adversarial Activities
02:50pm - 03:05pm | Higher-order Structure Based Anomaly Detection on Attributed Networks
03:05pm - 03:15pm | Influence in Transient Populations
03:15pm - 03:25pm | Evaluating the subgraph matching problem in the presence of categorical constraints
03:25pm - 03:45pm | Coffee Break
03:45pm - 04:30pm | Keynote 3 - Prof. Marinka Zitnik
04:30pm - 04:45pm | Active Learning for the Subgraph Matching Problem
04:45pm - 05:00pm | An Analysis of COVID-19 Knowledge Graph Construction and Applications
05:00pm - 05:10pm | A Constraint Propagation Approach for Identifying Biological Pathways in COVID-19 Knowledge Graphs
05:10pm - 05:20pm | Characterizing Disease Spreading via Visibility Graph Embedding
05:20pm - 05:30pm | A Graph Embedding Approach to User Behavior Anomaly Detection
05:30pm - 05:40pm | Semantic Property Graph for Scalable Knowledge Graph Analytics
05:40pm | Closing Remarks

Program Committee

  • Alexei Kopylov (HRL Laboratories, USA)
  • Anil Gaihre (Stevens Institute of Technology, USA)
  • Boxin Du (UIUC, USA)
  • Dana Warmsley (HRL Laboratories, USA)
  • Daniel L. Sussman (Boston University, USA)
  • Dawei Zhou (UIUC, USA)
  • Dominic Yang (UCLA, USA)
  • Jingrui He (UIUC, USA)
  • Joseph Cottam (PNNL, USA)
  • Jun Wu (UIUC, USA)
  • Kang-Yu Ni (HRL Laboratories, USA)
  • Lihui Liu (UIUC, USA)
  • Patrick Mackey (PNNL, USA)
  • Samuel Johnson (HRL Laboratories, USA)
  • Shane Roach (HRL Laboratories, USA)
  • Si Zhang (UIUC, USA)
  • Thomas Tu (UCLA, USA)
  • Tsai-Ching Lu (HRL Laboratories, USA)
  • Tyler Derr (Vanderbilt, USA)
  • Yizhou Sun (UCLA, USA)
  • Yuchen Yan (UIUC, USA)
  • Zhe Xu (UIUC, USA)

Program Chairs (Organizers)