Networks and Learning

 

Chuanyi Ji

Ph.D Caltech 1992, MS Univ. of Pennsylvania 1986, BS (Honors) Tsinghua University 1983.


Associate Professor at School of Electrical and Computer Engineering
Georgia Institute of Technology


Office: 5165 Centergy Building, Georgia Tech
Atlanta, GA30332-0250
jichuanyi@gatech.edu
Phone: 404-894-2393 (Office)   404-894-7883 (Fax)


Research Interest

Our research lies in both basic and applied areas of networks, machine learning, and large-scale data. We study fundamental issues and derive engineering solutions for modeling and managing heterogeneous large networks; develop algorithmic and analytical approaches for machine learning; seek knowledge from real data.


Selected Publications:

 

(Publication list)

  • Resilience of Large-Scale Power Grid and Communication Network to External Disruptions:

·         Chuanyi Ji, Yun Wei, and H. Vincent Poor, “Resilience of Energy Infrastructure and Services: Modeling, Data Analytics and Metrics.”Accepted with minor revisions, Proceedings of The IEEE. http://arxiv.org/abs/1611.06914

 

·         Chuanyi Ji, Yun Wei, Henry Mei, Jorge Calzada, Matthew Carey, Steve Church, Timothy Hayes, Brian Nugent, Gregory Stella, Matthew Wallace, Joe White, & Robert Wilcox. Large-Scale Data Analysis of Power Grid Resilience across Multiple US Service Regions. Nature Energy, May 2016. DOI: http://dx.doi.org/10.1038/nenergy.2016.52

Simulated data in place of real data http://dx.doi.org/10.6084/m9.figshare.3119893.v1

 

(News and Views by Ian Dobson, Electricity grid: When the lights go out. Nature Energy, May 2016)

 

·         Y. Wei, C. Ji, F. Galvan, S. Couvillon, G. Orellana, J. Momoh, “Learning Geo-Temporal Non-Stationary Failure and Recovery of Power Distribution,” Special issue on Learning in Non-stationary and Evolving Environments, IEEE Trans. on Neural Networks, Vol. 25, No.1, 229-240. Jan., 2014.

 

(An article about this work at IEEE Spectrum by Tekla Perry, 2012)

·         S. Erjongmanee and C. Ji, “Large-Scale Network Service Disruptions: Dependencies and External Factors,” IEEE Trans. on Network and Service Management, Vol. 8, No. 4, Dec. 2011.

  • Networks and Learning: Hierarchical Dependency (Graphical) Models and Scalability

·         S. Jeon and C. Ji, “Randomized and Distributed Self-Configuration of Wireless Networks: Two-Layer Markov Random Fields and Near-Optimality,” IEEE Trans. Sig. Proc. Vol. 58, No.9, pp. 4859-4870, Sept. 2010.

 

·         R. Narasimha, S. Dihidar, C. Ji and S. McLaughlin, “Scalable Diagnosis in IP Networks Using Path-Based Measurement and Inference: A Learning Approach,” Special Issue  on  Network Technologies for Emerging Broadband Multimedia Services, Elsevier Journal of Visual Communication and Image Representation, Vol. 21, No. 2, 175-191, Feb. 2010.

·         G. Liu and C. Ji, “Scalability of Network-Failure Resilience: Analysis Using Multi-Layer Probabilistic Graphical Models,” IEEE/ACM Trans. Networking, Vol. 17, No. 1, pp. 319-331, Feb. 2009.

·         G. Liu and C. Ji, “Resilience of All Optical Networks Under In-Band Cross-Talk Attacks: A Probabilistic Graphical Model Approach,” IEEE Journal of Selected Area of Communications (JSAC), Part Supplement, Vol.25, No. 3,  pp. 2-17, April 2007. (Also US patent US Patent # 7903790, “Optical Network Evaluation Systems and Methods” March. 2011)

·         G. Liu, C. Ji and V. Chan, “On the Scalability of Network Management Information for Inter-Domain Light Path Assessment,” IEEE/ACM Trans. Networking, Vol. 13, No. 1, pp. 160-172, Feb. 2005.

·         C. Ji and A. Elwalid, “Measurement-Based Network Monitoring: Achievable Performance and Scalability,” Special Issue on Recent Advances in Fundamentals of Network Management, IEEE Journal of Selected Areas of Communications (JSAC), Vol. 20, No. 4, pp. 714-725, May 2002

  • Large-Scale Network Disruptions and Attacks: Learning, Information Theory, and Data Sets at Internet Scale

·         C. Ji, S. Li, D. Leytchipayia and P. Barford, “Community Networks for Information Sharing,” in Use of Risk Analysis in Computer Aided Persuasion, NATO Science for Peace and Security Series, edited by E. Duman and A. Atiya, May 2011, Vol. 88, pp. 247-255.

 

·         Z. Chen and C. Ji, “An Information-Theoretical View of Network-Aware Attacks,”  IEEE Trans. Information Forensics and Security, Vol. 4, No. 3, pp. 530-541, Sept. 2009.

·         Z. Chen and C. Ji, “Spatial Temporal Modeling of Malware Propagation in Networks,” Special Issue of Adaptive Learning Systems in Networking,  IEEE Trans Neural Networks, Vol. 16, No.5, pp. 1291-1303, Sept. 2005.

·         Z. Chen, C. Ji, and P. Barford, “Spatial Temporal Characteristics of Internet Malicious Sources,” INFOCOM  Mini-Conference, Phoenix, AZ, April 2008, pp. 2306-2314.

  • Proactive Network Anomaly Detection and Traffic Modeling  

·         M. Thottan and C. Ji, “Anomaly Detection in IP Networks,” Special Issue of Signal Processing in Networking, IEEE Trans. Signal Processing, vol. 51, No. 8, pp. 2191-2204, Aug. 2003

·         M. Thottan and C. Ji, “Proactive Anomaly Detection Using Distributed Intelligent Agents,” IEEE Network, Special Issue on Network Management, Vol. 12, No. 7, pp. 21-27, Sept ./Oct. 1998.

·         C. Hood and C. Ji, “Intelligent Agents for Proactive Network Fault Detection,” IEEE Internet Computing, Vol. 2, No.2, p. 65-72, March/April, 1998.

·         C. Hood and C. Ji, “Proactive Network Fault Detection,” IEEE Trans. Reliability, Vol. 46, No.3, pp. 333-341, Sept. 1997.

·         S. Ma and C. Ji, “Modeling Heterogeneous Network Traffic in Wavelet Domain,” IEEE/ACM Trans. Networking, Vol.9, Issue 5, 634-649, Oct. 2001

  • Learning

·         S. Ma and C. Ji, “Performance and Efficiency: Recent Advances in Supervised Learning,” Proceedings of The IEEE, Vol. 87, No. 9, pp. 1519-1535, Sept/Oct, 1999.

·         S. Ma and C. Ji, “A Unified Approach on Fast Training of Feedforward and Recurrent Networks Using EM Algorithm,” IEEE Trans. Signal Processing, Vol .46, No. 8,  pp. 2270-2274, Aug., 1998.

·         S. Ma and C. Ji, “Fasting Training of Recurrent Networks Based on the EM-Algorithm,” IEEE Trans. Neural Networks, Vol. 9, No.1, pp. 11-26, Jan. 1998.

·         C. Ji and D. Psaltis, The Capacity of Two Layer Feedforward Neural Networks with Binary Weights,” IEEE Trans. Information Theory, Vol. 44, No.1, pp. 256-268, Jan. 1998.

·         C. Ji and D. Psaltis, “Network Synthesis Through Data-Driven Growth and Decay,’’ Neural Networks, Vol. 10, No.6, pp. 1133-1141, Aug. 1997.

·         A. Atiya and C. Ji, “How Initial Conditions Affect Generalization Performance in Large Networks,’’ IEEE Trans. Neural Networks, Vol. 8, No.2, pp. 448-451, Mar. 1997.

·         S. Ma, C. Ji and J. Farmer, “An Efficient EM-based Training Algorithms for Feedforward Neural Networks,” Neural Networks, Vol. 10(2), pp. 243-256, Mar. 1997.

·         C. Ji and S. Ma, “Combinations of Weak Classifiers,” IEEE Trans. Neural Networks, Special Issue on Neural Networks and Pattern Recognition, Vol. 8, No.1, pp. 32-42, Jan. 1997.

·         C. Ji, R. Snapp and D. Psaltis, “Generalizing Smoothness Constraint from Discrete Data,’’ Neural Computation, Vol. 2,  pp. 188-197, 1990

·         C. Ji and S. Ma, ''Combined Weak Classifiers'', Proceedings of Neural Information Processing Systems: Natural and Synthetic (NIPS), 494-500, Denver, Colorado, 1996

·         C. Ji, “Generalization Error and The Expected Network Complexity,” Proceedings of Neural Information Processing Systems: Natural and Synthetic (NIPS), Denver, Colorado, 1993, pp. 367-374.

·         C. Ji and D. Psaltis, “The Information Capacity and the Universal Sample Bound for Generalization,” Proceedings of Neural Information Processing Systems: Natural and Synthetic (NIPS), Denver, Colorado, 1991, 928-935.