Interplay Between Topology and Social Learning Over Weak Graphs

You are here

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

Interplay Between Topology and Social Learning Over Weak Graphs

Vincenzo Matta; Virginia Bordignon; Augusto Santos; Ali H. Sayed

This work examines a distributed learning problem where the agents of a network form their beliefs about certain hypotheses of interest. Each agent collects streaming (private) data and updates continually its belief by means of a diffusion strategy, which blends the agent’s data with the beliefs of its neighbors. We focus on weakly-connected graphs, where the network is partitioned into sending and receiving sub-networks, and we allow for heterogeneous models across the agents. First, we examine what agents learn (social learning) and provide an analytical characterization for the long-term beliefs at the agents. Among other effects, the analysis predicts when a leader-follower behavior is possible, where some sending agents control the beliefs of the receiving agents by forcing them to choose a particular and possibly fake hypothesis. Second, we consider the dual or reverse learning problem that reveals how agents learn: given the beliefs collected at a receiving agent, we would like to discover the influence that any sending sub-network might have exerted on this receiving agent (topology learning). An unexpected interplay between social and topology learning emerges: given H hypotheses and S sending sub-networks, topology learning can be feasible when H ≥ S. The latter being only a necessary condition, we then examine the feasibility of topology learning for two useful classes of problems. The analysis reveals that a critical element to enable topology learning is a sufficient degree of diversity in the statistical models of the sending sub-networks. 

SPS on Twitter

  • SPS WEBINAR: Join us on Tuesday, 2 August for a new SPS Webinar, when Dr. Yue Li presents "Learning a Convolutional…
  • Registration for ICIP 2021 is now open! This hybrid event will take place 19-22 September, with the in-person compo…
  • The Brain Space Initiative Talk Series continues on Friday, 30 July when Dr. Ioulia Kovelman presents "The Bilingua…
  • There’s still time to register your team to win the US$5,000 grand prize in the 5-Minute Video Clip Contest, “Autom…
  • Join the SPS Vizag Bay, Long Island, and Finland Chapters for the Seasonal School on Signal Processing and Communic…

SPS Videos

Signal Processing in Home Assistants


Multimedia Forensics

Careers in Signal Processing             


Under the Radar