Caleb Belth

Hello! I'm Caleb, a PhD student at the University of Michigan, where I work with Danai Koutra. Some of my interests are streaming algorithms, graph summarization, information theory, and philosophy.

My current projects are on identifying inductive patterns—those which generalize beyond the data they were identified in. These may be patterns which extend beyond the boundaries of an incomplete knowledge graph, or patterns which reoccur in a graph edge stream, even in the presence of concept drift. The methods I work on draw on ideas from information theory and cognitive science.

Pervious projects I have worked on involved representation learning to capture high-order (non-Markovian) dependencies in network trajectories, identifying categories of influencers in social movements, and predicting protein binding sites.

Underlying all my work, I try my best to think critically about its implications. Right now, there are at least a couple fundamental questions that I especially wrestle with:
1) What might be the implications of methods I work on? Will they be constructive or destructive to society?
2) What is the motive of my research?
3) Does my research methodology match my motive?

A current musing: are flocks of birds Turing Complete?

Prior to Michigan, I received a B.Sc. in Computer Science from Purdue University, where I was fortunate to work with Jennifer Neville, Dan Goldwasser, and Daisuke Kihara.

Feel free to contact me at cbelth@umich.edu.
In case you are wondering, the name of this website ("quickshift") is a nod to my life-long love of road trips, driving, and cars in general.

Publications

• Personalized Knowledge Graph Summarization: From the Cloud to Your Pocket
  Tara Safavi, Caleb Belth, Lukas Faber, Davide Mottin, Emmanuel Muller, Danai Koutra
  IEEE International Conference on Data Mining (ICDM), 2019
• When to Remember Where You Came from: Node Representation Learning in Higher-order Networks
  Caleb Belth, Fahad Kamran, Donna Tjandra, Danai Koutra
  IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2019 (acceptance rate: 15%) [pdf] [slides]
  Also accepted for presentation at the 15th SIGKDD International Workshop on Mining and Learning with Graphs.

Essays

Minds, Brains, and Maybe Programs. And also elephants. [pdf]

×