Home / Research
One arc, three stages — from making overlapping community structure reliable, to making it scale, to making structure inspectable.
Each project below asks one version of the same question: which structure is load-bearing, and how would you know? Triad answered it by optimizing all of the structure at once. Highway answered it by discarding most of it and keeping a backbone. DSEG asks it of a model's internal representation.
Structural reliability
Overlapping community detection lets a node belong to several communities at once. Most existing methods are heuristics that lean on only part of the available structural signal, and two failure modes recur: mass collapse, where communities degenerate into empty or collapsed sets, and uniform fuzziness, where every membership is smeared into the same vague value.
Triad casts the problem as a single quadratic constrained program over continuous memberships — using all three structural dimensions (node, edge, community) and explicitly penalizing degeneracy in each, instead of patching heuristics together.
The limit it hitThe reliability was bought at a price that is intrinsic, not incidental: a quadratic constrained program does not scale to large networks. So the question had to change — not "how do I solve this faster," but "how much of this structure do I actually need?"
Scalability through sparse structure
Highway takes the reframed question seriously. Instead of solving the exact program faster, it asks how much structure overlapping-community inference really requires — and answers with a four-step method built on a deliberately sparse backbone: backbone construction, anchor-based initialization, neighbor-only propagation, and anchor-preserving pattern calibration.
What it opened upThe backbone is not only a speed-up — it is a hypothesis about which structure carries the inference. And once you start claiming that this part of the structure is load-bearing while that part is not, you need to be able to look at the structure and check the claim. That is the question the third stage inherits.
Inspectable structure
DSEG asks the same question one level in — of a model's internal representation rather than of a network. If the internal state were an explicit, nameable structure — a set of interpretable units and the relations between them — rather than one entangled vector, what would that buy you?
I currently locate its value in inspection and editing: being able to read the structure, audit it, and change one part of it locally — rather than probing a black box after the fact. This is early work that I am developing hands-on, and I will link concrete findings here once they are public.
Three stages, one arc: structure made reliable → structure made efficient → structure made readable.
As artificial intelligence advances rapidly, both scalability and interpretability are becoming increasingly important. What I hope to investigate is how a model's decisions can be made easier to analyze, test, and trace — without giving up efficiency or the ability to scale — and how every piece of data can be put to fuller and more efficient use.