Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Thresholded Local Hyper-Flow Diffusion

About

Local Hyper-Flow Diffusion (HFD) gives an edge-size-independent Cheeger-type guarantee for seeded clustering in general submodular hypergraphs, but existing HFD solvers do not keep intermediate computation local at every iteration. We introduce Thresholded Local HFD (TL-HFD), a first-order method that maintains an active region around the seeds, performs projected subgradient updates on that region and its immediate boundary, and expands via thresholded (top-k) boundary activation. We prove that the local update is exact: the degree-preconditioned projected subgradient step restricted to the active region and its boundary coincides with the unrestricted global update. We establish finite-time dual suboptimality for both exact and thresholded updates, treating the latter as inexact projected subgradient steps with explicit skipped-boundary error. We further derive an additive activated-volume bound controlled by realized local subgradient norms and the minimum boundary-push among newly activated vertices, and translate approximate dual optimality with localized support into a robust sweep-cut guarantee for early-stopped iterates. For general submodular cut-costs, each iteration is local in the scanned region and oracle-sensitive in the hyperedge primitive. Empirically, TL-HFD often matches or improves over HFD while activating less volume, with the largest gains on noisy instances where diffusion tends to absorb non-target vertices.

Meher Chaitanya, Sebastian Dalleiger, Luana Ruiz• 2026

Related benchmarks

TaskDatasetResultRank
Hypergraph ClusteringContact-high-school
Median F1100
36
Local Hypergraph ClusteringTrivago-clicks 10 destination-country clusters
KOR Cluster Score0.86
9
Local ClusteringAmazon-reviews sub-benchmarks by cluster unit costs
Fashion28
5
Hypergraph Local ClusteringFlorida Bay food web Detritus cluster
Median F168
2
Hypergraph Local ClusteringFlorida Bay food web Pelagic cluster
Median F169
2
Hypergraph Local ClusteringFlorida Bay food web Benthic cluster
Median F184
2
Showing 6 of 6 rows

Other info

Follow for update