|
||||||||||||||||||||||||||||||||||||||||||||||
|
||||||||||||||||||||||||||||||||||||||||||||||
ABSTRACT
Many load balancing problems that arise in scientific computing applications ask to partition a graph with weights on the vertices and costs on the edges into a given number of almost equally-weighted parts such that the maximum boundary cost over all parts is small.Here, this partitioning problem is considered for boundeddegree graphs G ≡ (V,E) with edge costs c: E → R+ that have a p-separator theorem for some p > 1, i.e., any (arbitrarily weighted) subgraph of G can be separated into two parts of roughly the same weight by removing separator S⊆V such that the edges incident to S in the subgraph have total cost at most proportional to (Εecp<over>e)1/p, where the sum is over all edges in the subgraph.We show for all positive integers k and weights w that the vertices of G can be partitioned into k parts such that the weight of each part differs from the average weight Εv∈V wv<over>k by less than maxv∈V wv, and the boundary edges of each part have cost at most proportional to (Εe∈ cp<over>e/k)1/p + maxe∈E ce. The partition can be computed in time nearly proportional to the time for computing a separator S of G.Our upper bound on the boundary costs is shown to be tight up to a constant factor for infinitely many instances with a broad range of parameters. Previous results achieved this bound only if one has c ≡ 1, w ≡ 1, and one allows parts with weight exceeding the average by a constant fraction. REFERENCES
Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.
INDEX TERMS
Primary Classification:
Additional Classification:
General Terms:
Keywords:
|
||||||||||||||||||||||||||||||||||||||||||||||