On Greedy Approaches to Hierarchical Aggregation
Alexandra Porter, Mary Wootters

TL;DR
This paper critically analyzes greedy algorithms for the Hierarchical Aggregation problem in GNNs, correcting previous approximation claims, establishing new guarantees, and proposing more efficient heuristics with practical performance benefits.
Contribution
It corrects the approximation factor for a greedy algorithm in HAG, introduces a new connection to hypergraph matchings, and develops faster heuristics for real-world applications.
Findings
Previous greedy approach has at best a 1/2 approximation factor.
New connection established between HAG and maximum hypergraph matching.
Heuristics perform well on real-world graph datasets.
Abstract
We analyze greedy algorithms for the Hierarchical Aggregation (HAG) problem, a strategy introduced in [Jia et al., KDD 2020] for speeding up learning on Graph Neural Networks (GNNs). The idea of HAG is to identify and remove redundancies in computations performed when training GNNs. The associated optimization problem is to identify and remove the most redundancies. Previous work introduced a greedy approach for the HAG problem and claimed a 1-1/e approximation factor. We show by example that this is not correct, and one cannot hope for better than a 1/2 approximation factor. We prove that this greedy algorithm does satisfy some (weaker) approximation guarantee, by showing a new connection between the HAG problem and maximum matching problems in hypergraphs. We also introduce a second greedy algorithm which can out-perform the first one, and we show how to implement it efficiently in…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
