HOPPER learns graph- and hop-adaptive sequence extraction for linearized graph sequence models, recovering fixed LGSM extractors as special cases and achieving the best reported scores on eccentricity and shortest-path prediction in ECHO-SYNTH.
On vanishing gradients, over- smoothing, and over-squashing in gnns: Bridging recurrent and graph learning.Advances in Neural Information Processing Systems, 38:74356–74393, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
HOPPER: Learnable Hop Extraction for Linearized Graph Sequence Models
HOPPER learns graph- and hop-adaptive sequence extraction for linearized graph sequence models, recovering fixed LGSM extractors as special cases and achieving the best reported scores on eccentricity and shortest-path prediction in ECHO-SYNTH.