FI-GNNs improve graph neural networks by adding pairwise feature interactions and personalized attention, yielding consistently stronger node representations on sparse-feature graphs.
Polynomial Networks and Factorization Machines: New Insights and Efficient Training Algorithms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Polynomial networks and factorization machines are two recently-proposed models that can efficiently use feature interactions in classification and regression tasks. In this paper, we revisit both models from a unified perspective. Based on this new view, we study the properties of both models and propose new efficient training algorithms. Key to our approach is to cast parameter learning as a low-rank symmetric tensor estimation problem, which we solve by multi-convex optimization. We demonstrate our approach on regression and recommender system tasks.
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Feature Interaction-aware Graph Neural Networks
FI-GNNs improve graph neural networks by adding pairwise feature interactions and personalized attention, yielding consistently stronger node representations on sparse-feature graphs.