FLOWGEN: Fast and slow graph generation
Not on the map. Why?
Abstract (arXiv)
Machine learning systems typically apply the same model to both easy and tough cases. This is in stark contrast with humans, who tend to evoke either fast (instinctive) or slow (analytical) thinking depending on the problem difficulty, a property called the dual-process theory of mind. We present FLOWGEN, a graph-generation model inspired by the dual-process theory of mind that generates large graphs incrementally. Depending on the difficulty of completing the graph at the current step, graph generation is routed to either a fast (weaker) or a slow (stronger) model. These modules have identical architectures, but vary in the number of parameters and consequently differ in generative power. Experiments on real-world graphs show that ours can successfully generate graphs similar to those generated by a single large model, while being up to 2x faster.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 23 of its 59 references that are in the map. First posted on arXiv 15 Jul 2022.
Builds on
23 of 59 references.
References · 23
- 2017Attention Is All You Needcited by 59,932
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2014DeepWalk: Online Learning of Social Representationscited by 1,543
- 2016Variational Graph Auto-Encoderscited by 1,373
- 2020How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answeringcited by 439
- 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
- 2018MolGAN: An implicit generative model for small molecular graphscited by 392
- 2022Confident Adaptive Language Modelingcited by 297
- 2020BERT Loses Patience: Fast and Robust Inference with Early Exitcited by 267
- 2017Thinking Fast and Slow with Deep Learning and Tree Searchcited by 245
- 2020FastBERT: a Self-distilling BERT with Adaptive Inference Timecited by 224
- 2018NetGAN: Generating Graphs via Random Walkscited by 129
11 more
- 2021Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networkscited by 108
- 2021Consistent Accelerated Inference via Confident Adaptive Transformerscited by 73
- 2018NeVAE: A Deep Generative Model for Molecular Graphscited by 66
- 2021ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoningcited by 58
- 2020Grounded Language Learning Fast and Slowcited by 54
- 2021HDMapGen: A Hierarchical Graph Generative Model of High Definition Mapscited by 40
- 2021Think about it! Improving defeasible reasoning by first modeling the question scenariocited by 20
- 2021RomeBERT: Robust Training of Multi-Exit BERTcited by 19
- 2020Neural Language Modeling for Contextualized Temporal Graph Generationcited by 13
- 2017Fast-Slow Recurrent Neural Networkscited by 12
- 2021Datasets for Studying Generalization from Easy to Hard Examplescited by 12
Built on by
Citing papers per year: 2023: 2.
2 papers.