PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures

By Jin-Dong Dong, An-Chieh Cheng, Da-Cheng Juan, Wei Wei, Min Sun. 2018

58 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution (2018, methodology): “Multi-objective Neural Architecture Search Very recently, there has also been some work on multi-objective neural architecture search (Kim et al., 2017; Dong et al., 2018; Tan et al., 2018) with the goal of not solely optimizing the accuracy on a given task but also considering resource consumption.”
NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search (2018, methodology): “…et al. (2017); Real et al. (2017; 2018); Xie & Yuille (2017); Kim et al. (2017); Liu et al. (2018); Elsken et al. (2018); Liu et al. (2017); Dong et al. (2018) approaches for NAS focus on the single objective of minimizing an error metric on a task and cannot be easily adapted to handle…”
Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search (2019, methodology): “, 2015), meta-architectures like stacks of blocks (Dong et al., 2018) or predetermined placement of cells (Zoph et al.”
Regularized Evolution for Image Classifier Architecture Search (2018, unknown): “Platform-aware optimization is a viable approach (Dong et al., 2018).”
Searching for Fast Model Families on Datacenter Accelerators (2021, methodology): “When designing fast models for inference with NAS, previous work employed multi-objective search [56, 18, 13, 29, 64, 27, 12, 21, 39, 16] to consider accuracy together with performance/efficiency.”
A Survey on Evolutionary Neural Architecture Search (2020, unknown): “object Computational expense [169]–[171] [30], [61], [69], [89], [101], [105], [106], [119], [127], [135], [172]–[175] [176]”
NSGA-Net: neural architecture search using multi-objective genetic algorithm (2018, unknown): “Dong et al. [7] extended this method to use a multi-objective approach, selected the K networks based on their Pareto-optimality when compared to other networks.”
Progressive Neural Architecture Search (2017, methodology): “reedily picking the top K(see e.g., [39,40]); adaptively varying the number of models Kevaluated at each step (e.g., reducing it over time); the automatic exploration of speed-accuracy tradeos (cf., [41], who compute a Pareto curve using our PNAS algorithm), etc. Acknowledgements We thank Quoc Le fo”