‒ 現在 助教@東北⼤ (最近)関⼼のある研究分野 • Vision and Language NAS + 画像分類 [GECCOʼ17 (Best paper)] NAS+画像復元 [ICMLʼ18, CVPRʼ19] GT-1: a child is brushing her hair in the mirror GT-2: a little girl is brushing GT-1: an ele to far from a GT-2: an ele GT-2: A cat is sleeping on a skateboard. M2: a kitten laying on the floor next to a skateboard GRIT: a cat laying on a skateboard on the floor GT-2: A small standing next to M2: an elephan two birds in the GRIT: a baby e walking in a fie GT-1: a kitchen with a refrigerator next to a sink. GT-2: a red bucket sits in a sink next to an open refrigerator M2: an open refrigerator with the door open in a kitchen GRIT: a kitchen with a sink and an open refrigerator GT-1: a woman luggage past an GT-2: a woman suitcase past a f M2: a person rid down a street w GRIT: a person suitcase next to GT-1: a small teddy bear is wedged into an opening in a car dashboard GT-1: horses ra track with jocke GT-2: a group o BHSPVQPGKPDLF POB BMJUUMFHJSMCSVTIJOHIFSIBJS XJUIBCSVTI V&L [ECCVʼ20, IJCAIʼ21, ECCVʼ22]
Mutationによって新しい構造を⽣成 • Hidden state mutation:セル内の⼀つの演算を選択し,それの⼊⼒元をランダムに変更 • Op mutation :セル内の⼀つの演算を選択し,その演算をランダムに変更 20 進化計算法+Cellベース a. 𝑆個体をランダムに選択 b. 𝑆個体中最も優れた個体を選択 a〜eの繰返し … × d. 最も古い個体を除外 e. 新しい個体を追加 c. 選択された個体に対して mutationを適⽤
上記の学習を10試⾏し,各試⾏で200アーキテクチャをサンプルし,Kendall Tau metricを 算出( [−1.0, 1.0]の値をとり,1.0に近いほどrankingが近いことを⽰す) • 結果として,Kendall Tau metric=0.195かつ下記表から,WSはモデルサンプリングに悪影響を 与えることがわかる 55 Weight sharingの検証 Test error (Average) Test error (Best) Best ranking NAO 6.92±0.71 5.89 3543 ENAS 6.46±0.45 5.96 4610 Test error rate on NASBench (WSなし) Test error (Average) Test error (Best) Best ranking 7.41±0.59 6.67 19552 8.17±0.42 7.46 96939 WSあり 引⽤:Yu+, Evaluating the search space of neural architecture search, ICLRʻ20 [Yu+, ICLRʼ20]
attackに対する頑健性を調査 Supernet … sampling Finetuning the network with adversarial training and evaluate it on eval samples Subnets … … Finetuning the network with adversarial training and evaluate it on eval samples
探索コストは1145.8 TPUv2 days • 様々な⾔語タスク上で良好な結果(e.g. , Primer improves the original T5 architecture on C4 auto-regressive language modeling, reducing the training cost by 4X) 92 Primer: Searching for Efficient Transformers for Language Modeling [So+, NeurIPSʼ21] 獲得された構造例
Search • Distribution Consistent Neural Architecture Search • ISNAS-DIP: Image-Specific Neural Architecture Search for Deep Image Prior • Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search • BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule • HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet • Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning • Neural Architecture Search with Representation Mutual Information • Training-free Transformer Architecture Search • Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training? • β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search • Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search 103 CVPR2022に採択されているNAS論⽂リスト