👨🏾‍💼 🤽🏾 👨🏿‍🤝‍👨🏻 Menjelajahi fitur-fitur penting dengan menyebarkan perbedaan aktivasi. DeepLIFT 🙅🏼 🍡 👩‍🔬

anotasi

Sifat kotak hitam yang dirasakan dari jaringan saraf merupakan kendala untuk digunakan dalam aplikasi di mana interpretabilitas penting. Di sini kami menyajikan DeepLIFT (Deep Learning Important FeaTures), sebuah metode untuk mendekomposisi prediksi output jaringan saraf pada input tertentu dengan melakukan propagasi balik respons semua neuron (node) jaringan ke setiap fitur sinyal input. DeepLIFT membandingkan aktivasi setiap neuron dengan "aktivasi referensi" dan memberikan perkiraan kontribusi individualnya. Dengan mempertimbangkan kontribusi positif dan negatif secara terpisah, DeepLIFT juga dapat mengidentifikasi ketergantungan yang dilewatkan oleh pendekatan lain. Skor dapat dihitung secara efisien dalam satu kali pengembalian. Kami menerapkan DeepLIFT ke model yang dilatih MNIST dan simulasi data genom,menunjukkan keunggulan yang signifikan dibandingkan metode gradien.

Tutorial video: http://goo.gl/qKb7pL

Slide ICML: bit.ly/deeplifticmlslides

Pembicaraan ICML: https://vimeo.com/238275076

kode: http://goo.gl/RM8jvH

1. Perkenalan

, , « » , . DeepLIFT ( ), . . -, «» , «» . , , DeepLIFT , , , . -, , DeepLIFT , . DeepLIFT , , ,

2.

2.1.

. & ( & , 2013 [12]) . «In-silico mutagenesis» (Zhou & Troyanskaya, 2015 [13]) . Zintgraf . (Zintgraf et al., 2017 [14]) . , . , (. 1).

Angka: 1. Pendekatan perturbasi dan pendekatan gradien tidak mampu mensimulasikan saturasi. — . 1. , , .

, . , i₁ = 1 i₂ = 1, i₁ i₂ 0 . , , i₁ + i₂> 1.

2.2. ,

, , . DeepLIFT.

2.2.1. , (, )

. ( ., 2013 [9]) « » . , () (Zeiler & Fergus, 2013 [12]), (ReLU). , ReLU , , ReLU . , , ReLU , , , ReLU . . (Springenberg et al., 2014 [10]) , ReLU, ReLU , . , , , ReLU. - , , () , . , , . 1, y h ( ), h i₁ i₂ , i₁ + i₂> 1 ( ). (. 2).

2.2.2. ×

. (Bach et al., 2015 [1]) , (LRP). . Kindermans et al. (Shrikumar et al., 2016; Kindermans et al., 2016 [8]) , , , LRP ReLU Simonyan et al. ( , × ). DeepLIFT gradient × input, GPU, LRP GPU, .

× , , , . 1 . 2.

2.2.3.

, , (: ) (Sundararajan et al., 2016). , 1 2, ( , , ) . , (. 3.4.3).

2.3. Grad-CAM CAM

Grad-CAM (Selvaraju et al., 2016 [7]) , , , , . ( ) , , Grad-CAM , , Grad-CAM. , . .

3. DeepLIFT

3.1. DeepLIFT

DeepLIFT «» «». «» - «» , , ( . 3.3). , t , , x₁, x₂, ..., x_n , t. t₀ t. ∆t , ∆t = t − t0. DeepLIFT

$C _ {\ Delta x_i \ Delta t} \; untuk \ Delta xi \; sebagai$

$C _ {∆x_i ∆t} \ text {boleh bukan nol}$ $\ text {even if} \ frac {∂t} {∂x_i} \ text {sama dengan nol. }$

DeepLIFT , , . 1, , . , DeepLIFT, .2, - () . , , , .

Gambar 2. Gradien terputus-putus dapat memberikan perkiraan kepentingan yang salah. — 2. .

-10. , x = 10; x = 10 + e, × 10 + e x -10 ( - ). x < 10, x 0. , ( , ) .

3.2.

3.2.1.

x ∆x t ∆t, , m∆x∆t :

, m∆x∆t - ∆x ∆t, ∆x. : ∂t / ∂x - ∆t, ∆x, ∆x. , .

3.2.2.

, x₁, ..., x_n, y₁, ..., y_n t.

$m_ {∆x_i∆y_j} \; dan \; m_ {∆y_j∆t} \; lanjut \; definisi \; m_ {∆x_i∆t}$

. 1 (. ):

. 3 . , - , .

3.3.

DeepLift, 3.5, , - . : y x₁, x₂, ... , y = f(x₁, x₂,...).

, ... , y0 :

, .

DeepLIFT. , , , DeepLIFT . « ?». MNIST , . ( {A,C,G, T}) , , ACGT (. 5), , ( J).

, × ( × ∆, ∆ ). , ( 2.2.3) , , DeepLIFT. Guided Backprop , , , , , .

3.4.

3.5.3 , - . , y ∆y + ∆y−, ∆y, :

∆y+ ∆y− ∆y , ∆x_i, . RevealCancel ( 3.5.3), t , m∆y + ∆t m∆y − ∆t . ( 3.5.1 3.5.2) : m∆y∆t = m∆y + ∆t = m∆y − ∆t.

3.5.

. ( 3.2) ( ) .

3.5.1.

( ). y - x_i ,

$y = b + \sum_{i=1}^n w_ix_i$

$∆y =\sum_{i}w_ix_i$

∆y :

, 3.2.1.

, ∆x_i = 0? « » « », , ∆x + i ∆x - i ( ), « » . ,

$m_{∆x^+_ i ∆y^+} = m_{∆x^+_i ∆y^−} = 0,5 w_i$

∆x_i 0 ( ∆x-).

. B, , .

3.5.2.

, , ReLU, tanh sigmoid. y - x , y = f(x). y , , ,

$C_{∆∆} = ∆Y, , \; , m_{∆∆} =\frac { ∆y}{∆x }$

: ∆y+ ∆y− ∆+ ∆x− :

, :

$x → x^0, \; \; ∆x → 0 \; \; y → 0.$

, . .

$m_{∆x∆y} → \frac{dy}{dx}, \frac{dy}{dx} \; \; x = x^0.$

, , x , , .

, , , . 1 . 2. . 1,

$i^0_1 = i^0_2 = 0, \; \; \; i_1 + i_2 > 1 \; ∆h= \text{-} 1$ $∆y = 1, \; m_{∆h∆y} = \frac{∆h}{∆y} = \text{-}1, \; \; \frac{d}{dh} = 0$

( , , ). . 2, ₀ = ₀ = 0, x = 10 + , ∆y =

, × 10+e x -10 (DeepLIFT ).

(Lundberg & Lee, 2016 [6]), DeepLIFT Shapely. , Shapely , . «» , DeepLIFT Shapely. Lundberg & Lee DeepLIFT, .

3.5.3. : REVEALCANCEL

, , . min (i₁, i₂), . 3, i₁ = 0 i₂ = 0. , i₁, i₂ ( , ). , min.

, , ,

$i_1 > i_2. \; \; \; \; h_1 = (i_1 - i_2) > 0 \; \; h_2 = max(0, h_1) = h_1.$

$C_{∆i_1∆h_1} = i_1 \;\; C_{∆i_2∆h_1} = \text{-}i2.$

$M_{∆h_1,∆h_2} \; \; \frac{∆h_2 }{∆h_1} = 1,$

, ,

$C_{∆i_1∆h_2} = m_{∆h_1 ∆h_2}C_{∆i_1∆h_1} =i_1 \; \; C_ {∆i_2 ∆h_2} = m_{∆h_1∆ h_2}C_{∆i_2∆h_1} = \text{-}i2.$

i₁

$(i_1 \text{-} C_{∆i_1∆h_2}) = (i_1 \text{-} i_1) = 0,$

$i_2 \; to \; o\; is \; \text{-}∆i_2∆h_2 = i_2.$

, ,

$C_{∆i_2∆h_2} \; \; \; \;0,\; \; \; i_1$

- , , i₁ i₂, - , i₂ i₁ h₂. i₁ < i₂;

$C_{∆i_1∆_o} = i_1 \; \; C_{∆i_2∆o} = 0.$

, , ×, i₁, i₂, i₁ i₂ ( . C).

. y = f (x). , ∆y + ∆y−

$∆^+ ∆^− \; \; m_{∆^+∆y^+} = m_{∆^\text{-}∆y^\text{-}} = m_{∆x∆y}$

( ), :

, ∆y+ ∆x+ , ∆x−, ∆y− ∆x− , ∆x+. Shapely ∆x+ ∆x−, y.

, , - , . . 3 RevealCancel 0,5min(i₁, i₂) ( . C).

RevealCancel , . 1 .2, , . , ReLU, ∆y > 0 iff ∆x ≥ b. ∆x < b , ∆x+, ∆x− ( ), («») . RevealCancel , ∆x+ ∆x- .

$i^0_1 =i^0_2 = 0.\; \; i_1 < i_2 \; \frac {dy}{di_2} = 0, \; \; \; i_2 < i_1 \; \; \frac{do}{di_1}=0$

, , 2.2, i₁ i₂. RevealCancel 0,5min(i₁, i₂) .

3.6.

softmax , , . , , , 3.1. , o = (y), y - .

$, \; y = x_1 + x_2, \; \; x^0_1 = x^0_2 = 0. x1 = 50 \; \; x_2 = 0,$

o 1, x₁ x₂ 0,5 0 . , x₁ = 100 x₂ = 100, o - 1, x₁ x₂ 0,25 . , DeepLIFT. , y, o.

Softmax

, softmax, softmax, , softmax , softmax - . , , . , n - ,

$C_{∆x∆c_i}$

ci ,

$C'_{ ∆x c_i}$

, :

, softmax softmax .

4.

4.1. (MNIST)

MNIST (Le-Cun et al., 1999) Keras (Chollet, 2015) 99,2%. , , softmax (. D ). > 1 , , (Springenberg et al., 2014 [10]). DeepLift ( ).

, , : , co, , , C_o. ,

$S_{x_idiff} = S_{x_ic_o}-S_{x_ic_t} ( S_{x_ic} \text{ - } \; x_i \text{ } \;c)$

157 (20% ),

$S_{x_idiff}, \text{ }S_{x_idiff} > 0.$

C_o C_t .

: , (8) (3 6). 8, 3 6. 8→6 * . : - 1K , . " -n" n .

() TAL1 (. G GATA1). -5 . X: log- TAL1 . Y - : . , TAL1 GATA1; GATA1, TAL1, . “DeepLIFT-fc-RC-conv-RS” RevealCancel ( ) , , -, RevealCancel .

() (log-odds > 7) TAL1 , TAL1 GATA1, <= 0 0; * INP DeepLIFT RevealCancel , 1 ( ()).

4.2. ()

( {A,C,G, T}). ( 200-1000), , (RPs), . RP (, GATA1) (, ) (, GATAA GATTA). , (), . , DeepLIFT , , , .

200 ACGT 0,3, 0,2, 0,2 0,3 . (. F) RPs GATA1 TAL1(. 6) (Kheradpour &Kellis, 2014 [3]), 0-3 . , 3 . 1 « - GATA1 TAL1 ()», 2 «GATA1 ()» 3 «TAL1 ()». 1/4 GATA1, TAL1 ( 111), 1/4 GATA1 ( 010), 1/4 TAL1 ( 001) 1/4 ( 000). , F. , ACGT (. . ACGT 0.3, 0.2, 0.2, 0.3; . J). × × ( "", measured ). , , , × , , ; , .

, , ACGT. , 5 ( ) , , . . 5 ( TAL1) E ( GATA1). , : (1) TAL1 2 (2) TAL1 1, (3) ; GATA1 ( 1, 2); (4) TAL1 GATA1 0, (5) , , , ( ; , . 5).

× (2) TAL1 1 ( . H). (4), 0 ( ). Guided Backprop × input, gradient × input (3), , 7, logodds (, ). , Guided Backprop × input gradient × input (. 6). . 2. ( y) .

DeepLIFT: (DeepLIFT-Rescale), RevealCancel (DeepLIFT-RevealCancel) RevealCancel (DeepLIFT-fc-RC-conv-RS). MNIST, , DeepLIFT-fc-RC-convRS RevealCancel. , - , 3.5.3; , , , , (. 6 ).

Gradient × inp, DeepLIFT-Rescale TAL1 0 (. 5b), RevealCancel (. . 6). , RevealCancel . I, (: TAL1, , TAL1, ).

Angka: 6. RevealCancel mengalokasikan motif TAL1 dan GATA1 untuk tugas 0. — . 6. RevealCancel TAL1 GATA1 0.

(a) PWM- GATA1 TAL1, . (b) , , , TAL1, GATA1. . - GATA1, - TAL1. - TAL1 (CAGTTG CAGATG). TAL1 GATA1 0. RevealCancel RevealCancel .

5.

DeepLIFT, , «» «» . (. 1), , , tanh. DeepLIFT ( * - . . 2). , DeepLIFT-RevealCancel , (. 3). : () DeepLIFT RNN,(b) (c) «» ( Maxout Maxpooling ) .

[1] Bach, Sebastian, Binder, Alexander, Montavon, Gregoire, Klauschen, Frederick, Muller, Klaus-Robert, and Samek, Wojciech. On Pixel-Wise explanations for Non-Linear classifier decisions by Layer-Wise relevance propagation. PLoS One, 10(7):e0130140, 10 July 2015.

[2] Chollet, Franois. keras. https://github.com/fchollet/keras, 2015.

[3] Kheradpour, Pouya and Kellis, Manolis. Systematic discovery and characterization of regulatory motifs in encode tf binding experiments. Nucleic acids research, 42 (5):2976–2987, 2014.

[4] Kindermans, Pieter-Jan, Schtt, Kristof, Mller, KlausRobert, and Dhne, Sven. Investigating the influence of noise and distractors on the interpretation of neural networks. CoRR, abs/1611.07270, 2016. URL https://arxiv.org/abs/1611.07270.

[5] LeCun, Yann, Cortes, Corinna, and Burges, Christopher J.C. The mnist database of handwritten digits. http://yann.lecun.com/exdb/mnist/,1999.

[6] Lundberg, Scott and Lee, Su-In. An unexpected unity among methods for interpreting model predictions. CoRR, abs/1611.07478, 2016. URL http://arxiv.org/abs/1611.07478.

[7] Selvaraju, Ramprasaath R., Das, Abhishek, Vedantam, Ramakrishna, Cogswell, Michael, Parikh, Devi, and Batra, Dhruv. Grad-cam: Why did you say that? visual explanations from deep networks via gradient-based localization. CoRR, abs/1610.02391, 2016. URL http://arxiv.org/abs/1610.02391.

[8] Shrikumar, Avanti, Greenside, Peyton, Shcherbina, Anna,and Kundaje, Anshul. Not just a black box: Learning important features through propagating activation differences. arXiv preprint arXiv:1605.01713, 2016.

[9] Simonyan, Karen, Vedaldi, Andrea, and Zisserman, Andrew. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034, 2013.

[10] Springenberg, Jost Tobias, Dosovitskiy, Alexey, Brox, Thomas, and Riedmiller, Martin A. Striving for simplicity: The all convolutional net. CoRR, abs/1412.6806, 2014. URL http://arxiv.org/abs/1412.6806.

[11] Sundararajan, Mukund, Taly, Ankur, and Yan, Qiqi. Gradients of counterfactuals. CoRR, abs/1611.02639, 2016. URL http://arxiv.org/abs/1611.02639.

[12] Zeiler, Matthew D. dan Fergus, Rob. Memvisualisasikan dan memahami jaringan konvolusional. CoRR, abs / 1311.2901, 2013. URL http://arxiv.org/abs/1311.2901 .

[13] Zhou, Jian dan Troyanskaya, Olga G. Memprediksi efek varian noncoding dengan model urutan berbasis pembelajaran yang mendalam. Nat Methods, 12: 931-4, 2015 Oktober 2015. ISSN 1548-7105. doi: 10.1038 / nmeth.3547.

[14] Zintgraf, Luisa M, Cohen, Taco S, Adel, Tameem, dan Welling, Max. Memvisualisasikan keputusan jaringan saraf dalam: Analisis perbedaan prediksi. ICLR, 2017. URL https://openreview.net/pdf?id=BJ5UeU9xx

Menjelajahi fitur-fitur penting dengan menyebarkan perbedaan aktivasi. DeepLIFT

anotasi

1. Perkenalan

2.

3. DeepLIFT

4.

5.

More articles: