Melhorando a marcação de dados multimodais: menos avaliadores, mais camadas

Olá! Nós - cientistas do laboratório de aprendizado de máquina da ITMO e a equipe principal de ML no VKontakte - estamos fazendo pesquisas conjuntas. Uma das tarefas importantes do VK é a classificação automática das postagens: é necessário não só gerar feeds temáticos, mas também identificar conteúdos indesejados. Os avaliadores estão envolvidos nesse processamento de registros. Ao mesmo tempo, o custo de seu trabalho pode ser reduzido significativamente usando um paradigma de aprendizado de máquina como o aprendizado ativo.

É sobre sua aplicação para a classificação de dados multimodais que será discutida neste artigo. Vamos falar sobre os princípios gerais e métodos de aprendizagem ativa, as peculiaridades de sua aplicação à tarefa, bem como os insights obtidos durante a pesquisa.

Introdução

— machine learning, . , , , .

, (, Amazon Mechanical Turk, .) . — reCAPTCHA, , , , — Google Street View. — .

. , Voyage — , . , , . , .

Amazon DALC (Deep Active Learning from targeted Crowds). , . Monte Carlo Dropout ( ). — noisy annotation. , « , », .

Amazon . : / . , , . , : , . .

— ! , . pool-based sampling.

. 1. pool-based

. , , ( ). : , .

, — . (. — query). , . ( , ) .

, , .

, — . ( ). ≈250 . . () 50 — — :

1. , (. embedding), ;
2. .

, (. . 2).

. 2 —

ML — . , .

. , . , , , . , , early stopping. , .

. residual , highway , (. encoder). , (. fusion): , .

— , . -.

, — , . , .

. , (. 3):

. 3.

. , . , , . , ( + ) — .

, . 3, :

. 4.

, , . , ó , , .

, : ? :

1. ;
2. ;
3. .

. : maximum likelihood , - . :

$$

$$L = \frac{1}{\sigma_1 ^ 2}L_1 + \frac{1}{\sigma_2 ^ 2}L_2 + \frac{1}{\sigma_3 ^ 2}L_3 + \log{\sigma_1} + \log{\sigma_2} + \log{\sigma_3}$$

$$$L_1, L_2, L_3$ — ( -), $$$\sigma_1, \sigma_2, \sigma_3$ — , .

Pool-based sampling

— , . pool-based sampling :

1. - .
2. .
3. , , .
4. .
5. ( ).
6. 3–5 (, ).

, 3–6 — .

, , :

1. , . , : . , , , . . , 2 000.

   
   
   

2. . , . ( ). , , . , . 20 .
   
   . , . — , . 100 200.

   
   
   

, , , .

№1: batch size

baseline , ( ) (. 5).

. 5. baseline- .

random state. .

. «» , , .

, (. batch size). 512 — - (50). , batch size . . :

1. upsample, ;
2. , .

batch size: (1).

$$

$$current\_batch\_size =b + \Big \lfloor\frac{n \mod b}{\lfloor\frac{n}{b}\rfloor}\Big\rfloor [1]$$

$$$b$ — batch size, $$$n$ — .

“” (. 6).

. 6. batch size (passive ) (passive + flexible )

: c . , , batch size . .

.

Uncertainty

— uncertainty sampling. , , .

:

1. (. Least confident sampling)

, :

$$

$$x^{*}_{LC} = \underset{x}{\arg\max} \ 1 - P_{\theta }(\hat{y}|x) [2]$$

$$$\hat{y} = \underset{y}{\arg\max}\ P_{\theta}(y|x)$ — , $$$y$ — , $$$x$ — , $$$x^{*}_{LC}$ — , .

2. (. Margin sampling)

, , , :

$$

$$x^{*}_{M} = \underset{x}{\arg\min} \ P_{\theta }(\hat{y}_{1}|x) - P_{\theta }(\hat{y}_{2}|x)[3]$$

$$$\hat{y}_1$ — $$$x$, $$$\hat{y}_2$ — .

3. (. Entropy sampling)

:

$$

$$x^{*}_{H} = \underset{x}{\arg\max} -\sum \ P_{\theta }(y_{i}|x)\log{P_{\theta }(y_{i}|x)}[4]$$

$$$y_{i}$ — $$$i$- $$$x$ .

, , . , entropy sampling .

(. 7).

. 7. uncertainty sampling ( — , — , — )

, least confident entropy sampling , . margin sampling .

, , : MNIST. , , entropy sampling , . , .

. $$$O(p\log{q})$, $$$p$ — , $$$q$ — . , .

BALD

, , — BALD sampling (Bayesian Active Learning by Disagreement). .

, query-by-committee (QBC). — . uncertainty sampling. , . QBC Monte Carlo Dropout, .

, , — . dropout . dropout , ( ). , dropout- (. 8). Monte Carlo Dropout (MC Dropout) . , . ( dropout) Mutual Information (MI). MI , , — , . .

. 8. MC Dropout BALD

, QBC MC Dropout uncertainty sampling. , (. 9).

. 9. uncertainty sampling ( QBC ) ( — , — , — )

BALD. , Mutual Information :

$$

$$a_{BALD}=\mathbb{H}(y_1,...,y_n)-\mathbb{E}[\mathbb{H}(y_1,...,y_n|\omega)] [5]$$

$$

$$\mathbb{E}[\mathbb{H}(y_1,...,y_n|w)]=\frac{1}{k}\sum_{i=1}^{n}\sum_{j=1}^{k}\mathbb{H}(y_i|w_j) [6]$$

$$$n$ — , $$$k$ — .

(5) , — . , , . BALD . 10.

. 10. BALD



, , .

query-by-committee BALD , . , uncertainty sampling. , — $$$O(kp\log(q))$, $$$p$ — , $$$q$ — , $$$k$ — , .

BALD tf.keras, . PyTorch, dropout , batch normalization , .

№2: batch normalization

batch normalization. batch normalization — , . , , , , batch normalization. , . , . BALD. (. 11).

. 11. batch normalization BALD

, , .

batch normalization, . , .

Learning loss

. , . , .

, . — . , . learning loss, . , (. 12).

. 12. Learning loss



learning loss . .

. , . «» learning loss: , , . ideal learning loss (. 13).

. 13. ideal learning loss



, learning loss.

, . , , - , . :

1. (2000 ), ;
2. 10000 ( );
3. ;
4. ;
5. 100 ;
6. , , 1;
7. .

, , . , ( margin sampling).

1.

, margin sampling — , , , . c .

: ?

, , (. 14).

. 14. ideal learning loss ideal learning loss

, MNIST :

2. MNIST

ideal learning loss , (. 15).

. 15. MNIST ideal learning loss. — ideal learning loss, —



, , , , . .

learning loss , uncertainty sampling: $$$O(p\log{q})$, $$$p$ — , $$$q$ — . , , . , .

, . . , margin sampling — . 16.



. 16. ( ) , margin sampling

: ( — margin sampling), — , , . ≈25 . . 25% — .

, . , , .

, , . , :

• batch size;
• , , — , batch normalization.