Why do we share parameters between two different inputs in the embeddings layer?












0












$begingroup$


I noticed in some deep learning networks that have two inputs to the network, they use one embeddings layer to share the parameters between these two different inputs.



As an example, in Keras:



input_target = Input((1,))
input_context = Input((1,))
embedding = Embedding(vocab_size, embed_size, input_length=1, name='embedding')
target = embedding(input_target)
context = embedding(input_context)


Why do they use this way?



To make everything clear, the other case is: for each input we have different embeddings layer before moving to the RNN or CNN layers.










share|improve this question









$endgroup$












  • $begingroup$
    It depends on the use case. Sometimes you have parameter sharing in order to decrease parameters or because all inputs need to be embedded in the same manner.
    $endgroup$
    – Andreas Look
    2 days ago










  • $begingroup$
    @Andreas Look , could you give an example?
    $endgroup$
    – Ghanem
    2 days ago










  • $begingroup$
    e.g. you embedd two images in a low dimensional space where distance is interpretable and want to calculate their similarity afterwards. like siamese networks
    $endgroup$
    – Andreas Look
    2 days ago
















0












$begingroup$


I noticed in some deep learning networks that have two inputs to the network, they use one embeddings layer to share the parameters between these two different inputs.



As an example, in Keras:



input_target = Input((1,))
input_context = Input((1,))
embedding = Embedding(vocab_size, embed_size, input_length=1, name='embedding')
target = embedding(input_target)
context = embedding(input_context)


Why do they use this way?



To make everything clear, the other case is: for each input we have different embeddings layer before moving to the RNN or CNN layers.










share|improve this question









$endgroup$












  • $begingroup$
    It depends on the use case. Sometimes you have parameter sharing in order to decrease parameters or because all inputs need to be embedded in the same manner.
    $endgroup$
    – Andreas Look
    2 days ago










  • $begingroup$
    @Andreas Look , could you give an example?
    $endgroup$
    – Ghanem
    2 days ago










  • $begingroup$
    e.g. you embedd two images in a low dimensional space where distance is interpretable and want to calculate their similarity afterwards. like siamese networks
    $endgroup$
    – Andreas Look
    2 days ago














0












0








0





$begingroup$


I noticed in some deep learning networks that have two inputs to the network, they use one embeddings layer to share the parameters between these two different inputs.



As an example, in Keras:



input_target = Input((1,))
input_context = Input((1,))
embedding = Embedding(vocab_size, embed_size, input_length=1, name='embedding')
target = embedding(input_target)
context = embedding(input_context)


Why do they use this way?



To make everything clear, the other case is: for each input we have different embeddings layer before moving to the RNN or CNN layers.










share|improve this question









$endgroup$




I noticed in some deep learning networks that have two inputs to the network, they use one embeddings layer to share the parameters between these two different inputs.



As an example, in Keras:



input_target = Input((1,))
input_context = Input((1,))
embedding = Embedding(vocab_size, embed_size, input_length=1, name='embedding')
target = embedding(input_target)
context = embedding(input_context)


Why do they use this way?



To make everything clear, the other case is: for each input we have different embeddings layer before moving to the RNN or CNN layers.







deep-learning keras word-embeddings embeddings






share|improve this question













share|improve this question











share|improve this question




share|improve this question










asked 2 days ago









GhanemGhanem

1186




1186












  • $begingroup$
    It depends on the use case. Sometimes you have parameter sharing in order to decrease parameters or because all inputs need to be embedded in the same manner.
    $endgroup$
    – Andreas Look
    2 days ago










  • $begingroup$
    @Andreas Look , could you give an example?
    $endgroup$
    – Ghanem
    2 days ago










  • $begingroup$
    e.g. you embedd two images in a low dimensional space where distance is interpretable and want to calculate their similarity afterwards. like siamese networks
    $endgroup$
    – Andreas Look
    2 days ago


















  • $begingroup$
    It depends on the use case. Sometimes you have parameter sharing in order to decrease parameters or because all inputs need to be embedded in the same manner.
    $endgroup$
    – Andreas Look
    2 days ago










  • $begingroup$
    @Andreas Look , could you give an example?
    $endgroup$
    – Ghanem
    2 days ago










  • $begingroup$
    e.g. you embedd two images in a low dimensional space where distance is interpretable and want to calculate their similarity afterwards. like siamese networks
    $endgroup$
    – Andreas Look
    2 days ago
















$begingroup$
It depends on the use case. Sometimes you have parameter sharing in order to decrease parameters or because all inputs need to be embedded in the same manner.
$endgroup$
– Andreas Look
2 days ago




$begingroup$
It depends on the use case. Sometimes you have parameter sharing in order to decrease parameters or because all inputs need to be embedded in the same manner.
$endgroup$
– Andreas Look
2 days ago












$begingroup$
@Andreas Look , could you give an example?
$endgroup$
– Ghanem
2 days ago




$begingroup$
@Andreas Look , could you give an example?
$endgroup$
– Ghanem
2 days ago












$begingroup$
e.g. you embedd two images in a low dimensional space where distance is interpretable and want to calculate their similarity afterwards. like siamese networks
$endgroup$
– Andreas Look
2 days ago




$begingroup$
e.g. you embedd two images in a low dimensional space where distance is interpretable and want to calculate their similarity afterwards. like siamese networks
$endgroup$
– Andreas Look
2 days ago










0






active

oldest

votes











Your Answer





StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});


}
});














draft saved

draft discarded


















StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47367%2fwhy-do-we-share-parameters-between-two-different-inputs-in-the-embeddings-layer%23new-answer', 'question_page');
}
);

Post as a guest















Required, but never shown

























0






active

oldest

votes








0






active

oldest

votes









active

oldest

votes






active

oldest

votes
















draft saved

draft discarded




















































Thanks for contributing an answer to Data Science Stack Exchange!


  • Please be sure to answer the question. Provide details and share your research!

But avoid



  • Asking for help, clarification, or responding to other answers.

  • Making statements based on opinion; back them up with references or personal experience.


Use MathJax to format equations. MathJax reference.


To learn more, see our tips on writing great answers.




draft saved


draft discarded














StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47367%2fwhy-do-we-share-parameters-between-two-different-inputs-in-the-embeddings-layer%23new-answer', 'question_page');
}
);

Post as a guest















Required, but never shown





















































Required, but never shown














Required, but never shown












Required, but never shown







Required, but never shown

































Required, but never shown














Required, but never shown












Required, but never shown







Required, but never shown







Popular posts from this blog

How to label and detect the document text images

Vallis Paradisi

Tabula Rosettana