Trjtdtk

Echoing a tail command produces unexpected output?

What would be the ideal power source for a cybernetic eye?

How do I stop a creek from eroding my steep embankment?

Is there a documented rationale why the House Ways and Means chairman can demand tax info?

Is above average number of years spent on PhD considered a red flag in future academia or industry positions?

Models of set theory where not every set can be linearly ordered

LaTeX gives error undefined control sequence table

Right-skewed distribution with mean equals to mode?

What does the "x" in "x86" represent?

The logistics of corpse disposal

How can I fade player character when he goes inside or outside of the area?

Is the Standard Deduction better than Itemized when both are the same amount?

iPhone Wallpaper?

"Seemed to had" is it correct?

Can inflation occur in a positive-sum game currency system such as the Stack Exchange reputation system?

Super Attribute Position on Product Page Magento 1

Did Xerox really develop the first LAN?

3 doors, three guards, one stone

Is there any avatar supposed to be born between the death of Krishna and the birth of Kalki?

Why don't the Weasley twins use magic outside of school if the Trace can only find the location of spells cast?

Should I call the interviewer directly, if HR aren't responding?

Is a manifold-with-boundary with given interior and non-empty boundary essentially unique?

What's the purpose of writing one's academic bio in 3rd person?

Why was the term "discrete" used in discrete logarithm?

Why margin-based ranking loss is reversed in these two papers?

1

$begingroup$

For knwoledge graph completion, it is very common to use margin-based ranking loss

In the paper:margin-based ranking loss is defined as

$$ min sum_(h,l,t)in S sum_(h',l,t')in S'[gamma + d(h,l,t) - d(h',l,t')]_+$$

Here $d(cdot)$ is the predictive model, $(h,l,t)$ means a positive training instance, and $(h',l,t')$ means a negative training instance corresponding to $(h,l,t)$.

However, in the Andrew's paper, it defines

$$ min sum_(h,l,t)in S sum_(h',l,t')in S'[gamma + d(h',l,t') - d(h,l,t)]_+$$

It seems that they switch the terms $d(h',l,t')$ and $d(h,l,t)$.

My question is that

does it matter to switch $d(h',l,t')$ and $d(h,l,t)$? it's real strange definition. Thanks

deep-learning loss-function hinge-loss

share|improve this question

edited Apr 2 at 8:34

Esmailian

3,311420

asked Apr 1 at 14:34

jasonjason

1444

$endgroup$

add a comment | 

1

$begingroup$

For knwoledge graph completion, it is very common to use margin-based ranking loss

In the paper:margin-based ranking loss is defined as

$$ min sum_(h,l,t)in S sum_(h',l,t')in S'[gamma + d(h,l,t) - d(h',l,t')]_+$$

Here $d(cdot)$ is the predictive model, $(h,l,t)$ means a positive training instance, and $(h',l,t')$ means a negative training instance corresponding to $(h,l,t)$.

However, in the Andrew's paper, it defines

$$ min sum_(h,l,t)in S sum_(h',l,t')in S'[gamma + d(h',l,t') - d(h,l,t)]_+$$

It seems that they switch the terms $d(h',l,t')$ and $d(h,l,t)$.

My question is that

does it matter to switch $d(h',l,t')$ and $d(h,l,t)$? it's real strange definition. Thanks

deep-learning loss-function hinge-loss

share|improve this question

edited Apr 2 at 8:34

Esmailian

3,311420

asked Apr 1 at 14:34

jasonjason

1444

$endgroup$

add a comment | 

$begingroup$

For knwoledge graph completion, it is very common to use margin-based ranking loss

In the paper:margin-based ranking loss is defined as

$$ min sum_(h,l,t)in S sum_(h',l,t')in S'[gamma + d(h,l,t) - d(h',l,t')]_+$$

Here $d(cdot)$ is the predictive model, $(h,l,t)$ means a positive training instance, and $(h',l,t')$ means a negative training instance corresponding to $(h,l,t)$.

However, in the Andrew's paper, it defines

$$ min sum_(h,l,t)in S sum_(h',l,t')in S'[gamma + d(h',l,t') - d(h,l,t)]_+$$

It seems that they switch the terms $d(h',l,t')$ and $d(h,l,t)$.

My question is that

does it matter to switch $d(h',l,t')$ and $d(h,l,t)$? it's real strange definition. Thanks

deep-learning loss-function hinge-loss

share|improve this question

edited Apr 2 at 8:34

Esmailian

3,311420

asked Apr 1 at 14:34

jasonjason

1444

$endgroup$

share|improve this question

edited Apr 2 at 8:34

Esmailian

3,311420

asked Apr 1 at 14:34

jasonjason

1444

share|improve this question

edited Apr 2 at 8:34

Esmailian

3,311420

asked Apr 1 at 14:34

jasonjason

1444

edited Apr 2 at 8:34

Esmailian

3,311420

edited Apr 2 at 8:34

Esmailian

3,311420

asked Apr 1 at 14:34

jasonjason

1444

asked Apr 1 at 14:34

jasonjason

1444

1 Answer
1

active

oldest

votes

2

$begingroup$

In this paper, $d$ denotes "dissimilarity" which should be minimized for positive samples.

In this paper, $d$ ($g$ in the paper) denotes "similarity" which should be maximized for positive samples (or equivalently $-gleft(T^(i)right)$ should be minimized)

share|improve this answer

answered Apr 1 at 14:47

EsmailianEsmailian

3,311420

$endgroup$

add a comment | 

Your Answer

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

Sign up or log in

StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48357%2fwhy-margin-based-ranking-loss-is-reversed-in-these-two-papers%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

2

$begingroup$

In this paper, $d$ denotes "dissimilarity" which should be minimized for positive samples.

In this paper, $d$ ($g$ in the paper) denotes "similarity" which should be maximized for positive samples (or equivalently $-gleft(T^(i)right)$ should be minimized)

share|improve this answer

answered Apr 1 at 14:47

EsmailianEsmailian

3,311420

$endgroup$

add a comment | 

2

$begingroup$

In this paper, $d$ denotes "dissimilarity" which should be minimized for positive samples.

In this paper, $d$ ($g$ in the paper) denotes "similarity" which should be maximized for positive samples (or equivalently $-gleft(T^(i)right)$ should be minimized)

share|improve this answer

answered Apr 1 at 14:47

EsmailianEsmailian

3,311420

$endgroup$

add a comment | 

$begingroup$

In this paper, $d$ denotes "dissimilarity" which should be minimized for positive samples.

In this paper, $d$ ($g$ in the paper) denotes "similarity" which should be maximized for positive samples (or equivalently $-gleft(T^(i)right)$ should be minimized)

share|improve this answer

answered Apr 1 at 14:47

EsmailianEsmailian

3,311420

$endgroup$

share|improve this answer

answered Apr 1 at 14:47

EsmailianEsmailian

3,311420

answered Apr 1 at 14:47

EsmailianEsmailian

3,311420

answered Apr 1 at 14:47

EsmailianEsmailian

3,311420