Why margin-based ranking loss is reversed in these two papers? Announcing the arrival of Valued Associate #679: Cesar Manara Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern) 2019 Moderator Election Q&A - Questionnaire 2019 Community Moderator Election ResultsWhy is each successive tree in GBM fit on the negative gradient of the loss function?Why does the square loss not decrease in deconvolution network?Why is my loss so high?Recommended papers for deep learning based classification?Why does my loss value start at approximately -10,000 and my accuracy not improve?Why validation loss worsens while precision/recall continue to improve?Why is my loss function for DQN converging too quickly?Why Huber loss has its form?Why do people use CrossEntropyLoss and not just a softmax probability as the loss?Why increasing the number of units or layers does not increase the accuracy and decrease the loss?

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?



Announcing the arrival of Valued Associate #679: Cesar Manara
Planned maintenance scheduled April 17/18, 2019 at 00:00UTC (8:00pm US/Eastern)
2019 Moderator Election Q&A - Questionnaire
2019 Community Moderator Election ResultsWhy is each successive tree in GBM fit on the negative gradient of the loss function?Why does the square loss not decrease in deconvolution network?Why is my loss so high?Recommended papers for deep learning based classification?Why does my loss value start at approximately -10,000 and my accuracy not improve?Why validation loss worsens while precision/recall continue to improve?Why is my loss function for DQN converging too quickly?Why Huber loss has its form?Why do people use CrossEntropyLoss and not just a softmax probability as the loss?Why increasing the number of units or layers does not increase the accuracy and decrease the loss?










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










share|improve this question











$endgroup$
















    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










    share|improve this question











    $endgroup$














      1












      1








      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










      share|improve this question











      $endgroup$




      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















      share|improve this question













      share|improve this question




      share|improve this question








      edited Apr 2 at 8:34









      Esmailian

      3,311420




      3,311420










      asked Apr 1 at 14:34









      jasonjason

      1444




      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









          $endgroup$













            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


















            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















            Required, but never shown

























            1 Answer
            1






            active

            oldest

            votes








            1 Answer
            1






            active

            oldest

            votes









            active

            oldest

            votes






            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









            $endgroup$

















              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









              $endgroup$















                2












                2








                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









                $endgroup$



                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












                share|improve this answer



                share|improve this answer










                answered Apr 1 at 14:47









                EsmailianEsmailian

                3,311420




                3,311420



























                    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%2f48357%2fwhy-margin-based-ranking-loss-is-reversed-in-these-two-papers%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

                    Adding axes to figuresAdding axes labels to LaTeX figuresLaTeX equivalent of ConTeXt buffersRotate a node but not its content: the case of the ellipse decorationHow to define the default vertical distance between nodes?TikZ scaling graphic and adjust node position and keep font sizeNumerical conditional within tikz keys?adding axes to shapesAlign axes across subfiguresAdding figures with a certain orderLine up nested tikz enviroments or how to get rid of themAdding axes labels to LaTeX figures

                    Tähtien Talli Jäsenet | Lähteet | NavigointivalikkoSuomen Hippos – Tähtien Talli

                    Do these cracks on my tires look bad? The Next CEO of Stack OverflowDry rot tire should I replace?Having to replace tiresFishtailed so easily? Bad tires? ABS?Filling the tires with something other than air, to avoid puncture hassles?Used Michelin tires safe to install?Do these tyre cracks necessitate replacement?Rumbling noise: tires or mechanicalIs it possible to fix noisy feathered tires?Are bad winter tires still better than summer tires in winter?Torque converter failure - Related to replacing only 2 tires?Why use snow tires on all 4 wheels on 2-wheel-drive cars?