版權(quán)說明:本文檔由用戶提供并上傳,收益歸屬內(nèi)容提供方,若內(nèi)容存在侵權(quán),請進行舉報或認領(lǐng)
文檔簡介
UnravelingMeta-Learning:UnderstandingFeature
RepresentationsforFew-ShotTasks
HarichandanaVejendla
(50478049)
1
2
Definitions
?Meta-Learning:Meta-learningdescribesmachinelearningalgorithmsthatacquireknowledgeandunderstandingfromtheoutcomeofothermachinelearningalgorithms.Theylearnhowtobest
combinethepredictionsfromothermachine-learningalgorithms.
?Few-shotLearning:Few-ShotLearningisaMachineLearningframeworkthatenablesapre-trainedmodeltogeneralizeovernewcategoriesofdatausingonlyafewlabeledsamplesperclass.
?FeatureExtraction:Featureextractionisaprocessofdimensionalityreductionthatinvolvestransformingrawdataintonumericalfeaturesthatcanbeprocessed.
?Featureclustering:Featureclusteringaggregatespointfeaturesintogroupswhosemembersaresimilartoeachotherandnotsimilartomembersofothergroups.
?FeatureRepresentation:RepresentationLearningorfeaturelearningisthesubdisciplineofthe
machinelearningspacethatdealswithextractingfeaturesorunderstandingtherepresentationofadataset.
3
Introduction
?TransferLearning:Pre-trainingamodelonlargeauxiliarydatasetsandthenfine-tuningtheresultingmodelsonthetargettask.Thisisusedforfew-shotlearningsinceonlyafewdatasamplesareavailableinthetarget
domain.
?Transferlearningfromclassicallytrainedmodelsyieldspoorperformanceforfew-shotlearning.Recently,few-shotlearninghasbeenrapidlyimprovedusingmeta-learningmethods.
?Thissuggeststhatthefeaturerepresentationslearnedbymeta-learningmustbefundamentallydifferentfromfeaturerepresentationslearnedthroughconventionaltraining.
?Thispaperunderstandsthedifferencesbetweenfeatureslearnedbymeta-learningandclassicaltraining.
?Basedonthis,thepaperproposessimpleregularizersthatboostfew-shotperformanceappreciably.
4
Meta-LearningFramework
?Inthecontextoffew-shotlearning,theobjectiveofmeta-learningalgorithmsistoproduceanetworkthatquicklyadaptstonewclassesusinglittledata.
?Meta-learningalgorithmsfindparametersthatcanbefine-tunedinafewoptimizationstepsandonafewdatapointsinordertoachievegoodgeneralization.
?Thetaskischaracterizedasn-way,k-shotifthemeta-learningalgorithmmustadapttoclassifydatafromTiafterseeingkexamplesfromeachofthenclassesinTi.
Algorithm
5
6
AlgorithmDescription
?Meta-learningschemestypicallyrelyonbi-leveloptimizationproblemswithaninnerloopandanouterloop.
?Aniterationoftheouterloopinvolvesfirstsamplinga“task,”whichcomprisestwosetsoflabeleddata:thesupportdata,Tis,andthequerydata,Tiq.
?Intheinnerloop,themodelbeingtrainedisfine-tunedusingthesupportdata.
?Fine-tuningproducesnewparametersθi,thatareafunctionoftheoriginalparametersandsupportdata.
?Weevaluatethelossonthequerydataandcomputethegradientsw.r.ttheoriginalparametersθ.Weneedtounrollthefine-tuningstepsandbackpropagatethroughthemtocomputethegradients.
?Finally,theroutinemovesbacktotheouterloop,wherethemeta-learningalgorithmminimizeslossonthequerydatawithrespecttothepre-fine-tunedweights.Basemodelparametersareupdatedusingthe
gradients.
7
Meta-LearningAlgorithms
Avarietyofmeta-learningalgorithmsexist,mostlydifferinginhowtheyarefine-tunedusingthesupportdataduringtheinnerloop:
?MAML:Updatesallnetworkparametersusinggradientdescentduringfine-tuning.
?R2-D2andMetaOptNet:Last-layermeta-learningmethods(onlytrainthelastlayer).Theyfreezethefeatureextractionlayers(featureextractor’sparametersarefrozen)duringtheinnerloop.Onlythelinearclassifierlayeristrainedduringfine-tuning.
?ProtoNet:Last-layermeta-learningmethod.Itclassifiesexamplesbytheproximityoftheirfeaturestothoseofclasscentroids.Theextractedfeaturesareusedtocreateclasscentroidswhichthen
determinethenetwork’sclassboundaries.
8
Few-ShotDatasets
?Mini-ImageNet:ItisaprunedanddownsizedversionoftheImageNetclassificationdataset,
consistingof60,000,84×84RGBcolorimagesfrom100.These100classesaresplitinto64,16,and20classesfortraining,validation,andtestingsets,respectively.
?CIFAR-FSdataset:samplesimagesfromCIFAR-100.CIFAR-FSissplitinthesamewayasmini-ImageNetwith60,00032×32RGBcolorimagesfrom100classesdividedinto64,16,and20
classesfortraining,validation,andtestingsets,respectively.
ComparisonbetweenMeta-LearningandClassicalTrainingModels
?DatasetUsed:1-shotmini-ImageNet
?Classicallytrainedmodelsaretrainedusingcross-entropylossandSGD.
?Commonfine-tuningproceduresareusedforbothmeta-learnedandclassically-trainedmodelsforafaircomparison
?Resultsshowthatmeta-learningmodelsperformbetterthanclassicaltrainingmodelsonfew-shotclassification.
?Thisperformanceadvantageacrosstheboardsuggeststhatmeta-learnedfeaturesarequalitativelydifferentfromconventionalfeaturesandfundamentallysuperiorforfew-shotlearning.
9
10
ClassClusteringinFeatureSpace
MeasuringClusteringinFeatureSpace:
Tomeasurefeatureclustering(FC),weconsidertheintra-classtointer-classvarianceratio:
φi,j-featurevectorcorrespondingtodatapointinclassiintrainingdata
μi-meanoffeaturevectorsinclassi
μ-meanacrossallfeaturevectors
C-numberofclasses
N-numberofdatapointsperclass
Where,fθ(xi,j)=φi,jfθ-featureextractor
xi,j-trainingdatainclassi
Lowvaluesofthisfractioncorrespondtocollectionsoffeaturessuchthatclassesarewell-separatedandahyperplaneformedbychoosingapointfromeachoftwoclassesdoesnotvarydramaticallywiththechoiceofsamples.
WhyClusteringisimportant?
?Asfeaturesinaclassbecomespreadoutandtheclassesarebroughtclosertogether,theclassificationboundariesformedbysamplingone-shotdataoftenmisclassifylargeregions.
?Asfeaturesinaclassarecompactedandclassesmovefarapartfromeachother,theintra-classtointer-classvarianceratiodrops,andthedependenceoftheclassboundaryonthechoiceofone-shotsamplesbecomesweaker.
11
ComparingFeatureRepresentationsofMeta-LearningandClassicallyTrainedModels
?Threeclassesarerandomlychosenfromthetestset,and100samplesaretakenfromeachclass.Thesamplesarethenpassedthroughthefeatureextractor,andtheresultingvectorsareplotted.
?Becausefeaturespaceishigh-dimensional,weperformalinearprojectionontothefirsttwocomponentvectorsdeterminedbyLDA.
?Lineardiscriminantanalysis(LDA)projectsdataontodirectionsthatminimizetheintra-classtointer-classvarianceratio.
?Theclassicallytrainedmodelmashesfeaturestogether,whilethemeta-learnedmodelsdrawtheclassesfartherapart.
12
13
HyperplaneInvariance
Thisregularizerwithonethatpenalizesvariationsinthemaximum-marginhyperplaneseparatingfeaturevectorsin
oppositeclasses
HyperplaneVariationRegularizer:
DatpointsinclassA:x1,x2
DatapointsinclassB:y1,y2
fθ-featureextractor
fθ(x1)-fθ(y1):determinesthedirectionofthemaximum
marginhyperplaneseparatingthetwopointsinthefeaturespace
?Thisfunctionmeasuresthedistancebetweendistancevectorsx1?y1andx2?y2relativetotheirsize.
?Inpractice,duringabatchoftraining,wesamplemanypairsofclassesandtwosamplesfromeachclass.Then,wecomputeRHVonallclasspairsandaddthesetermstothecross-entropyloss.
?WefindthatthisregularizerperformsalmostaswellasFeatureClusteringRegularizerandconclusivelyoutperformsnon-regularizedclassicaltraining.
14
Experiments
?FeatureclusteringandHyperplanevariationvaluesarecomputed.
?Thesetwoquantitiesmeasuretheintra-classtointer-classvarianceratioandinvarianceofseparatinghyperplanes.
?Lowervaluesofeachmeasurementcorrespondtobetterclassseparation.
?OnbothCIFAR-FSandmini-ImageNet,themeta-learnedmodelsattainlowervalues,indicatingthatfeaturespaceclusteringplaysaroleintheeffectivenessofmeta-learning.
15
Experiments
?Weincorporatetheseregularizersintoastandardtrainingroutineoftheclassicaltrainingmodel.
?Inallexperiments,featureclusteringimprovestheperformanceoftransferlearningandsometimesevenachieveshigherperformancethanmeta-learning
16
WeightClustering:FindingClustersofLocalMinimaforTaskLossesinParameterSpace
?SinceReptiledoesnotfixthefeatureextractorduringfine-tuning,itmustfindparametersthatadapteasilytonewtasks.
?WehypothesizethatReptilefindsparametersthatlieveryclosetogoodminimaformanytasksandis,therefore,abletoperformwellonthesetasksafterverylittlefine-tuning.
?ThishypothesisisfurthermotivatedbythecloserelationshipbetweenReptileandconsensusoptimization.
?Inaconsensusmethod,anumberofmodelsareindependentlyoptimizedwiththeirowntask-specificparameters,andthetaskscommunicateviaapenaltythatencouragesalltheindividualsolutionsto
convergearoundacommonvalue.
17
ConsensusFormulation:
?Reptilecanbeinterpretedasapproximatelyminimizingtheconsensusformulation
?Reptiledivergesfromatraditionalconsensusoptimizeronlyinthatitdoesnotexplicitlyconsiderthequadraticpenaltytermwhenminimizingfor?θp.
18
ConsensusOptimizationImprovesReptile
?WemodifyReptiletoexplicitlyenforceparameterclusteringaroundaconsensusvalue.
?Wefindthatdirectlyoptimizingtheconsensusformulationleadstoimprovedperformance.
?duringeachinnerloopupdatestepinReptile,wepenalizethesquareddistancefromtheparametersforthecurrenttasktotheaverageoftheparametersacrossalltasksinthecurrentbatch.
?ThisisequivalenttotheoriginalReptilewhenα=0.Wecallthismethod“Weight-Clustering.
ReptilewithWeightClusteringRegularizer
n-numberofmeta-trainingsteps
k-numberofiterationsorstepstoperformwithineachmeta-trainingstep
19
20
Resultsofweightclustering
?WecomparetheperformanceofourregularizedReptilealgorithmtothatoftheoriginalReptilemethodaswellasfirst-orderMAML(FOMAML)andaclassicallytrainedmodelofthesamearchitecture.We
testthesemethodsonasampleof100,0005-way1-shotand5-shotmini-ImageNettasks
?ReptilewithWeight-Clusteringachieveshigherperformance.
21
Resultsofweightclustering
?ParametersofnetworkstrainedusingourregularizedversionofReptiledonottravelasfarduringfine-tuningatinferenceasthosetrainedusingvanillaReptile
?Fromthese,weconcludethatourregularizerdoesindeedmovemo
溫馨提示
- 1. 本站所有資源如無特殊說明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請下載最新的WinRAR軟件解壓。
- 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請聯(lián)系上傳者。文件的所有權(quán)益歸上傳用戶所有。
- 3. 本站RAR壓縮包中若帶圖紙,網(wǎng)頁內(nèi)容里面會有圖紙預(yù)覽,若沒有圖紙預(yù)覽就沒有圖紙。
- 4. 未經(jīng)權(quán)益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
- 5. 人人文庫網(wǎng)僅提供信息存儲空間,僅對用戶上傳內(nèi)容的表現(xiàn)方式做保護處理,對用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯,并不能對任何下載內(nèi)容負責(zé)。
- 6. 下載文件中如有侵權(quán)或不適當(dāng)內(nèi)容,請與我們聯(lián)系,我們立即糾正。
- 7. 本站不保證下載資源的準確性、安全性和完整性, 同時也不承擔(dān)用戶因使用這些下載資源對自己和他人造成任何形式的傷害或損失。
最新文檔
- 2025-2030年中國除雪車市場競爭格局及投資前景規(guī)劃研究報告
- 2025-2030年中國酒精飲料產(chǎn)業(yè)發(fā)展?fàn)顩r及投資前景規(guī)劃研究報告
- 2025-2030年中國豆醬(大醬)行業(yè)競爭格局展望及投資策略分析報告
- 2025-2030年中國花卉種植行業(yè)供需現(xiàn)狀及投資發(fā)展規(guī)劃研究報告
- 2025-2030年中國生態(tài)廁所行業(yè)運行趨勢及投資前景分析報告
- 2025-2030年中國焊接材料行業(yè)市場十三五規(guī)劃與投資戰(zhàn)略研究報告
- 2025年房地產(chǎn)項目信用證擔(dān)保專項合同2篇
- 2025-2030年中國汽車發(fā)電機調(diào)節(jié)器產(chǎn)業(yè)發(fā)展現(xiàn)狀及前景規(guī)劃研究報告
- 二零二五年度商業(yè)地產(chǎn)交易預(yù)付款合同模板4篇
- 2025年旅游紀念品擔(dān)保交易協(xié)議3篇
- GB/T 18476-2001流體輸送用聚烯烴管材耐裂紋擴展的測定切口管材裂紋慢速增長的試驗方法(切口試驗)
- GA 1551.5-2019石油石化系統(tǒng)治安反恐防范要求第5部分:運輸企業(yè)
- 拘留所教育課件02
- 沖壓生產(chǎn)的品質(zhì)保障
- 《腎臟的結(jié)構(gòu)和功能》課件
- 2023年湖南聯(lián)通校園招聘筆試題庫及答案解析
- 上海市徐匯區(qū)、金山區(qū)、松江區(qū)2023屆高一上數(shù)學(xué)期末統(tǒng)考試題含解析
- 護士事業(yè)單位工作人員年度考核登記表
- 天津市新版就業(yè)、勞動合同登記名冊
- 產(chǎn)科操作技術(shù)規(guī)范范本
- 人教版八年級上冊地理全冊單元測試卷(含期中期末試卷及答案)
評論
0/150
提交評論