<table id="ej5zp"></table>

  • չϢչȫ

    ΛρFܿAIڔֽеČ`c̽
    Դ“W   lڣ2022-03-31 11:59:00   g[8419  

    xC֮Ĉ C֮ľ݋ 3 23 ڙC֮ AI ƼΛρFڙCܲܿl}v AI ڔֽеČ`c̽ ܿBֽһØе˹ (AI)󔵓Ӌȼg...

    C֮Ĉ

    C֮ľ݋

    3 23 ڙC֮ AI ƼΛρFڙCܲܿl}v AI ڔֽеČ`c̽

    ܿBֽһØе˹ (AI)󔵓Ӌȼg˔ֽĺφµе[˽ȫQLԼδɸ횾oں֦~ï AI + [˽AI + ȫȳɞ鮔ؽͻƵķ AI gǔ֕rLUƼݶȵPI֮һΛρF 2020 6 ʽl̽ 6 Ŀ AI gܘwϵĿǰ[˽oɽƽȼgwϵвٵоͻƺҲȻصhҪmͶ

    ΛρFܿAIڔֽеČ`c̽

    žܿڙC֮ AI ƼϵvC֮M˲׃ԭľ݋

    dzdC֮Ҷ֪˹ڳɞճдҲɻȱһڎÑɸNӵěQ AI g䌍Ҳ¶˺ܶcƫҊܹ˽Q AI е@Щ}ه˹ܵęCdzҪ@ҲҽҪ} AI ڔֽеČ`c̽

    wֽ҂ԿڇHyнoĽڿƼAI õˏVđе˹Ӌȼgɞ˽ڿƼĺҳd˷dzҪijφµ

    ΛρFܿAIڔֽеČ`c̽

    DԴhttps://twitter.com/bis_org/status/1222834967920685057

    ڮaIܻ^[˽oȫȸԵĆ}˹ܵӰ푕׃ԽԽҪҲQδֽ߄ɸ횾oںϲп֦~ïAI + [˽ / ȫȳɞ鮔´ؽͻƵķ AI I͌WgȦdzҪֻд_ AI ěQ߰ȫ[˽˂ AIl]

    ҂ڴ씵ֽƽ_^Ҳ“˺ܶⲿĸУlչ˿ AI ļg҂ϣ AI ڔ[˽oɽԺƽԺͰȫԣԣ涼б^õ@ӲܝM㹫ߘI猦 AI ڴ

    ˌF AI ļg҂ڸֽYϵͬrһЩcķ繫ƽCWCWDCWɽCW[˽Ӌȵͨ^@Щcgаl҂܉LUȫLؔόӾwṩ֧_@ЩՓ܉򱻿ƌWضxɹ̵ĿĶƳNƽ_͹ʹ AI ﶼܑá AI@һ

    ΛρFܿAIڔֽеČ`c̽

    ҕһB҂Dɽ[˽oĂȡõMչ

    DCW

    DǷdzҊķǚWʽgµһNY罻WjtˎIзdzVđHnjc߅MнģڈDзdzõı_@F˴ıQD񽛾WjGNNķGNN ڈD\еȌW]pzyȺܶIзdzõЧ

    ڌ`҂lFGNN ܉^õؿ˷ϢĆ}Ķ AI Lβ͑С΢IȱϢȺķʹַֽܵĸʴ AI ĸw AI İҲؕIһ^̎IҎģĈDģ}

    ҂֪CW㷨һ]Џ󹤳̵֧㷨yҎģ֧ǰfĹIDĽY҂аlһDWϵyAGLAnt Graph Learning[1]@ϵyD񽛾WjăɂRۺ͸MЌW҂@һʽһԲ׽ k-hop ӵĈD񽛾Wj k ӵČWʽDʾʾDҲԿ@Ă;ۺϵķ

    ΛρFܿAIڔֽеČ`c̽

    ˌF@һD񽛾WjӖʹҎģ҂ϵyҪ֞Ȼ@ϵyOӋijԕPעɔUչeԼM܌FеķMЏ@һԭt҂ĺģK

    GraphFlatӱM̎

    GraphTrainerӖ֣

    GraphInferTģϵ

    ҕеһЩPIMн

    ΛρFܿAIڔֽеČ`c̽

    Ӗ@һ҂\˂yąĽYԴ惦^ąхзֳɶƬܺõش惦ȻùIϵyдڵĴCYԴҲ workerMвеӋ

    ΛρFܿAIڔֽеČ`c̽

    AGL ҂̎ MapReduce MЈDӱӖgOӋ߅օ^DÜpˮеȶNӋマ҂܉򿴵һ^ĹIһ 62 |c3300 |l߅挍ĈD҂܉ʹ 3 f core 挍ϵyĜyԇҲ܉򿴵@һҎģ҂ AGL ϵy܉߂Եļٱб^õĿɔUչҲֹ֧IҎģĈDCW㷨˱^ԌĻ

    ΛρFܿAIڔֽеČ`c̽

    @һϵy҂OӋһ׬Fđ҂@ND~׵ĴҎģYPϵᘌIӈDuӈDIu·ӈDͨ^DaӈDȻ AGL ϵyMЄӑBĈDWWD҂M朽AyҎģYPϵдڵ׬FMReʹ׬Fб^ȵ½½ 10%

    ΛρFܿAIڔֽеČ`c̽

    @΄֮ڶ҂νY@ӵϵy AI İnjLβÑСI҂lFСIׂȱڣڽYԴoγɵľ޴Yȱڣ@_СIİlչ҂Ҳ֪СIëѪڵ\Юa˷dzPI҂ϣͨ^ GNNʹ÷Úvʷ޵Ŀ͑öȳɞĶMСIڽϵһЩV AI İ

    wf҂ȕMйھ朽AygAyЩI֮gܴڽIȺȻ[˽oǰ»ȺM÷҂܌СIڹȺR۵һһķ֮ReIr

    ΛρFܿAIڔֽеČ`c̽

    ҂һrսYϵ GNNSpatial-Temporal aware Graph Neural NetworkST-GNN [2]҂ͨ^ǰᵽĹھaI֮gP“ٽYψDFеһЩLU˺ͨ^@rսYϵ ST-GNN @һ}DuֵĆ}Ķ朾WjIu@ӵuu@I`sĸĶMϵV

    ΛρFܿAIڔֽеČ`c̽

    ҂һЩy GBDTGATˌY@ʾ҂@Y˕rϢķ܉СIĽVAyϴMģ͵Ҫԭ҂ķY˺ܶDϢOӋ˕rעęC܉^õں϶ԪSȵϢwFI֮g^sȺPĶReСIu@ӵu܌Ľڷ

    ΛρFܿAIڔֽеČ`c̽

    ߹ھ҂ҲһN·֪ĈD񽛾WjPath-aware Graph Neural NetworkPaGNN[3]ں˂ͅRۃɂںϵ^ЌW˃ɂc֮gĽY·ĽY@ӾܸõДɂc֮gܴڵďsPĶõLȺ朽MСIYϵ

    ΛρFܿAIڔֽеČ`c̽

    ҂@oһͨ^_IϢ҂Բ鵽朾WjһD@һD֮҂γijЩƷƵĹ朾WjȻͨ^ǰᵽĸʽӵ GNN DMPھȻٰDuֵĆ}@ӵһDķ֮ȺlFĜʴ_Ҳб^@εIõõIJ AI wʺͰ

    ΛρFܿAIڔֽеČ`c̽

    ͬr҂Ҳע⵽DW@N㷨ԵĆ}҂ⲿУģ͵ҲQģ^ƽyȝچ}҂߀һµķĮ| GNN ܁팦ؓ䌦ԹһעؓϢ޼􌦿ĶMһ AI Ŀɿ [4] [5] [6] 

    ΛρFܿAIڔֽеČ`c̽

    ɽCW

    Fںܶ AI ķһںģKˆD˂g^̲؄e˽҂ϣͨ^ɽጵCW׌ںɺ׃ңһ̶ϿɽጣK׃ɰ׺УȫɽጣɽCWʹCWģ܉ķʽÑጻʬFО

    ΛρFܿAIڔֽеČ`c̽

    ҂һNµķ COCO(COnstrained feature perturbation and COunterfactual instances) [7] ģ͵Ĝyԇӱڴ֮ǰIѽһЩɽጷɽԷQߘ䣩ȫֿɽԷ PLNNþֲɽԷ SHAP҂һ^mڹIБõĿɽԷ

    @Ǻ܏s㷨ҪȥYxyԇӱĽ Mixup ɔ_ӔȻyԇӱMƵĔ_ӵõӱͨ^ӱӋyԇӱҪoģ͵Ŀɽ

    ΛρFܿAIڔֽеČ`c̽

    ڈD񔵓҂@Yxǰ 200 ҪɈDԒ@ЩNڔֵ߅@һ֪ھҪ_ڹIгõı҂ҲȰҪھӖģȻģھҪʽ SHAPLIMEھЧČԿ҂ķھб^õЧ

    ΛρFܿAIڔֽеČ`c̽

    ҂Եó@ӎׂYՓһͨ^ƵĔ_COCO ܉ױRҪͨ^ Mixup MV COCO ԱF^òҸ

    ҂@ӵķõLU֪Еr҂lFijˣ珈ijij֧Ѓɂ~һ~loԼͬһ~MD~˕r҂LU֪ģͿܕД@~ð҂ϣ֪@LU֪ģ͞ʲô@һQ҂ COCO ģԓLU֪ģ͵ҪQ҂ܕó@һЩӣfͬ֙C̖ƽ_TȼvʷӋ֧Δ 360 콻׮ָ

    ͨ^@ӵһЩҪ҂ԷһLU֪ģ͞ʲôijQĶȥC@LU֪ģǷoĽYDzǿɿͨ^@һʽ҂@ЩҪQӽoI՛QMһˌHrð˺ͱð֮gǷHPϵȻMһȥ˙CYϵДQǷY~̖@ʹ҂ĘIˆTõLU֪ģ͛Qߵ߉݋Ҳ܎҂ĘIՌҽYģͽጁQģLU

    ΛρFܿAIڔֽеČ`c̽

    @һ漰~ěQ҂䌍Ƿdz֔҂ϣõؿģ͵LUÑĴ_ʹLU֪ģ܉^õرoҵ~ȫ҂Ҳϣ@ģȻјIյĽ򞷴IģĶʹ˙CY_^õЧ

    [˽oCW

    [˽oѽژIlչ˺ܶҲe˺ܶgZ[˽TEE෽ȫӋÿһNgԼmõĈ҂lFFڵ[˽ogyģ͏Чȡñ^õƽ@Ŀǰһ໥Ƽsľ

    ΛρFܿAIڔֽеČ`c̽

    ҂]INVȹIнҊĔͬrַdzϡmȻWgȦкܶ[˽CWΌõҎģϡ蔵һ^Ć}

    ҂һN CAESARSecure Large Scale Sparse Logistic Regression[8] ķڻ MPC fhOӋҎģ[˽o LR 㷨

    ΛρFܿAIڔֽеČ`c̽

    ʲôOӋ@һ MPC fh҂lF1mȻͬB܅fhwfͨŏsȱ^Ӌsȱ^ܷfhͨŏsmȻ^Ӌs^2CWģеķǾԺܑBg›]kֱӋfӋܛ]kM挍ҪЧı_ʽڝMģ;ȵǰ½ͺӋҪ Mһͨ_N҂˻ MPC fhOӋ[˽oꇳ˷ͨ^̩չ_ȥͷǾ\ďs LR ķ

    @Ҫc1ϡľꇳ˷҂ͨ^ϵ MPC fhںmĵطxmąfhҪa Beaver’s triple܉õЧ2ȫϡľ\܉ͬrܷͬBܵļgYϷֲʽӋڅf{ָ]³ѽеļȺYԴÿȺҲǷֲʽČWϵyͨ^@ӵķʽ҂܉dzõȥMзֲʽ\Ȼͨ^wąf{ąf{K\

    ΛρFܿAIڔֽеČ`c̽

    ΛρFܿAIڔֽеČ`c̽

    ͨ^@Nʽ҂lF CAESAR Ч_˘Iе SecureML 130 

    ΛρFܿAIڔֽеČ`c̽

    @ӵ[˽og҂ְly“Lصđ҂ѽڙĔMˇLԇʹģӖģ\Aξԭʼcη\“\ģʽ܉õģ͵ָˣ猢 KS ָ 12%~23%ģͮaĽY\õL؈҂ܱ^õ،FŲֹڸLUJĶmJomFLUĿ

    ΛρFܿAIڔֽеČ`c̽

    ͬr҂Ҳ@ӵļgõ“Ϸ֪RںϵȈ [9]ļgԸ飺ӋͿ[˽Ӌ㼼gͨ^ģݶȺͅȫ팍Frֵͨ@ԑڙCȲ\I͙C֮gȫϢ҂ͨ^[˽o֪RDVȼgFC֮gI֪RںwReʴ_UCȯȑ

    ΛρFܿAIڔֽеČ`c̽

    CW

    ڌCW҂Ҫõֻķʽٶ҂ģͱ]̫˽@һٶȥ҂ϵyںй҂OӋ˃ɷNʽˆDͨ^@ӵһЩԼӱĶ҂ϣӱwԺwƹЧԴˁIծД·İȫrͬr҂ЮaĘӱҲŵCWӖƽ_҂һӖƽ_ǰ湥aĘӱںϵӖCʹÛQ߅ļt׃{fƽƽζͨԕ׃ø܉ģ͵ijЩr܉ƘӱĆ}ĶIվȵ [10] 

    ΛρFܿAIڔֽеČ`c̽

    ǰ҂Y˺ܶ AI ڔֽеغ͌`İԵɽ[˽oW҂ҲlFI AI ÿһСđöζ҂xδĉһc

    ڌ`̽ AI ^҂ҲlFImȻһЩ AI ذо@ȻضhmȻѽвٵͻĿǰ󲿷ֵͻ߀ۼcĈ

    ҂Ҳ AI g܉m˹ܼgڽڈе͸ѺʹÛQ߸Ŀǰ AI ߀̎ڸٰlչA҂Č`ؿxKĿ AI ߀Щx҂Ҳϣͨ^҂ڹIео`ȿӽͲćLԇ܉׌ͬȥ˼܉ͨ^ AI ֕rLUƼݶ

    ΛρFܿAIڔֽеČ`c̽

    [1] Zhang D, Huang X, Liu Z, et al. AGL: a scalable system for industrial-purpose graph machine learning[J]. Proceedings of the VLDB Endowment, 2020, 13(12): 3125-3137.

    [2] Yang S, Zhang Z, Zhou J, et al. Financial Risk Analysis for SMEs with Graph-based Supply Chain Mining[C]//IJCAI. 2020: 4661-4667

    [3] Yang S, Hu B, Zhang Z, et al. Inductive Link Prediction with Interactive Structure Learning on Attributed Graph[C]//Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Cham, 2021: 383-398.

    [4] Yu L, Pei S, Zhang C, et al. Self-supervised smoothing graph neural networks[C]. AAAI 2022, accepted.

    [5] Bo D, Hu B B, Wang X, et al. Regularizing Graph Neural Networks via Consistency-Diversity Graph Augmentations[C]. AAAI 2022, accepted.

    [6] Zhang M, Wang X, Zhu M, et al. Robust Heterogeneous Graph Neural Networks against Adversarial Attacks[C]. AAAI 2022, accepted.

    [7] Fang J P, Zhou J, Cui Q, et al. Interpreting Model Predictions with Constrained Perturbation and Counterfactual Instances[J]. International Journal of Pattern Recognition and Artificial Intelligence, 2021: 2251001.

    [8] Chen C, Zhou J, Wang L, et al. When homomorphic encryption marries secret sharing: Secure large-scale sparse logistic regression and applications in risk control[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021: 2652-2662.

    [9] Chen C, Wu B, Wang L, et al. Nebula: A Scalable Privacy-Preserving Machine Learning System in Ant Financial[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management. 2020: 3369-3372.

    [10] Huan Z, Wang Y, Zhang X, et al. Data-free adversarial perturbations for practical black-box attack[C]//Pacific-Asia conference on knowledge discovery and data mining. Springer, Cham, 2020: 127-138.

    ٝվ

    ˹܌

    P~ Λρ F ܿ е ` ̽

    չ_
    Copyright © 2010-2022 AiLab Team. ˹܌     | “ϵ҂ | V | ˾ӑB | ؟• | [˽l | C | չ
    18禁无遮拦无码国产在线播放

    <table id="ej5zp"></table>