{"id":43499,"date":"2023-07-06T21:23:32","date_gmt":"2023-07-06T13:23:32","guid":{"rendered":"https:\/\/swarma.org\/?p=43499"},"modified":"2023-07-06T21:23:32","modified_gmt":"2023-07-06T13:23:32","slug":"%e5%9b%be%e8%a1%a8%e7%a4%ba%e5%ad%a6%e4%b9%a0%e3%80%81%e9%a2%84%e6%b5%8b%e5%92%8c%e8%af%84%e4%bc%b0-nat-comput-sci-%e9%80%9f%e9%80%92","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=43499","title":{"rendered":"\u56fe\u8868\u793a\u5b66\u4e60\u3001\u9884\u6d4b\u548c\u8bc4\u4f30 | Nat. Comput. Sci. \u901f\u9012"},"content":{"rendered":"
\n
\n
\n
\n

<\/p>\n


<\/strong><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/strong><\/strong><\/span><\/p>\n

\u5173\u952e\u8bcd\uff1a\u56fe\u8868\u793a\u5b66\u4e60\uff0c\u56fe\u5d4c\u5165\uff0c\u968f\u673a\u6e38\u8d70<\/span><\/strong><\/strong><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/span><\/strong><\/strong><\/strong><\/span><\/p>\n<\/section>\n

\n
\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
<\/section>\n<\/section>\n
\n


<\/p>\n

<\/p>\n<\/section>\n

\n
\n
\n
\n
\u8bba\u6587\u9898\u76ee\uff1aGRAPE for fast and scalable graph processing and random-walk-based embedding<\/span><\/section>\n
\u671f\u520a\u6765\u6e90\uff1aNature Computational Science<\/em><\/span><\/section>\n
\u8bba\u6587\u94fe\u63a5\uff1ahttps:\/\/pattern.swarma.org\/paper\/b7c59134-1477-11ee-9f2e-0242ac17000d<\/span><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/section>\n
\u56fe\u8868\u793a\u5b66\u4e60<\/span>\uff08Graph representation learning\uff09<\/span>\u65b9\u6cd5\u4e3a\u89e3\u51b3\u7531\u56fe\u8868\u793a\u7684\u590d\u6742\u73b0\u5b9e\u95ee\u9898\u5f00\u8f9f\u4e86\u65b0\u9014\u5f84\u3002\u7136\u800c\uff0c\u8fd9\u4e9b\u5e94\u7528\u7a0b\u5e8f\u4e2d\u4f7f\u7528\u7684\u8bb8\u591a\u56fe\u7531\u6570\u767e\u4e07\u4e2a\u8282\u70b9\u548c\u6570\u5341\u4ebf\u4e2a\u8fb9\u7ec4\u6210\uff0c\u8d85\u51fa\u4e86\u5f53\u524d\u65b9\u6cd5\u548c\u8f6f\u4ef6\u5b9e\u73b0\u7684\u80fd\u529b\u3002\u8fd9\u7bc7\u8bba\u6587\u4e2d\u63d0\u51fa GRAPE<\/span> (Graph Representation Learning, Prediction and Evaluation\uff0c\u56fe\u8868\u793a\u5b66\u4e60\u3001\u9884\u6d4b\u548c\u8bc4\u4f30)<\/span> \uff0c\u4e00\u4e2a\u7528\u4e8e\u56fe\u5904\u7406\u548c\u5d4c\u5165\u7684\u8f6f\u4ef6\u8d44\u6e90\uff0c\u5b83\u80fd\u591f\u901a\u8fc7\u4f7f\u7528\u4e13\u95e8\u7684\u548c\u667a\u80fd\u7684\u6570\u636e\u7ed3\u6784\u3001\u7b97\u6cd5\uff0c\u4ee5\u53ca\u57fa\u4e8e\u968f\u673a\u6e38\u8d70\u65b9\u6cd5\u7684\u5feb\u901f\u5e76\u884c\u5b9e\u73b0\uff0c\u968f\u7740\u8f93\u5165\u56fe\u7684\u5927\u5c0f\u63d0\u5347\u7b97\u6cd5\u6027\u80fd\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u4e0e\u6700\u5148\u8fdb\u7684\u8f6f\u4ef6\u8d44\u6e90\u76f8\u6bd4\uff0cGRAPE \u5728\u5b9e\u9645\u7684\u7a7a\u95f4\u4e0e\u65f6\u95f4\u590d\u6742\u5ea6\u65b9\u9762\u6709\u6570\u91cf\u7ea7\u7684\u63d0\u9ad8\uff0c\u800c\u4e14\u5728\u8fb9\u548c\u8282\u70b9\u7684\u6807\u7b7e\u9884\u6d4b\u6027\u80fd\u4e0a\u4e5f\u6709\u6240\u63d0\u9ad8\u3002GRAPE \u5305\u542b\u5927\u7ea6170\u4e07\u884c\u5b8c\u6574\u7684 Python \u548c Rust \u4ee3\u7801\uff0c\u63d0\u4f9b69\u4e2a\u8282\u70b9\u5d4c\u5165\u65b9\u6cd5\u300125\u4e2a\u63a8\u7406\u6a21\u578b\u3001\u4e00\u7cfb\u5217\u9ad8\u6548\u7684\u56fe\u5f62\u5904\u7406\u5de5\u5177\uff0c\u4ee5\u53ca\u6765\u81ea\u6587\u732e\u548c\u5176\u4ed6\u6765\u6e90\u7684\u8d85\u8fc78\u4e07\u4e2a\u56fe\u3002\u6807\u51c6\u5316\u7684\u754c\u9762\u5141\u8bb8\u7b2c\u4e09\u65b9\u5305\u8fdb\u884c\u65e0\u7f1d\u96c6\u6210\uff0c\u800c\u73b0\u6210\u7684\u548c\u6a21\u5757\u5316\u7684\u7ba1\u9053\u5141\u8bb8\u5bf9\u56fe\u8868\u793a\u5b66\u4e60\u65b9\u6cd5\u8fdb\u884c\u6613\u4e8e\u4f7f\u7528\u7684\u8bc4\u4f30\uff0c\u56e0\u6b64 GRAPE \u4e5f\u88ab\u5b9a\u4f4d\u4e3a\u53ef\u5728\u56fe\u8868\u5f81\u548c\u5d4c\u5165\u7684\u65b9\u6cd5\u548c\u8f6f\u4ef6\u5305\u4e4b\u95f4\u8fdb\u884c\u516c\u5e73\u6bd4\u8f83\u7684\u8f6f\u4ef6\u5de5\u5177\u3002<\/span><\/section>\n

<\/span><\/section>\n
<\/section>\n

\u56fe1 a\uff09GRAPE\u7684\u5904\u7406\u6a21\u5757\uff1bb\uff09\u7528\u4e8e\u5bf9\u56fe\u5d4c\u5165\u6280\u672f\u3001\u56fe\u5904\u7406\u65b9\u6cd5\u548c\u5e93\u8fdb\u884c\u7b80\u5355\u3001\u516c\u5e73\u548c\u53ef\u91cd\u590d\u7684\u6bd4\u8f83\u7684\u6d41\u7a0b\uff1bc\uff09\u5bf9KGCOVID19\u7684\u56fe\u8fdb\u884c\u53ef\u89c6\u5316\uff0c\u901a\u8fc7\u663e\u793a\u901a\u8fc7\u4f7f\u7528 Node2Vec SkipGram \u6a21\u578b\u8ba1\u7b97\u7684 t \u5206\u5e03\u968f\u673a\u90bb\u5c45\u5d4c\u5165\u7684\u524d\u4e24\u4e2a\u7ec4\u4ef6\u83b7\u5f97\uff0c\u5e76\u5bf9\u8282\u70b9\u7c7b\u578b\u3001\u8fb9\u7c7b\u578b\u53ca\u8fb9\u6807\u7b7e\u8fdb\u884c\u9884\u6d4b\u3002<\/span><\/p>\n


<\/span><\/section>\n
<\/section>\n

\u56fe2 \u4e0d\u540c\u8282\u70b9\u6570\u7684\u56fe\u4f5c\u4e3a\u8f93\u5165\u65f6\uff0c\u8f7d\u5165\u56fe\uff0c\u4f7f\u7528\u4e00\u9636\u53ca\u4e8c\u9636\u968f\u673a\u6e38\u8d70\u65f6\uff0c\u4e0d\u540c\u8f6f\u4ef6\u5305\u6d88\u8017\u7684\u5cf0\u503c\u5185\u5b58\u4e0e\u8fd0\u884c\u65f6\u95f4\uff0c\u53ef\u4ee5\u770b\u5230GRAPE\u5728\u5927\u6570\u636e\u65f6\uff0c\u8868\u73b0\u6700\u4f73<\/span><\/p>\n


<\/span><\/section>\n
<\/section>\n

\u56fe3 \u4f7f\u7528GRAPE\u4e2d\u7684\u591a\u79cd\u65b9\u6cd5\uff0c\u5bf9\u56fe\u8fdb\u884c\u5d4c\u5165\u65f6\u7684\u51c6\u786e\u6027\uff0c\u5176\u4e2d\u7d2b\u8272\u662f\u4e3aGRAPE\u5305\u76f4\u63a5\u5b9e\u73b0\u7684\u65b9\u6cd5\uff0c\u84dd\u8272\u7684\u4e3a\u5728cran\u5305\u4e2d\u96c6\u6210\u7684\u7b97\u6cd5<\/span><\/p>\n


<\/section>\n
\n

<\/span><\/section>\n
\u7f16\u8bd1\uff5c\u90ed\u745e\u4e1c<\/span><\/span><\/span><\/section>\n

<\/section>\n
\n
\n
\n
\n

\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7ec4\u5408\u4f18\u5316\u8bfb\u4e66\u4f1a\u542f\u52a8<\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n


<\/section>\n
<\/span><\/a><\/section>\n
<\/span><\/section>\n
\u8be6\u60c5\u8bf7\u89c1\uff1a<\/span><\/span><\/section>\n
\u52a0\u901f\u7ecf\u5178\u7b97\u6cd5\u6548\u7387\uff0c\u7a81\u7834\u73b0\u5b9e\u6280\u672f\u74f6\u9888\uff1a\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7ec4\u5408\u4f18\u5316\u8bfb\u4e66\u4f1a\u542f\u52a8<\/a><\/span>
<\/span><\/section>\n

<\/section>\n

<\/section>\n

\u63a8\u8350\u9605\u8bfb<\/span><\/strong><\/strong><\/p>\n

\u200d<\/span>1. <\/strong>\u56fe\u8868\u793a\u65b9\u6cd5\u9a71\u52a8\u5927\u5206\u5b50\u8ba1\u7b97\u7814\u7a76 | arXiv\u901f\u9012<\/a><\/strong><\/span><\/section>\n
2.<\/strong> \u5927\u6a21\u578b\u70ed\u6f6e\u4e4b\u540e\u7684\u672a\u6765\u65b0\u65b9\u5411\uff1a\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7ec4\u5408\u4f18\u5316 | \u6587\u732e\u6c47\u603b<\/a><\/strong><\/span><\/strong><\/section>\n
3. <\/strong><\/strong>Nat. Mach. Intell. \u901f\u9012\uff1a\u56fe\u795e\u7ecf\u7f51\u7edc\u5b9e\u73b0\u4e09\u7ef4\u6d41\u4f53\u8fd0\u52a8\u4e2d\u7684\u7c92\u5b50\u8ddf\u8e2a<\/a><\/strong><\/strong><\/span><\/section>\n
4. \u300a\u5f20\u6c5f\u00b7\u590d\u6742\u79d1\u5b66\u524d\u6cbf27\u8bb2\u300b\u5b8c\u6574\u4e0a\u7ebf\uff01<\/strong><\/a><\/strong><\/strong><\/strong><\/section>\n
<\/strong><\/a><\/strong><\/strong><\/strong><\/section>\n
<\/strong><\/a><\/strong><\/strong><\/strong><\/section>\n
5. \u6210\u4e3a\u96c6\u667aVIP\uff0c\u89e3\u9501\u5168\u7ad9\u8bfe\u7a0b\uff0f\u8bfb\u4e66\u4f1a<\/span><\/strong><\/a><\/strong><\/strong><\/strong><\/strong><\/section>\n
6.<\/strong><\/strong><\/strong> <\/strong><\/strong><\/strong>\u52a0\u5165\u96c6\u667a\uff0c\u4e00\u8d77\u590d\u6742\uff01<\/strong><\/a><\/strong><\/strong><\/strong><\/span><\/section>\n

<\/section>\n


<\/p>\n

\u70b9\u51fb\u201c\u9605\u8bfb\u539f\u6587\u201d\uff0c\u62a5\u540d\u8bfb\u4e66\u4f1a<\/strong><\/span><\/strong><\/strong><\/span><\/strong><\/section>\n

<\/mp-style-type><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

\u5173\u952e\u8bcd\uff1a\u56fe\u8868\u793a\u5b66\u4e60\uff0c\u56fe\u5d4c\u5165\uff0c\u968f\u673a\u6e38\u8d70 \u8bba\u6587\u9898\u76ee\uff1aGRAPE for fast and scalable graph processing and random-walk-based embedding \u671f\u520a\u6765\u6e90\uff1aNature Computational Science \u8bba\u6587\u94fe\u63a5\uff1ahttps:\/\/pa…<\/p>\n","protected":false},"author":0,"featured_media":43493,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[1],"tags":[],"special":[],"_links":{"self":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/43499"}],"collection":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=43499"}],"version-history":[{"count":0,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/43499\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/media\/43493"}],"wp:attachment":[{"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=43499"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=43499"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=43499"},{"taxonomy":"special","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fspecial&post=43499"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}