{"id":19559,"date":"2020-05-08T18:12:07","date_gmt":"2020-05-08T10:12:07","guid":{"rendered":"https:\/\/swarma.org\/?p=19559"},"modified":"2020-05-08T18:12:07","modified_gmt":"2020-05-08T10:12:07","slug":"%e5%9b%be%e7%bd%91%e7%bb%9c%e5%85%a5%e9%97%a8%e8%b7%af%e5%be%84%ef%bc%9a%e4%bb%8e%e7%bd%91%e7%bb%9c%e7%a7%91%e5%ad%a6%e8%a7%86%e8%a7%92%e5%87%ba%e5%8f%91%ef%bc%8c%e4%b8%8a%e6%89%8b%e6%b7%b1%e5%ba%a6","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=19559","title":{"rendered":"\u56fe\u7f51\u7edc\u5165\u95e8\u8def\u5f84\uff1a\u4ece\u7f51\u7edc\u79d1\u5b66\u89c6\u89d2\u51fa\u53d1\uff0c\u4e0a\u624b\u6df1\u5ea6\u5b66\u4e60\u524d\u6cbf\u6280\u672f"},"content":{"rendered":"
\n
<\/section>\n

<\/section>\n
\n
\u5bfc\u8bed<\/span><\/strong><\/span><\/section>\n
\n
\n
\n

\u4ece\u77e5\u8bc6\u56fe\u8c31\u5230\u6982\u7387\u56fe\u6a21\u578b\uff0c\u4ece\u86cb\u767d\u8d28\u76f8\u4e92\u4f5c\u7528\u7f51\u7edc\u5230\u793e\u4ea4\u7f51\u7edc\uff0c\u4ece\u57fa\u672c\u7684\u903b\u8f91\u7ebf\u8def\u5230\u56e0\u7279\u7f51\uff0c\u56fe\u4e0e\u7f51\u7edc\u65e0\u5904\u4e0d\u5728\u3002\u7531\u4e8e\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u65b9\u6cd5\u96be\u4ee5\u5904\u7406\u56fe\u6570\u636e\u4fe1\u606f\uff0c\u8fd1\u5e74\u6765\u5174\u8d77\u4e86\u56fe\u795e\u7ecf\u7f51\u7edc\u65b9\u6cd5\uff0c\u5728\u8bf8\u591a\u771f\u5b9e\u95ee\u9898\u7684\u5efa\u6a21\u548c\u89e3\u51b3\u4e0a\uff0c\u53d6\u5f97\u826f\u597d\u6548\u679c\u3002\u4f5c\u4e3a\u6b63\u706b\u70ed\u7684\u65b0\u9886\u57df\uff0c\u56fe\u7f51\u7edc\u65b9\u6cd5\u8fd8\u6ca1\u6709\u975e\u5e38\u6210\u719f\u7684\u6559\u6750\u6559\u7a0b\uff0c\u6211\u4eec\u6574\u7406\u4e86\u8fd9\u4efd\u7ed3\u5408\u591a\u95e8\u57fa\u7840\u8bfe\u7a0b\u3001\u591a\u7bc7\u7ecf\u5178\u8bba\u6587\u7684\u5b66\u4e60\u8def\u5f84\uff0c\u4f9b\u4f60\u5165\u95e8\u53c2\u8003\u3002<\/span><\/span><\/strong><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n


<\/p>\n

<\/section>\n

\u626b\u7801\u767b\u5f55\u96c6\u667a\u6591\u56fe\uff0c\u83b7\u53d6\u5b8c\u6574\u5b66\u4e60\u8def\u5f84
<\/span><\/strong><\/span><\/p>\n


<\/p>\n

\u56fe\u7f51\u7edc\u662f\u4e00\u79cd\u7ed3\u5408\u673a\u5668\u5b66\u4e60\u548c\u7f51\u7edc\u79d1\u5b66\u7684\u524d\u6cbf\u5b66\u79d1\uff0c\u5b83\u5c06\u4f20\u7edf\u7684\u7528\u4e8e\u81ea\u7136\u8bed\u8a00\u5904\u7406\u3001\u56fe\u50cf\u5904\u7406\u3001\u8ba1\u7b97\u673a\u89c6\u89c9\u7b49\u9886\u57df\u4e2d\u7684\u795e\u7ecf\u7f51\u7edc\u3001\u6df1\u5ea6\u5b66\u4e60\u6280\u672f\u6269\u5145\u5230\u4e86\u4e00\u822c\u7684\u56fe\u4e0a\uff0c\u4f7f\u5f97\u8fd9\u4e9b\u6280\u672f\u53ef\u4ee5\u5904\u7406\u7c7b\u4f3c\u4e8e\u56fe\u3001n \u7ef4\u6d41\u5f62\u7b49\u66f4\u52a0\u4e00\u822c\u800c\u666e\u9002\u7684\u975e\u6b27\u51e0\u91cc\u5fb7\u51e0\u4f55\u5bf9\u8c61\uff0c\u4ee5\u53ca\u591a\u5173\u7cfb\u7f51\u7edc\u3001\u77e5\u8bc6\u56fe\u8c31\u3001\u5e26\u5c5e\u6027\u7684\u56fe\u7ed3\u6784\u7b49\u66f4\u52a0\u590d\u6742\u7684\u6570\u636e\u7ed3\u6784\u3002<\/span>\u5927\u6982\u4ece 2015 \u5e74\u5f00\u59cb\uff0c\u8be5\u9886\u57df\u540c\u65f6\u5728\u5b66\u672f\u754c\u548c\u5de5\u4e1a\u754c\u83b7\u5f97\u4e86\u84ec\u52c3\u7684\u53d1\u5c55\u673a\u9047\uff0c\u5b83\u4e0d\u4ec5\u53ef\u4ee5\u5f88\u6709\u6548\u5730\u89e3\u51b3\u8bf8\u5982\u8fde\u8fb9\u9884\u6d4b\u3001\u793e\u533a\u5212\u5206\u7b49\u4f20\u7edf\u7ecf\u5178\u7684\u7f51\u7edc\u79d1\u5b66\u95ee\u9898\uff0c\u800c\u4e14\u8fd8\u53ef\u4ee5\u89e3\u51b3\u8bf8\u5982\u8282\u70b9\u5206\u7c7b\u3001\u7f51\u7edc\u91cd\u6784\u3001\u7f51\u7edc\u8865\u5168\u3001\u56fe\u4e0a\u7684\u7ec4\u5408\u4f18\u5316\u95ee\u9898\u7b49\u975e\u4f20\u7edf\u7684\u7f51\u7edc\u79d1\u5b66\u95ee\u9898\uff0c\u751a\u81f3\u8fd8\u53ef\u4ee5\u89e3\u51b3\u8bf8\u5982\u8ba1\u7b97\u673a\u89c6\u89c9\u3001\u56fe\u50cf\u7406\u89e3\u3001\u81ea\u7136\u8bed\u8a00\u5904\u7406\u3001\u81ea\u52a8\u63a8\u7406\u3001\u673a\u5668\u4eba\u63a7\u5236\u3001\u52a8\u529b\u5b66\u5efa\u6a21\u7b49\u4eba\u5de5\u667a\u80fd\u9886\u57df\u4e2d\u7684\u95ee\u9898\u3002<\/span><\/p>\n


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

\n
\n


<\/p>\n

\n
\n
<\/p>\n

\u4e00\u3001\u6df1\u5ea6\u5b66\u4e60\u4e0e PyTorch \u5165\u95e8<\/strong><\/span><\/p>\n

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


<\/p>\n

\u7cfb\u5217\u8bfe\u7a0b\uff1a<\/span><\/strong>\u706b\u70ac\u4e0a\u7684\u6df1\u5ea6\u5b66\u4e60\uff0c\u7279\u522b\u662f\uff08\u4e0b\uff09\u201c\u81ea\u7136\u8bed\u8a00\u5904\u7406\u201d\u7bc7<\/span><\/p>\n


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

<\/section>\n
https:\/\/campus.swarma.org\/course\/217<\/span><\/strong><\/span>
<\/section>\n


<\/p>\n

\u4e3a\u4e86\u80fd\u591f\u6253\u597d\u6df1\u5ea6\u5b66\u4e60\u7684\u57fa\u7840\uff0c\u4ee5\u53ca\u638c\u63e1\u4e00\u9879\u7f16\u7a0b\u5de5\u5177\uff0c\u5efa\u8bae\u5b66\u4e60\u96c6\u667a\u5b66\u56ed\u4e0a\u7684\u7ebf\u4e0a\u8bfe\u7a0b\u3002<\/span><\/p>\n

\n
\n


<\/p>\n


<\/p>\n

\n
\n
<\/p>\n

\u4e8c\u3001\u56fe\u5411\u91cf\u5316\uff08\u56fe\u5d4c\u5165\uff09<\/strong><\/span><\/p>\n

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


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

\u8981\u60f3\u7528\u673a\u5668\u5b66\u4e60\u7684\u6280\u672f\u5904\u7406\u56fe\u7ed3\u6784\u7684\u6570\u636e\uff0c\u9996\u5148\u8981\u505a\u7684\u5c31\u662f\u5c06\u7f51\u7edc\u4e0a\u7684\u6bcf\u4e2a\u8282\u70b9\u8868\u793a\u6210\u89c4\u6574\u7684\u6b27\u6c0f\u7a7a\u95f4\u5411\u91cf\u3002<\/span><\/p>\n


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


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

1\u3001Word2Vec<\/span><\/strong><\/span><\/h3>\n


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

\u8bfe\u7a0b\uff1a<\/span><\/strong>\u8bcd\u5411\u91cf\u539f\u7406\u521d\u63a2\u4e0eWord2Vec<\/span><\/p>\n


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

<\/section>\n
https:\/\/campus.swarma.org\/course\/212<\/span><\/strong><\/span>
<\/section>\n


<\/p>\n


<\/p>\n

\u8bfe\u7a0b\uff1a<\/span><\/strong>\u6d45\u8c08Word2Vec\uff1a\u81ea\u7136\u8bed\u8a00\u5904\u7406\u7684\u57fa\u77f3<\/span><\/p>\n


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

<\/section>\n
https:\/\/campus.swarma.org\/course\/212<\/span><\/strong><\/span>
<\/section>\n


<\/p>\n

\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/span><\/p>\n

Effi<\/span>cient Estimation of Word Representations in Vector Space<\/span><\/span><\/p>\n

\u8bba\u6587\u5730\u5740\uff1a<\/span><\/p>\n

http:\/\/arxiv.org\/abs\/1301.3781<\/span><\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n

\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

Distributed Repre<\/span>sentations of Words and Phrases and their Compositionality<\/span><\/p>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/arxiv.org\/abs\/1310.4546<\/span><\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n

\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

Linguistic Regularities in Continuous Space Word Representations<\/span><\/p>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/www.aclweb.org\/anthology\/N13-1090\/<\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n

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

\u8fd9\u4e09\u7bc7\u6587\u7ae0\u5f15\u51fa\u4e86\u81ea\u7136\u8bed\u8a00\u5904\u7406\u9886\u57df\u4e2d\u7ecf\u5178\u7684 Word2Vec \u6280\u672f\uff0c\u5b83\u53ef\u4ee5\u901a\u8fc7\u626b\u63cf\u6587\u672c\uff0c\u5c06\u6bcf\u4e2a\u5355\u8bcd\u8d4b\u4e88\u4e00\u4e2a\u5411\u91cf\u3002\u672c\u8d28\u4e0a\u8bb2\uff0c\u5982\u679c\u6211\u4eec\u5c06\u4e00\u7bc7\u6587\u7ae0\u770b\u4f5c\u662f\u8bcd\u8bed\u5171\u73b0\u7684\u7f51\u7edc\uff1a\u5355\u8bcd\u4e3a\u8282\u70b9\uff0c\u5982\u679c\u4e00\u5bf9\u5355\u8bcd\u540c\u65f6\u51fa\u73b0\u5728\u4e00\u4e2a\u53e5\u5b50\u4e2d\u5c31\u8fde\u4e00\u6761\u8fb9\uff0c\u5219\u8bcd\u5411\u91cf\u7684\u5d4c\u5165\u5c31\u76f8\u5f53\u4e8e\u7f51\u7edc\u7684\u5d4c\u5165\u3002<\/span><\/p>\n


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


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

2\u3001\u7f51\u7edc\u5d4c\u5165\u7b97\u6cd5<\/span><\/strong><\/span><\/h3>\n
\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

DeepWalk: Online Learning of Social Representations<\/span><\/h1>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/arxiv.org\/abs\/1403.6652<\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n

\u8fd9\u662f\u7f51\u7edc\u5d4c\u5165\u7b97\u6cd5\u7684\u7b2c\u4e00\u7bc7\u5de5\u4f5c\u3002
<\/span><\/p>\n


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

\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

node2vec: Scalable Feature Learning for Networks<\/span><\/span><\/h1>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/arxiv.org\/abs\/1607.00653<\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n

\u8fd9\u662f\u5bf9 DeepWalk \u7684\u6539\u8fdb\uff0c\u5b83\u76ee\u524d\u5df2\u7ecf\u6210\u4e3a\u4e00\u79cd Benchmark\u3002<\/span><\/span><\/p>\n

\n
\n


<\/p>\n


<\/p>\n

\n
\n
<\/p>\n

\u4e09\u3001\u56fe\u7f51\u7edc<\/strong><\/span><\/p>\n

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


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

\u5982\u679c\u8be6\u7ec6\u8ffd\u6eaf\uff0c\u56fe\u795e\u7ecf\u7f51\u7edc\u65e9\u5728 2008 \u5e74\u5de6\u53f3\u5c31\u88ab\u4eba\u63d0\u51fa\u4e86\uff0c\u4f46\u662f\u5230\u4e86 2015 \u5e74\u5de6\u53f3\uff0c\u968f\u7740\u56fe\u5377\u79ef\u795e\u7ecf\u7f51\u7edc\u7684\u51fa\u73b0\u4e0e\u6d41\u884c\uff0c\u4eba\u4eec\u7a81\u7136\u53d1\u73b0\uff0c\u6211\u4eec\u53ef\u4ee5\u5728\u56fe\u7ed3\u6784\u4e0a\u8fdb\u884c\u5377\u79ef\u64cd\u4f5c\u4e86\uff0c\u800c\u4e14\u8fd9\u79cd\u5377\u79ef\u64cd\u4f5c\u4e0d\u4ec5\u8ba1\u7b97\u7b80\u5355\uff0c\u8fd8\u5177\u6709\u8d85\u5f3a\u7684\u51c6\u786e\u5ea6\uff0c\u8fd9\u5927\u5927\u523a\u6fc0\u4e86\u8be5\u9886\u57df\u7684\u7a81\u98de\u731b\u8fdb\u5730\u53d1\u5c55\u3002<\/span><\/p>\n


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


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

1\u3001\u56fe\u7f51\u7edc\u7efc\u8ff0\uff1a<\/span><\/strong><\/span><\/h3>\n
\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

Relational inductive biases, deep learning, and graph networks<\/span><\/span><\/h1>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/arxiv.org\/abs\/1806.01261<\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n

\u8fd9\u57fa\u672c\u4e0a\u662f\u7b2c\u4e00\u7bc7\u6709\u5173\u56fe\u7f51\u7edc\u7684\u7efc\u8ff0\uff0c\u975e\u5e38\u5168\u9762\uff0c\u4f46\u4e5f\u4e0d\u592a\u5bb9\u6613\u8bfb\u61c2\u3002<\/span><\/span><\/p>\n


<\/p>\n


<\/p>\n

2\u3001\u56fe\u5377\u79ef\u53ca\u5176\u76f8\u5173\u67b6\u6784<\/span><\/strong><\/span><\/h3>\n

<\/h3>\n
\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/span><\/p>\n

Semi-Supervised Classification with Graph Convolutional Networks <\/span><\/p>\n

\u8bba\u6587\u5730\u5740\uff1a<\/span><\/p>\n

https:\/\/arxiv.org\/abs\/1609.02907<\/span><\/span><\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n

\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

Graph Attention Networks<\/span><\/p>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/arxiv.org\/abs\/1710.10903<\/span><\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n

\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

Inductive Representation Learning on Large Graphs<\/span><\/p>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

http:\/\/papers.nips.cc\/paper\/6703-inductive-representation-learning-on-large-graphs<\/span><\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n

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

\u7b2c\u4e00\u7bc7\u662f\u7ecf\u5178\u7684\u56fe\u5377\u79ef\u5de5\u4f5c\uff0c\u5728\u534a\u76d1\u7763\u5b66\u4e60\u4efb\u52a1\u4e0a\u6548\u679c\u975e\u5e38\u597d\uff0c\u7b2c\u4e8c\u7bc7\u662f\u4e00\u79cd\u57fa\u4e8e\u6ce8\u610f\u529b\u7684\u56fe\u5377\u79ef\u67b6\u6784\uff0c\u7b2c\u4e09\u7bc7\u662f\u63d0\u51fa\u4e86 GraphSAGE \u6846\u67b6\uff0c\u4e00\u79cd\u53ef\u4ee5\u5904\u7406\u5927\u89c4\u6a21\u7f51\u7edc\u7684\u56fe\u5377\u79ef\u7f51\u7edc\uff0c\u6548\u679c\u975e\u5e38\u68d2\u3002<\/span><\/p>\n


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

\n
\n


<\/p>\n

\n
\n
<\/p>\n

\u56db\u3001\u76f8\u5173\u5e94\u7528<\/strong><\/span><\/p>\n

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


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

\u53ef\u4ee5\u5c06\u4e0a\u8ff0\u6280\u672f\u5e94\u7528\u4e8e\u5404\u79cd\u5177\u4f53\u7684\u7f51\u7edc\u95ee\u9898\u4e0a\uff0c\u5305\u62ec\u8fde\u8fb9\u9884\u6d4b\u3001\u8282\u70b9\u5206\u7c7b\u3001\u56fe\u5206\u7c7b\u3001\u63a8\u8350\u7b97\u6cd5\u7b49\u3002\u8fd9\u79cd\u5e94\u7528\u975e\u5e38\u591a\uff0c\u6211\u4eec\u4ec5\u6311\u5176\u4e2d\u51e0\u7bc7\u4e0e\u672c\u7814\u7a76\u7ec4\u6700\u76f8\u5173\u7684\u5de5\u4f5c\uff1a<\/span><\/p>\n


<\/p>\n

1\u3001\u8fde\u8fb9\u9884\u6d4b\uff1a<\/strong><\/span><\/h3>\n
\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

Variational Graph Auto-Encoders<\/span><\/span><\/h1>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/arxiv.org\/abs\/1403.6652<\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n


<\/p>\n

2\u3001\u56fe\u5206\u7c7b\uff1a<\/span><\/strong><\/span><\/h3>\n
\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

How Powerful are Graph Neural Networks?<\/span><\/span><\/h1>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/arxiv.org\/abs\/1810.00826<\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n


<\/p>\n

3\u3001\u63a8\u8350\u7b97\u6cd5\uff1a<\/strong><\/span><\/h3>\n
\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

Grap<\/span>h Convolutional Neural Networks for Web-Scale Recommender Systems<\/span><\/span><\/h1>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/arxiv.org\/abs\/1806.01973<\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n


<\/p>\n

4\u3001\u52a8\u529b\u5b66\u5b66\u4e60\u4e0e\u63a7\u5236\uff1a<\/strong><\/span><\/h3>\n
\n
\n
\n

\u8bba\u6587\u9898\u76ee\uff1a<\/p>\n

<\/span>Graph networks as learnable physics engines for inference and control<\/span><\/span><\/h1>\n

\u8bba\u6587\u5730\u5740\uff1a<\/p>\n

https:\/\/arxiv.org\/abs\/1806.01242<\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n


<\/p>\n

       <\/span><\/p>\n

\n
\n


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

\n
\n

\u53c2\u8003\u6587\u732e\uff1a<\/span><\/strong><\/p>\n<\/section>\n<\/section>\n

\n
\n
\n
\n
<\/span><\/section>\n
[1] Tomas Mikolov,Kai Chen,Greg Corrado.et al.: Efficient Estimation of Word Representations in Vector Space ,arxiv,2013<\/span>
<\/section>\n

[2] Tomas Mikolov,Ilya Sutskever,Kai Chen.et al.: Distributed Representations of Words and Phrases and their Compositionality ,arxiv,2013<\/span><\/p>\n

[3] Tomas Mikolov, Wen-tau Yih, Geoffrey Zweig: Linguistic Regularities in Continuous Space Word Representations ,2013<\/span><\/p>\n

[4] Bryan Perozzi,Rami Al-Rfou,Steven Skiena: DeepWalk: Online Learning of Social Representations ,arxiv,2014<\/span><\/p>\n

[5] Aditya Grover,Jure Leskovec: node2vec: Scalable Feature Learning for Networks ,arxiv,2016<\/span><\/p>\n

[6] Peter W. Battaglia,Jessica B. Hamrick,Victor Bapst.et al.: Relational inductive biases, deep learning, and graph networks,arxiv,2018<\/span><\/p>\n

[7] Thomas N. Kipf,Max Welling: Semi-Supervised Classification with Graph Convolutional Networks ,arxiv,2016<\/span><\/p>\n

[8] Petar Veli\u010dkovi\u0107,Guillem Cucurull,Arantxa Casanova.et al.: Graph Attention Networks ,arxiv,2017<\/span><\/p>\n

[9] Will Hamilton,Zhitao Ying,Jure Leskovec: Inductive Representation Learning on Large Graphs ,2017<\/span><\/p>\n

[10] Thomas N. Kipf,Max Welling: Variational Graph Auto-Encoders ,arxiv,2016<\/span><\/p>\n

[11] Keyulu Xu,Weihua Hu,Jure Leskovec.et al.: How Powerful are Graph Neural Networks? ,arxiv,2018<\/span><\/p>\n

[12] Rex Ying,Ruining He,Kaifeng Chen.et al.: Graph Convolutional Neural Networks for Web-Scale Recommender Systems ,arxiv,2018<\/span><\/p>\n

[13] Alvaro Sanchez-Gonzalez,Nicolas Heess,Jost Tobias Springenberg.et al.: Graph networks as learnable physics engines for inference and control ,arxiv,2018<\/span><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n


<\/p>\n

\uff08\u53c2\u8003\u6587\u732e\u53ef\u4e0a\u4e0b\u6ed1\u52a8\uff09<\/p>\n<\/section>\n<\/section>\n


<\/p>\n


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

\u4f5c\u8005\uff1a\u5f20\u6c5f<\/p>\n

\u7f16\u8f91\uff1a\u5f20\u723d<\/p>\n<\/section>\n<\/section>\n<\/blockquote>\n


<\/p>\n

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

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

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


<\/p>\n

\u8d85\u8d8a\u7b80\u5355\u89c4\u5219\u2014\u2014\u7528\u56fe\u795e\u7ecf\u7f51\u7edc\u5bf9\u590d\u6742\u7cfb\u7edf\u8fdb\u884c\u81ea\u52a8\u5efa\u6a21<\/span><\/strong><\/a>
<\/p>\n

\u56fe\u7f51\u7edc\u5982\u4f55\u52a9\u529b\u57ce\u5e02\u5927\u8111\uff1a\u8de8\u65f6\u7a7a\u5927\u5c3a\u5ea6\u7f51\u7ea6\u8f66\u6d41\u91cf\u9884\u6d4b<\/span><\/strong><\/a>
<\/p>\n

2020\u5e74\u7f51\u7edc\u79d1\u5b66\u76844\u4e2a\u524d\u6cbf\u65b9\u5411\uff1a\u4ece\u65f6\u5e8f\u7f51\u7edc\u5230\u9ad8\u9636\u7f51\u7edc<\/span><\/strong><\/a>
<\/p>\n

\u65af\u5766\u798fICLR2019\u56fe\u7f51\u7edc\u6700\u65b0\u8bba\u6587\uff1a\u56fe\u795e\u7ecf\u7f51\u7edc\u7684\u8868\u5f81\u80fd\u529b\u6709\u591a\u5f3a\uff1f<\/span><\/strong><\/a><\/p>\n

\u52a0\u5165\u96c6\u667a\uff0c\u4e00\u8d77\u590d\u6742\uff01<\/strong><\/span><\/a>
<\/p>\n


<\/p>\n

\n
\n
\n
\n
\n


<\/p>\n


<\/p>\n

\n
\n
\n
\n
\n
\n

\u96c6\u667a\u4ff1\u4e50\u90e8QQ\u7fa4\uff5c877391004<\/span><\/strong><\/p>\n

\u5546\u52a1\u5408\u4f5c\u53ca\u6295\u7a3f\u8f6c\u8f7d\uff5cswarma@swarma.org
<\/span><\/strong><\/p>\n

\n

\u25c6 <\/span>\u25c6 <\/span>\u25c6<\/span><\/span><\/strong><\/strong><\/h1>\n<\/section>\n

\u641c\u7d22\u516c\u4f17\u53f7\uff1a\u96c6\u667a\u4ff1\u4e50\u90e8<\/span><\/strong><\/span><\/p>\n


<\/p>\n

\u52a0\u5165\u201c\u6ca1\u6709\u56f4\u5899\u7684\u7814\u7a76\u6240\u201d<\/span><\/strong><\/span><\/p>\n

\n

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

\u8ba9\u82f9\u679c\u7838\u5f97\u66f4\u731b\u70c8\u4e9b\u5427\uff01<\/span><\/p>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n


<\/p>\n


<\/p>\n

\ud83d\udc47\u70b9\u51fb\u201c\u9605\u8bfb\u539f\u6587\u201d\uff0c\u4e86\u89e3\u66f4\u591a\u8bba\u6587\u4fe1\u606f<\/span><\/p>\n<\/p><\/div>\n","protected":false},"excerpt":{"rendered":"

\u5bfc\u8bed \u4ece\u77e5\u8bc6\u56fe\u8c31\u5230\u6982\u7387\u56fe\u6a21\u578b\uff0c\u4ece\u86cb\u767d\u8d28\u76f8\u4e92\u4f5c\u7528\u7f51\u7edc\u5230\u793e\u4ea4\u7f51\u7edc\uff0c\u4ece\u57fa\u672c\u7684\u903b\u8f91\u7ebf\u8def\u5230\u56e0\u7279\u7f51\uff0c\u56fe\u4e0e\u7f51\u7edc\u65e0\u5904\u4e0d\u5728\u3002\u7531\u4e8e\u4f20\u7edf\u673a\u5668\u5b66\u4e60\u65b9\u6cd5\u96be\u4ee5\u5904\u7406\u56fe\u6570\u636e\u4fe1\u606f\uff0c\u8fd1\u5e74\u6765\u5174\u8d77\u4e86\u56fe\u795e\u7ecf\u7f51\u7edc\u65b9\u6cd5\uff0c\u5728\u8bf8\u591a\u771f\u5b9e\u95ee\u9898\u7684\u5efa\u6a21\u548c\u89e3\u51b3\u4e0a\uff0c\u53d6\u5f97\u826f\u597d\u6548\u679c\u3002\u4f5c\u4e3a\u6b63\u706b\u70ed\u7684\u65b0\u9886\u57df\uff0c\u56fe\u7f51\u7edc\u65b9\u6cd5\u8fd8\u6ca1\u6709\u975e\u5e38\u6210\u719f\u7684\u6559\u6750\u6559\u7a0b\uff0c\u6211\u4eec\u6574\u7406\u4e86\u8fd9\u4efd\u7ed3\u5408\u591a\u95e8\u57fa\u7840…<\/p>\n","protected":false},"author":1,"featured_media":19553,"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\/19559"}],"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"}],"author":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=19559"}],"version-history":[{"count":0,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/19559\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/media\/19553"}],"wp:attachment":[{"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=19559"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=19559"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=19559"},{"taxonomy":"special","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fspecial&post=19559"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}