{"id":51587,"date":"2024-07-18T17:59:58","date_gmt":"2024-07-18T09:59:58","guid":{"rendered":"https:\/\/swarma.org\/?p=51587"},"modified":"2024-07-18T17:59:58","modified_gmt":"2024-07-18T09:59:58","slug":"%e6%8b%93%e6%89%91%e6%b7%b1%e5%ba%a6%e5%ad%a6%e4%b9%a0%e6%8d%95%e6%8d%89%e6%95%b0%e6%8d%ae%e7%9a%84%e9%ab%98%e9%98%b6%e5%85%b3%e7%b3%bb%ef%bc%9a%e4%bf%a1%e6%81%af%e4%bc%a0%e9%80%92%e6%8b%93%e6%89%91","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=51587","title":{"rendered":"\u62d3\u6251\u6df1\u5ea6\u5b66\u4e60\u6355\u6349\u6570\u636e\u7684\u9ad8\u9636\u5173\u7cfb\uff1a\u4fe1\u606f\u4f20\u9012\u62d3\u6251\u795e\u7ecf\u7f51\u7edc\u6982\u8ff0"},"content":{"rendered":"
\n
\n
\n
\n

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

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

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

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

\n

<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
\n
\u5728\u5f53\u4eca\u6570\u636e\u9a71\u52a8\u7684\u4e16\u754c\u4e2d\uff0c\u6211\u4eec\u9762\u4e34\u7740\u524d\u6240\u672a\u6709\u7684\u590d\u6742\u6027\u6311\u6218\u3002\u793e\u4ea4\u7f51\u7edc\u3001\u751f\u7269\u5206\u5b50\u7ed3\u6784\u3001\u57ce\u5e02\u4ea4\u901a\u7cfb\u7edf\u2014\u2014\u8fd9\u4e9b\u9886\u57df\u4ea7\u751f\u7684\u6570\u636e\u4e0d\u4ec5\u4f53\u91cf\u5e9e\u5927\uff0c\u5176\u5185\u5728\u5173\u7cfb\u4e5f\u9519\u7efc\u590d\u6742\uff0c\u4f20\u7edf\u7684\u673a\u5668\u5b66\u4e60\u65b9\u6cd5\u5c3d\u7ba1\u5728\u67d0\u4e9b\u60c5\u51b5\u4e0b\u8868\u73b0\u51fa\u8272\uff0c\u4f46\u5728\u5904\u7406\u5176\u4e2d\u7684\u9ad8\u9636\u5173\u7cfb\u65f6\u5374\u663e\u5f97\u529b\u4e0d\u4ece\u5fc3\u3002\u5728\u8fd9\u79cd\u80cc\u666f\u4e0b\uff0c\u62d3\u6251\u6df1\u5ea6\u5b66\u4e60\uff08Topological Deep Learning, TDL\uff09\u5e94\u8fd0\u800c\u751f\uff0c\u5b83\u5c06\u6df1\u5ea6\u5b66\u4e60\u7684\u5f3a\u5927\u80fd\u529b\u4e0e\u62d3\u6251\u5b66\u7684\u4e25\u8c28\u6027\u7ed3\u5408\u8d77\u6765\uff0c\u4e3a\u6211\u4eec\u63d0\u4f9b\u4e86\u4e00\u79cd\u5168\u65b0\u7684\u89c6\u89d2\u548c\u5de5\u5177\u3002<\/span><\/strong><\/span><\/strong><\/section>\n

<\/span><\/strong><\/span><\/strong><\/section>\n
\u96c6\u667a\u4ff1\u4e50\u90e8\u8054\u5408\u4e2d\u56fd\u4eba\u6c11\u5927\u5b66\u9ec4\u6587\u70b3\u526f\u6559\u6388\u3001\u4e0a\u6d77\u4ea4\u901a\u5927\u5b66\u738b\u5b87\u5149\u526f\u6559\u6388\u548c\u5357\u6d0b\u7406\u5de5\u5927\u5b66\u590f\u514b\u6797\u526f\u6559\u6388\u53d1\u8d77\u300c\u51e0\u4f55\u6df1\u5ea6\u5b66\u4e60<\/a>\u300d\u8bfb\u4e66\u4f1a\u3002\u4ece2024\u5e747\u670811\u65e5\u5f00\u59cb\uff0c\u6bcf\u5468\u56db19:00-21:00\u8fdb\u884c\uff0c\u6301\u7eed\u65f6\u95f4\u9884\u8ba1 8-10 \u5468\uff0c\u793e\u533a\u6210\u5458\u5c06\u4e00\u8d77\u7cfb\u7edf\u6027\u5730\u5b66\u4e60\u51e0\u4f55\u6df1\u5ea6\u5b66\u4e60\u76f8\u5173\u77e5\u8bc6\u3001\u6a21\u578b\u3001\u7b97\u6cd5\uff0c\u6df1\u5165\u68b3\u7406\u76f8\u5173\u6587\u732e\u3001\u6fc0\u53d1\u8de8\u5b66\u79d1\u7684\u5b66\u672f\u706b\u82b1\u3001\u5171\u540c\u6253\u9020\u56fd\u5185\u9996\u4e2a\u51e0\u4f55\u6df1\u5ea6\u5b66\u4e60\u793e\u533a\uff01\u6b22\u8fce\u52a0\u5165\u793e\u533a\u4e0e\u53d1\u8d77\u4eba\u8001\u5e08\u4e00\u8d77\u63a2\u7d22\uff01<\/span><\/strong><\/span><\/strong><\/section>\n
<\/strong><\/section>\n<\/section>\n
\n
<\/strong><\/section>\n
<\/strong><\/section>\n

<\/section>\n
<\/strong><\/section>\n
\u7814\u7a76\u9886\u57df\uff1a\u62d3\u6251\u6df1\u5ea6\u5b66\u4e60\uff0c\u9ad8\u9636\u6570\u636e\u8868\u5f81\uff0c\u5355\u7eaf\u590d\u5f62\uff0c\u80de\u5f62\u590d\u5f62\uff0c\u8d85\u56fe\uff0c\u6d88\u606f\u4f20\u9012<\/strong><\/strong><\/span><\/strong><\/section>\n
<\/strong><\/strong><\/strong><\/span><\/strong><\/section>\n<\/section>\n
\n
<\/strong><\/section>\n<\/section>\n
\n
<\/strong><\/strong><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
\n
\n
<\/svg><\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n<\/section>\n
\n
<\/section>\n<\/section>\n

\u738b\u82e5\u6668<\/span> <\/span>| \u7f16\u8bd1<\/span><\/strong><\/p>\n


<\/p>\n


<\/p>\n

\u300aArchitectures of Topological Deep Learning: A Survey of Message-Passing Topological Neural Net<\/span>works\u300b[1]\u901a\u8fc7<\/span>\u63d0\u4f9b\u4e00\u4e2a\u7edf\u4e00\u7684\u6846\u67b6\u548c\u76f4\u89c2\u7684\u6570\u5b66\u53ca\u56fe\u5f62\u7b26\u53f7\uff0c\u4e0d\u4ec5\u4e3a\u65b0\u5165\u95e8\u8005\u63d0\u4f9b\u4e86\u6613\u4e8e\u7406\u89e3\u7684TDL\u4ecb\u7ecd\uff0c\u8fd8\u5bf9\u73b0\u6709\u7684TNNs\u67b6\u6784\u8fdb\u884c\u4e86\u7cfb\u7edf\u7684\u6bd4\u8f83\u548c\u5168\u9762\u7684\u56de\u987e\u3002<\/span><\/p>\n


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


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

\n
\n
\n
\n
\n

<\/section>\n

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

1. \u4ecb\u7ecd<\/strong><\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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


<\/p>\n

\u5728\u51e0\u4f55\u6df1\u5ea6\u5b66\u4e60\u9886<\/span>\u57df[2]\uff0c\u56fe\u795e\u7ecf\u7f51\u7edc<\/span>\uff08Graph Neural Network, GNN\uff09<\/span>[3]\u5728\u5904\u7406\u5173\u7cfb\u6570\u636e\u65b9\u9762\u53d6\u5f97\u4e86\u663e\u8457\u6210\u5c31\u3002\u7136\u800c\uff0c\u5f53\u7814\u7a76\u5bf9\u8c61\u6d89\u53ca\u66f4\u590d\u6742\u7684\u5173\u7cfb\u7ed3\u6784\u548c\u591a\u4e2a\u4e2a\u4f53\u95f4\u7684\u76f8\u4e92\u4f5c\u7528\u65f6\uff0c\u56fe\u7684\u8868\u793a\u80fd\u529b\u4f1a\u9047\u5230\u5176\u7ed3\u6784\u672c\u8eab\u7684\u9650\u5236\u3002TDL [4]\u91c7\u7528\u4e00\u79cd\u66f4\u901a\u7528\u7684\u62bd\u8c61\u65b9\u6cd5\u6765\u5904\u7406\u5177\u6709\u9ad8\u9636\u5173\u7cfb\u7ed3\u6784\u7684\u6570\u636e\uff0c\u5176\u6838\u5fc3\u5728\u4e8e\u6d88\u606f\u4f20\u9012\u62d3\u6251\u795e\u7ecf\u7f51\u7edc<\/strong><\/span>\uff08Topological Neural Network, TNN\uff09<\/span>\uff0c\u5b83\u4eec\u901a\u8fc7\u7cbe\u5fc3\u8bbe\u8ba1\u7684\u6d88\u606f\u4f20\u9012\u673a\u5236\uff0c\u80fd\u591f\u6355\u6349\u548c\u5b66\u4e60\u6570\u636e\u4e2d\u7684\u9ad8\u9636\u5173\u7cfb\u3002\u4ece\u793e\u4ea4\u7f51\u7edc\u4e2d\u7684\u7fa4\u4f53\u52a8\u529b\u5b66\u5230\u86cb\u767d\u8d28\u7ed3\u6784\u7684\u590d\u6742\u76f8\u4e92\u4f5c\u7528\uff0cTDL \u5c55\u73b0\u51fa\u4e86\u5904\u7406\u8fd9\u4e9b\u590d\u6742\u7cfb\u7edf\u7684\u5de8\u5927\u6f5c\u529b\u3002<\/span><\/p>\n


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


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

\n
\n
\n
\n
\n

<\/section>\n

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

2. \u62d3\u6251\u6df1\u5ea6\u5b66\u4e60\u7684\u6570\u636e\u57df<\/strong><\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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


<\/p>\n

<\/p>\n

\u56fe 1 \u62d3\u6251\u795e\u7ecf\u7f51\u8def<\/span><\/p>\n


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

\u590d\u6742\u7cfb\u7edf\u7684\u6570\u636e\u662f\u5b9a\u4e49\u5728\u6570\u636e\u57df\u4e0a\u7684\u7279\u5f81[4]\uff0c\u8fd9\u4e9b\u7279\u5f81\u7ecf\u8fc7\u9884\u5904\u7406\u540e\u8f6c\u5316\u4e3a\u8ba1\u7b97\u57df\uff0c\u8ba1\u7b97\u57df\u7f16\u7801\u4e86\u7cfb\u7edf\u7ec4\u4ef6\u4e4b\u95f4\u7684\u4ea4\u4e92\u53ca\u5176\u90bb\u57df\u3002TNN \u7684\u5404\u5c42\u901a\u8fc7\u6d88\u606f\u4f20\u9012\u9010\u6b65\u66f4\u65b0\u8fd9\u4e9b\u7279\u5f81\uff0c\u5e76\u751f\u6210\u8f93\u51fa\uff0c\u4f8b\u5982\u5206\u7c7b\u4e2d\u7684\u7c7b\u522b\u6807\u7b7e\u6216\u56de\u5f52\u4e2d\u7684\u5b9a\u91cf\u503c\u3002\u6bcf\u5c42\u7684\u8f93\u51fa\u4ee3\u8868\u4ece\u8f93\u5165\u6570\u636e\u4e2d\u63d0\u53d6\u7684\u65b0\u77e5\u8bc6\u3002<\/span><\/p>\n


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

\u5982\u56fe2\u6240\u793a\uff0c\u62d3\u6251\u6df1\u5ea6\u5b66\u4e60\u7684\u6570\u636e\u57df\u5305\u62ec\u5355\u7eaf\u590d\u5f62\u3001\u7ec6\u80de\u590d\u5408\u4f53\u3001\u8d85\u56fe\u548c\u7ec4\u5408\u590d\u5408\u4f53\u7b49<\/strong>\u3002\u8fd9\u4e9b\u57df\u662f\u5bf9\u4f20\u7edf\u79bb\u6563\u6570\u636e\u57df<\/span>\uff08\u5982\u96c6\u5408\u3001\u56fe\uff09<\/span>\u7684\u6269\u5c55\uff0c\u80fd\u591f\u8868\u8fbe\u66f4\u4e30\u5bcc\u7684\u5173\u7cfb\u7ed3\u6784\u3002\u4f8b\u5982\uff0c\u5355\u7eaf\u590d\u5f62\u5141\u8bb8\u6211\u4eec\u901a\u8fc7\u591a\u7ef4\u5355\u5143<\/span>\uff08\u5982\u4e09\u89d2\u5f62\u3001\u56db\u9762\u4f53\uff09<\/span>\u6765\u8868\u793a\u5c42\u6b21\u5316\u7684\u90e8\u5206-\u6574\u4f53\u5173\u7cfb\u3002<\/span><\/p>\n


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

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

\u56fe 2 \u5404\u7c7b\u6570\u636e\u57df<\/span><\/p>\n


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


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

\n
\n
\n
\n
\n

<\/section>\n

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

3. \u90bb\u5c45\u7ed3\u6784<\/strong><\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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


<\/p>\n

\u5728\u62d3\u6251\u6df1\u5ea6\u5b66\u4e60\u4e2d\uff0c\u6bcf\u4e2a\u5355\u5143\u7684\u7279\u5f81\u66f4\u65b0\u4f9d\u8d56\u4e8e\u5176\u90bb\u5c45\u5355\u5143\u7684\u4fe1\u606f\u3002<\/span>\u90bb\u5c45\u7ed3\u6784\u5b9a\u4e49\u4e86\u4e0d\u540c\u5355\u5143\u95f4\u7684\u62d3\u6251\u90bb\u8fd1\u6027\uff0c\u5305\u62ec\u8fb9\u754c\u90bb\u57df\u3001\u5171\u8fb9\u754c\u90bb\u57df\u3001\u4e0b\u90bb\u57df\u548c\u4e0a\u90bb\u57df\u3002<\/span>\u8fd9\u4e9b\u7ed3\u6784\u901a\u8fc7\u8fb9\u754c\u5173\u7cfb\u77e9\u9635\u6765\u8868\u8fbe\uff0c\u5f62\u6210\u4e86\u62d3\u6251\u795e\u7ecf\u7f51\u7edc\u7684\u57fa\u7840\u3002<\/span><\/p>\n


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

<\/p>\n

\u56fe 3 \u90bb\u5c45\u7ed3\u6784<\/span><\/p>\n


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


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

\n
\n
\n
\n
\n

<\/section>\n

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

4. \u6d88\u606f\u4f20\u9012\u7684\u57fa\u672c\u6b65\u9aa4<\/strong><\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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


<\/p>\n

\u62d3\u6251\u6df1\u5ea6\u5b66\u4e60\u7684\u6838\u5fc3\u662f\u6d88\u606f\u4f20\u9012\uff0c\u8be5\u8fc7\u7a0b\u53ef\u4ee5\u5206\u4e3a\u4ee5\u4e0b\u56db\u4e2a\u6b65\u9aa4\uff1a\u6d88\u606f\u751f\u6210\u3001\u90bb\u57df\u805a\u5408\u3001\u8de8\u90bb\u57df\u805a\u5408\u548c\u7279\u5f81\u66f4\u65b0<\/span><\/strong>\u3002\u5177\u4f53\u7684\uff0c\u6d88\u606f\u751f\u6210\u6307\u5404\u4e2a\u5355\u5143\u5c06\u5176\u7279\u5f81\u5206\u4eab\u7ed9\u5404\u90bb\u5c45\u7ed3\u6784\u5355\u5143\uff1b\u90bb\u57df\u805a\u5408\u6307\u6c47\u603b\u6765\u81ea\u540c\u4e00\u90bb\u57df\u7684\u4fe1\u606f\uff1b\u8de8\u90bb\u57df\u805a\u5408\u6307\u6c47\u603b\u4e0d\u540c\u90bb\u57df\u7684\u4fe1\u606f\uff1b\u7279\u5f81\u66f4\u65b0\u5219\u6307\u6839\u636e\u6c47\u603b\u5f97\u5230\u7684\u4fe1\u606f\u548c\u7f51\u7edc\u53c2\u6570\u66f4\u65b0\u5355\u5143\u7279\u5f81\u3002<\/span><\/p>\n


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

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

\u56fe 4 \u6d88\u606f\u4f20\u9012\u7684\u57fa\u672c\u6b65\u9aa4<\/span><\/p>\n


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


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

\n
\n
\n
\n
\n

<\/section>\n

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

5. \u6d88\u606f\u4f20\u9012\u51fd\u6570\u7684\u7c7b\u578b<\/strong><\/span><\/strong><\/strong><\/p>\n<\/section>\n

\n

<\/section>\n

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


<\/p>\n

\u5728\u62d3\u6251\u6df1\u5ea6\u5b66\u4e60\u4e2d\uff0c\u6d88\u606f\u4f20\u9012\u51fd\u6570\u5b9a\u4e49\u4e86\u5982\u4f55\u4ece\u90bb\u5c45\u5355\u5143\u63a5\u6536\u4fe1\u606f\u5e76\u5c06\u5176\u4e0e\u5f53\u524d\u5355\u5143\u7684\u7279\u5f81\u76f8\u7ed3\u5408\uff0c\u53ef\u6839\u636e\u5176\u590d\u6742\u6027\u5206\u4e3a\u5982\u4e0b\u4e09\u79cd\u7c7b<\/span>\u578b[5]<\/span>\uff1a<\/span><\/section>\n