{"id":48781,"date":"2024-03-07T20:24:09","date_gmt":"2024-03-07T12:24:09","guid":{"rendered":"https:\/\/swarma.org\/?p=48781"},"modified":"2024-03-07T20:24:09","modified_gmt":"2024-03-07T12:24:09","slug":"ai4science%e7%9a%84%e5%9f%ba%e7%9f%b3%ef%bc%9a%e5%87%a0%e4%bd%95%e5%9b%be%e7%a5%9e%e7%bb%8f%e7%bd%91%e7%bb%9c%ef%bc%8c%e6%9c%80%e5%85%a8%e7%bb%bc%e8%bf%b0%e6%9d%a5%e4%ba%86%ef%bc%81","status":"publish","type":"post","link":"https:\/\/swarma.org\/?p=48781","title":{"rendered":"AI4Science\u7684\u57fa\u77f3\uff1a\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\uff0c\u6700\u5168\u7efc\u8ff0\u6765\u4e86\uff01"},"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
\u8fd1\u65e5\uff0c\u4eba\u5927\u9ad8\u74f4\u8054\u5408\u817e\u8baf AI Lab\u3001\u6e05\u534e\u3001\u65af\u5766\u798f\u7b49\u673a\u6784\u53d1\u5e03\u7efc\u8ff0\u8bba\u6587\uff1a\u300aA Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications\u300b\u3002\u8be5\u7efc\u8ff0\u5728\u7b80\u8981\u4ecb\u7ecd\u7fa4\u8bba\u3001\u5bf9\u79f0\u6027\u7b49\u7406\u8bba\u77e5\u8bc6\u7684\u57fa\u7840\u4e0a\uff0c\u4ece\u6570\u636e\u7ed3\u6784\u3001\u6a21\u578b\u5230\u4f17\u591a\u79d1\u5b66\u5e94\u7528\uff0c\u5bf9\u76f8\u5173\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u6587\u732e\u8fdb\u884c\u4e86\u7cfb\u7edf\u7684\u68b3\u7406\u3002<\/span><\/strong><\/section>\n

<\/span><\/strong><\/section>\n
\u5173\u952e\u8bcd\uff1a\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\uff0cAI for Science\uff0c\u56fe\u57fa\u7840\u6a21\u578b\uff0c\u5927\u8bed\u8a00\u6a21\u578b<\/span><\/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
\n
 XS<\/span> | \u7f16\u8f91<\/span><\/strong><\/section>\n
ScienceAI<\/span> <\/span>| <\/span><\/strong><\/span><\/strong>\u6765\u6e90<\/span><\/strong><\/section>\n<\/section>\n

<\/section>\n

<\/span><\/section>\n
2023 \u5e74 11 \u6708\uff0cNature \u8fde\u7eed\u520a\u767b\u4e86\u4e24\u7bc7\u91cd\u5927\u6210\u679c\uff1a\u86cb\u767d\u8d28\u751f\u6210\u65b9\u6cd5 Chroma \u548c\u6676\u4f53\u6750\u6599\u8bbe\u8ba1\u65b9\u6cd5 GNoME\uff0c\u5747\u4f7f\u7528\u4e86\u56fe\u795e\u7ecf\u7f51\u7edc\u4f5c\u4e3a\u79d1\u5b66\u6570\u636e\u7684\u8868\u793a\u5de5\u5177\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u5b9e\u9645\u4e0a\uff0c\u56fe\u795e\u7ecf\u7f51\u7edc\uff0c\u7279\u522b\u662f\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\uff0c\u4e00\u76f4\u662f\u79d1\u5b66\u667a\u80fd<\/span>\uff08AI for Science\uff09<\/span>\u7814\u7a76\u7684\u91cd\u8981\u5de5\u5177\u3002\u8fd9\u662f\u56e0\u4e3a\uff0c\u79d1\u5b66\u9886\u57df\u4e2d\u7684\u7c92\u5b50\u3001\u5206\u5b50\u3001\u86cb\u767d\u8d28\u3001\u6676\u4f53\u7b49\u7269\u7406\u7cfb\u7edf\u5747\u53ef\u88ab\u5efa\u6a21\u6210\u4e00\u79cd\u7279\u6b8a\u7684\u6570\u636e\u7ed3\u6784\u2014\u2014\u51e0\u4f55\u56fe\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u4e0e\u4e00\u822c\u7684\u62d3\u6251\u56fe\u4e0d\u540c\uff0c\u4e3a\u4e86\u66f4\u597d\u63cf\u8ff0\u7269\u7406\u7cfb\u7edf\uff0c\u51e0\u4f55\u56fe\u52a0\u5165\u4e86\u4e0d\u53ef\u6216\u7f3a\u7684\u7a7a\u95f4\u4fe1\u606f\uff0c\u9700\u8981\u6ee1\u8db3\u5e73\u79fb\u3001\u65cb\u8f6c\u548c\u7ffb\u8f6c\u7684\u7269\u7406\u5bf9\u79f0\u6027\u3002\u9274\u4e8e\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u5bf9\u4e8e\u7269\u7406\u7cfb\u7edf\u5efa\u6a21\u7684\u4f18\u8d8a\u6027\uff0c\u8fd1\u5e74\u6765\u5404\u7c7b\u65b9\u6cd5\u5c42\u51fa\u4e0d\u7a77\uff0c\u8bba\u6587\u6570\u91cf\u6301\u7eed\u589e\u957f\u3002<\/span><\/o:p><\/section>\n

<\/span><\/section>\n
\u8fd1\u65e5\uff0c\u4eba\u5927\u9ad8\u74f4\u8054\u5408\u817e\u8baf AI Lab\u3001\u6e05\u534e\u3001\u65af\u5766\u798f\u7b49\u673a\u6784\u53d1\u5e03\u7efc\u8ff0\u8bba\u6587\uff1a\u300aA Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications\u300b\u3002\u8be5\u7efc\u8ff0\u5728\u7b80\u8981\u4ecb\u7ecd\u7fa4\u8bba\u3001\u5bf9\u79f0\u6027\u7b49\u7406\u8bba\u77e5\u8bc6\u7684\u57fa\u7840\u4e0a\uff0c\u4ece\u6570\u636e\u7ed3\u6784\u3001\u6a21\u578b\u5230\u4f17\u591a\u79d1\u5b66\u5e94\u7528\uff0c\u5bf9\u76f8\u5173\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u6587\u732e\u8fdb\u884c\u4e86\u7cfb\u7edf\u7684\u68b3\u7406\u3002<\/span><\/section>\n

<\/span><\/section>\n
<\/section>\n
\n
\n
\n
\u8bba\u6587\u94fe\u63a5\uff1ahttps:\/\/arxiv.org\/abs\/2403.00485<\/span><\/o:p><\/section>\n
GitHub\u94fe\u63a5\uff1ahttps:\/\/github.com\/RUC-GLAD\/GGNN4Science<\/span><\/section>\n<\/section>\n<\/section>\n<\/blockquote>\n

<\/span><\/section>\n
\u5728\u8fd9\u7bc7\u7efc\u8ff0\u4e2d\uff0c\u4f5c\u8005\u8c03\u7814\u4e86 300 \u591a\u7bc7\u53c2\u8003\u6587\u732e\uff0c\u5f52\u7eb3\u51fa 3 \u79cd\u4e0d\u540c\u7684\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u6a21\u578b\uff0c\u4ecb\u7ecd\u4e86\u9762\u5411\u7c92\u5b50\u3001\u5206\u5b50\u3001\u86cb\u767d\u8d28\u7b49\u591a\u79cd\u79d1\u5b66\u6570\u636e\u4e0a\u5171 23 \u79cd\u4e0d\u540c\u4efb\u52a1\u7684\u76f8\u5173\u65b9\u6cd5\uff0c\u6536\u96c6\u4e86 50 \u591a\u4e2a\u76f8\u5173\u8bc4\u6d4b\u6570\u636e\u96c6\u3002\u6700\u540e\uff0c\u7efc\u8ff0\u5c55\u671b\u4e86\u672a\u6765\u7684\u7814\u7a76\u65b9\u5411\uff0c\u5305\u62ec\u51e0\u4f55\u56fe\u57fa\u7840\u6a21\u578b\u3001\u4e0e\u5927\u8bed\u8a00\u6a21\u578b\u7ed3\u5408\u7b49\u3002<\/span><\/o:p><\/section>\n

<\/span><\/section>\n
\u4e0b\u9762\u662f\u5404\u7ae0\u8282\u7b80\u8981\u4ecb\u7ecd\u3002<\/span><\/o:p><\/section>\n

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

<\/section>\n

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

\n
\n
\n
\n
\n

<\/section>\n

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

\u51e0\u4f55\u56fe\u6570\u636e\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

\u51e0\u4f55\u56fe\u7531\u90bb\u63a5\u77e9\u9635\u3001\u8282\u70b9\u7279\u5f81\u3001\u8282\u70b9\u51e0\u4f55\u4fe1\u606f<\/span>\uff08\u4f8b\u5982\u5750\u6807\uff09<\/span>\u6784\u6210\u3002\u5728\u6b27\u6c0f\u7a7a\u95f4\u4e2d\uff0c\u51e0\u4f55\u56fe\u901a\u5e38\u8868\u73b0\u51fa\u5e73\u79fb\u3001\u65cb\u8f6c\u548c\u53cd\u5c04\u7684\u7269\u7406\u5bf9\u79f0\u6027\uff0c\u4e00\u822c\u4f7f\u7528\u7fa4\u6765\u523b\u753b\u8fd9\u4e9b\u53d8\u6362\uff0c\u5305\u62ec\u6b27\u5f0f\u7fa4\u3001\u5e73\u79fb\u7fa4\u3001\u6b63\u4ea4\u7fa4\u3001\u7f6e\u6362\u7fa4\u7b49\u7b49\u3002\u76f4\u89c2\u4e0a\u770b\uff0c\u53ef\u4ee5\u7406\u89e3\u4e3a\u7f6e\u6362\u3001\u5e73\u79fb\u3001\u65cb\u8f6c\u3001\u7ffb\u8f6c\u56db\u79cd\u64cd\u4f5c\u6309\u4e00\u5b9a\u987a\u5e8f\u7684\u590d\u5408\u3002<\/span><\/o:p><\/section>\n

<\/span><\/section>\n
\u5bf9\u4e8e\u4f17\u591a AI for Science \u9886\u57df\uff0c\u51e0\u4f55\u56fe\u662f\u4e00\u79cd\u6709\u529b\u4e14\u901a\u7528\u7684\u8868\u793a\u65b9\u6cd5\uff0c\u5176\u53ef\u4ee5\u7528\u4e8e\u8868\u793a\u4f17\u591a\u7269\u7406\u7cfb\u7edf\uff0c\u5305\u62ec\u5c0f\u5206\u5b50\u3001\u86cb\u767d\u8d28\u3001\u6676\u4f53\u3001\u7269\u7406\u70b9\u4e91\u7b49\u3002<\/span><\/o:p><\/section>\n

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

\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u6a21\u578b<\/span><\/o:p><\/h2>\n

<\/span><\/section>\n
\u6839\u636e\u5b9e\u9645\u95ee\u9898\u4e2d\u7684\u6c42\u89e3\u76ee\u6807\u5bf9\u4e8e\u5bf9\u79f0\u6027\u7684\u8981\u6c42\uff0c\u672c\u6587\u5c06\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u5206\u4e3a\u4e09\u7c7b\uff1a\u4e0d\u53d8<\/span>\uff08invariant\uff09<\/span>\u6a21\u578b\u3001\u7b49\u53d8<\/span>\uff08equivariant\uff09<\/span>\u6a21\u578b\u3001\u4ee5\u53ca\u53d7 Transformer \u67b6\u6784\u542f\u53d1\u7684 Geometric Graph Transformer\uff0c\u5176\u4e2d\u7b49\u53d8\u6a21\u578b\u53c8\u7ec6\u5206\u4e3a\u6807\u91cf\u5316\u65b9\u6cd5\u6a21\u578b<\/span>\uff08Scalarization-Based Model\uff09<\/span>\u4e0e\u57fa\u4e8e\u7403\u9762\u8c03\u548c\u7684\u9ad8\u9636\u53ef\u64cd\u63a7\u6a21\u578b<\/span>\uff08High-Degree Steerable Model\uff09<\/span>\u3002\u6309\u7167\u4e0a\u8ff0\u89c4\u5219\uff0c\u6587\u7ae0\u6536\u96c6\u5e76\u5f52\u7c7b\u4e86\u8fd1\u5e74\u6765\u77e5\u540d\u7684\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u6a21\u578b\u3002<\/span><\/o:p><\/section>\n

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

<\/span><\/section>\n
\u8fd9\u91cc\u6211\u4eec\u901a\u8fc7\u5404\u4e2a\u5206\u652f\u7684\u4ee3\u8868\u6027\u5de5\u4f5c\u7b80\u8981\u4ecb\u7ecd\u4e0d\u53d8\u6a21\u578b<\/span>\uff08SchNet[1]\uff09<\/span>\u3001\u6807\u91cf\u5316\u65b9\u6cd5\u6a21\u578b<\/span>\uff08EGNN[2]\uff09<\/span>\u3001\u9ad8\u9636\u53ef\u64cd\u63a7\u6a21\u578b<\/span>\uff08TFN[3]\uff09<\/span>\u7684\u5173\u8054\u4e0e\u533a\u522b\u3002\u53ef\u4ee5\u53d1\u73b0\u4e09\u8005\u5747\u662f\u91c7\u7528\u4e86\u6d88\u606f\u4f20\u9012\u673a\u5236\uff0c\u53ea\u662f\u8eab\u4e3a\u7b49\u53d8\u6a21\u578b\u7684\u540e\u4e24\u8005\u989d\u5916\u5f15\u5165\u4e86\u4e00\u6b21\u51e0\u4f55\u6d88\u606f\u4f20\u9012\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u4e0d\u53d8\u6a21\u578b\u4e3b\u8981\u5229\u7528\u8282\u70b9\u672c\u8eab\u7684\u7279\u5f81<\/span>\uff08\u5982\u539f\u5b50\u79cd\u7c7b\u3001\u8d28\u91cf\u3001\u5e26\u7535\u91cf\u7b49\uff09<\/span>\u4e0e\u539f\u5b50\u95f4\u7684\u4e0d\u53d8\u7279\u5f81<\/span>\uff08\u5982\u8ddd\u79bb\u3001\u89d2\u5ea6[4]\u3001\u4e8c\u9762\u89d2[5]\uff09<\/span>\u7b49\u8fdb\u884c\u6d88\u606f\u8ba1\u7b97\uff0c\u968f\u540e\u8fdb\u884c\u4f20\u64ad\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u800c\u5728\u6b64\u4e4b\u4e0a\uff0c\u6807\u91cf\u5316\u65b9\u6cd5\u989d\u5916\u901a\u8fc7\u8282\u70b9\u95f4\u5750\u6807\u5dee\u5f15\u5165\u4e86\u51e0\u4f55\u4fe1\u606f\uff0c\u5e76\u5c06\u4e0d\u53d8\u4fe1\u606f\u4f5c\u4e3a\u51e0\u4f55\u4fe1\u606f\u7684\u6743\u91cd\u8fdb\u884c\u7ebf\u6027\u7ec4\u5408\uff0c\u5b9e\u73b0\u4e86\u7b49\u53d8\u6027\u7684\u5f15\u5165\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u9ad8\u9636\u53ef\u64cd\u63a7\u6a21\u578b\u5219\u662f\u4f7f\u7528\u4e86\u9ad8\u9636\u7684\u7403\u9762\u8c03\u548c<\/span>\uff08Spherical Harmonics\uff09<\/span>\u4e0e Wigner-D \u77e9\u9635\u8868\u5f81\u7cfb\u7edf\u7684\u51e0\u4f55\u4fe1\u606f\uff0c\u8fd9\u7c7b\u65b9\u6cd5\u901a\u8fc7\u91cf\u5b50\u529b\u5b66\u4e2d\u7684 Clebsch\u2013Gordan \u7cfb\u6570\u64cd\u63a7\u4e0d\u53ef\u7ea6\u8868\u793a\u7684\u9636\u6570\uff0c\u4ece\u800c\u5b9e\u73b0\u51e0\u4f55\u6d88\u606f\u4f20\u9012\u8fc7\u7a0b\u3002<\/span><\/o:p><\/section>\n

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

<\/span><\/section>\n
\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u901a\u8fc7\u8fd9\u7c7b\u8bbe\u8ba1\u4fdd\u8bc1\u7684\u5bf9\u79f0\u6027\uff0c\u51c6\u786e\u7387\u6709\u5927\u5e45\u63d0\u5347\uff0c\u5e76\u4e14\u5728\u751f\u6210\u4efb\u52a1\u4e2d\u4e5f\u5927\u653e\u5f02\u5f69\u3002<\/span><\/section>\n

<\/section>\n
\u4e0b\u56fe\u662f\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u4f20\u7edf\u6a21\u578b\u5728 QM9\u3001PDBBind\u3001SabDab \u4e09\u4e2a\u6570\u636e\u96c6\u4e0a\u8fdb\u884c\u5206\u5b50\u6027\u8d28\u9884\u6d4b\u3001\u86cb\u767d\u8d28-\u914d\u4f53\u5bf9\u63a5\u548c\u6297\u4f53\u8bbe\u8ba1<\/span>\uff08\u751f\u6210\uff09<\/span>\u4e09\u4e2a\u4efb\u52a1\u4e2d\u7684\u7ed3\u679c\uff0c\u53ef\u4ee5\u660e\u663e\u770b\u51fa\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u7684\u4f18\u52bf\u3002<\/span><\/o:p><\/section>\n

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


<\/p>\n


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

\n
\n
\n
\n
\n

<\/section>\n

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

\u79d1\u5b66\u5e94\u7528<\/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\u79d1\u5b66\u5e94\u7528\u65b9\u9762\uff0c\u7efc\u8ff0\u6db5\u76d6\u4e86\u7269\u7406<\/span>\uff08\u7c92\u5b50\uff09<\/span>\u3001\u751f\u7269\u5316\u5b66<\/span>\uff08\u5c0f\u5206\u5b50\u3001\u86cb\u767d\u8d28\uff09<\/span>\u4ee5\u53ca\u5176\u5b83\u5982\u6676\u4f53\u7b49\u591a\u4e2a\u5e94\u7528\u573a\u666f\uff0c\u4efb\u52a1\u5b9a\u4e49\u4e0e\u6240\u9700\u4fdd\u8bc1\u5bf9\u79f0\u6027\u79cd\u7c7b\u51fa\u53d1\uff0c\u5206\u522b\u4ecb\u7ecd\u4e86\u5404\u4e2a\u4efb\u52a1\u4e2d\u7684\u5e38\u7528\u6570\u636e\u96c6\u4e0e\u8be5\u7c7b\u4efb\u52a1\u4e2d\u7684\u7ecf\u5178\u6a21\u578b\u8bbe\u8ba1\u601d\u8def\u3002<\/span><\/o:p><\/section>\n

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

<\/section>\n
\u4e0a\u8868\u5c55\u793a\u4e86\u5404\u4e2a\u9886\u57df\u7684\u5e38\u89c1\u4efb\u52a1\u4e0e\u7ecf\u5178\u6a21\u578b\uff0c\u5176\u4e2d\uff0c\u6309\u7167\u5355\u4e00\u5b9e\u4f8b\u4e0e\u591a\u5b9e\u4f8b<\/span>\uff08\u5982\u5316\u5b66\u53cd\u5e94\uff0c\u9700\u8981\u591a\u5206\u5b50\u5171\u540c\u53c2\u4e0e\uff09<\/span>\uff0c\u6587\u7ae0\u5355\u72ec\u533a\u5206\u4e86\u5c0f\u5206\u5b50-\u5c0f\u5206\u5b50\u3001\u5c0f\u5206\u5b50-\u86cb\u767d\u8d28\u3001\u86cb\u767d\u8d28-\u86cb\u767d\u8d28\u4e09\u4e2a\u9886\u57df\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u4e3a\u4e86\u66f4\u597d\u5730\u65b9\u4fbf\u9886\u57df\u5185\u8fdb\u884c\u6a21\u578b\u8bbe\u8ba1\u4e0e\u5b9e\u9a8c\u5f00\u5c55\uff0c\u6587\u7ae0\u6309\u7167\u5355\u4e00\u5b9e\u4f8b\u4e0e\u591a\u5b9e\u4f8b\u7edf\u8ba1\u4e86\u4e24\u7c7b\u4efb\u52a1\u7684\u5e38\u7528\u6570\u636e\u96c6\u4e0e\u57fa\u51c6<\/span>\uff08benchmark\uff09<\/span>\uff0c\u5e76\u8bb0\u5f55\u4e86\u4e0d\u540c\u6570\u636e\u96c6\u7684\u6837\u672c\u91cf\u4e0e\u4efb\u52a1\u79cd\u7c7b\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u4e0b\u8868\u6574\u7406\u4e86\u5e38\u89c1\u7684\u5355\u5b9e\u4f8b\u4efb\u52a1\u6570\u636e\u96c6\u3002<\/span><\/o:p><\/section>\n

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

<\/section>\n
\u4e0b\u8868\u6574\u7406\u4e86\u5e38\u89c1\u7684\u591a\u5b9e\u4f8b\u4efb\u52a1\u6570\u636e\u96c6\u3002<\/span><\/o:p><\/section>\n

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

<\/section>\n


<\/p>\n

\n
\n
\n
\n
\n

<\/section>\n

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

\u672a\u6765\u5c55\u671b<\/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

\u6587\u7ae0\u5c31\u51e0\u4e2a\u65b9\u9762\u8fdb\u884c\u4e86\u521d\u6b65\u7684\u5c55\u671b\uff0c\u5e0c\u671b\u80fd\u4f5c\u629b\u7816\u5f15\u7389\u4e4b\u7528\uff1a<\/span><\/o:p><\/section>\n

<\/span><\/section>\n
1. \u51e0\u4f55\u56fe\u57fa\u7840\u6a21\u578b<\/span><\/strong><\/section>\n

<\/span><\/strong><\/section>\n
\u5728\u5404\u79cd\u4efb\u52a1\u548c\u9886\u57df\u4e2d\u91c7\u7528\u7edf\u4e00\u7684\u57fa\u7840\u6a21\u578b\u7684\u4f18\u8d8a\u6027\u5728GPT\u7cfb\u5217\u6a21\u578b\u7684\u663e\u8457\u8fdb\u6b65\u4e2d\u5df2\u7ecf\u4f53\u73b0\u5f97\u6dcb\u6f13\u5c3d\u81f4\u3002\u5982\u4f55\u5728\u4efb\u52a1\u7a7a\u95f4\u3001\u6570\u636e\u7a7a\u95f4\u3001\u6a21\u578b\u7a7a\u95f4\u8fdb\u884c\u5408\u7406\u7684\u8bbe\u8ba1\uff0c\u4ece\u800c\u5c06\u8fd9\u79cd\u601d\u8def\u5f15\u5165\u5230\u9488\u5bf9\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u7684\u8bbe\u8ba1\u4e0a\u4ecd\u662f\u4e00\u4e2a\u6709\u8da3\u7684\u5f00\u653e\u95ee\u9898\u3002<\/span><\/o:p><\/section>\n

<\/section>\n
2. \u6a21\u578b\u8bad\u7ec3\u4e0e\u73b0\u5b9e\u4e16\u754c\u5b9e\u9a8c\u9a8c\u8bc1\u7684\u9ad8\u6548\u5faa\u73af<\/span><\/strong><\/section>\n

<\/span><\/strong><\/section>\n
\u79d1\u5b66\u6570\u636e\u7684\u83b7\u53d6\u662f\u6602\u8d35\u4e14\u8017\u65f6\u7684\uff0c\u800c\u4ec5\u4ec5\u5728\u72ec\u7acb\u6570\u636e\u96c6\u4e0a\u8bc4\u4f30\u7684\u6a21\u578b\u4e0d\u80fd\u76f4\u63a5\u53cd\u5e94\u6765\u81ea\u73b0\u5b9e\u4e16\u754c\u7684\u53cd\u9988\u3002\u5982\u4f55\u7c7b\u4f3c\u4e8eGNoME<\/span>\uff08\u96c6\u6210\u4e86\u4e00\u4e2a\u7aef\u5230\u7aef\u7684\u6d41\u6c34\u7ebf\uff0c\u5305\u62ec\u56fe\u7f51\u7edc\u8bad\u7ec3\u3001\u5bc6\u5ea6\u6cdb\u51fd\u7406\u8bba\u8ba1\u7b97\u548c\u7528\u4e8e\u6750\u6599\u53d1\u73b0\u548c\u5408\u6210\u7684\u81ea\u52a8\u5b9e\u9a8c\u5ba4\uff09<\/span>\u5b9e\u73b0\u9ad8\u6548\u7684\u6a21\u578b-\u73b0\u5b9e\u5faa\u73af\u8fed\u4ee3\u7684\u5b9e\u9a8c\u8303\u5f0f\u7684\u91cd\u8981\u6027\u5c06\u4f1a\u4e0e\u65e5\u4ff1\u589e\u3002<\/span><\/o:p><\/section>\n

<\/span><\/section>\n
3. \u4e0e\u5927\u578b\u8bed\u8a00\u6a21\u578b\uff08LLMs\uff09\u7684\u878d\u5408<\/span><\/strong><\/section>\n

<\/span><\/strong><\/section>\n
\u5927\u578b\u8bed\u8a00\u6a21\u578b<\/span>\uff08LLMs\uff09<\/span>\u5df2\u88ab\u5e7f\u6cdb\u8bc1\u660e\u5177\u6709\u4e30\u5bcc\u7684\u77e5\u8bc6\uff0c\u6db5\u76d6\u4e86\u5404\u4e2a\u9886\u57df\u3002\u867d\u7136\u5df2\u7ecf\u6709\u4e00\u4e9b\u5de5\u4f5c\u5229\u7528 LLMs \u8fdb\u884c\u67d0\u4e9b\u4efb\u52a1\uff0c\u4f8b\u5982\u5206\u5b50\u5c5e\u6027\u9884\u6d4b\u548c\u836f\u7269\u8bbe\u8ba1\uff0c\u4f46\u5b83\u4eec\u4ec5\u5728\u57fa\u5143\u6216\u5206\u5b50\u56fe\u4e0a\u64cd\u4f5c\u3002\u5982\u4f55\u5c06\u5b83\u4eec\u4e0e\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\u6709\u673a\u7ec4\u5408\uff0c\u4f7f\u5176\u80fd\u591f\u5904\u7406 3D \u7ed3\u6784\u4fe1\u606f\u5e76\u5728 3D \u7ed3\u6784\u4e0a\u6267\u884c\u9884\u6d4b\u6216\u751f\u6210\uff0c\u4ecd\u7136\u5177\u6709\u76f8\u5f53\u7684\u6311\u6218\u6027\u3002<\/span><\/o:p><\/section>\n

<\/span><\/section>\n
4. \u7b49\u53d8\u6027\u7ea6\u675f\u6761\u4ef6\u7684\u653e\u677e<\/span><\/strong><\/section>\n

<\/span><\/strong><\/section>\n
\u6beb\u65e0\u7591\u95ee\uff0c\u7b49\u53d8\u6027\u5bf9\u589e\u5f3a\u6570\u636e\u6548\u7387\u548c\u6a21\u578b\u6cdb\u5316\u80fd\u529b\u81f3\u5173\u91cd\u8981\uff0c\u4f46\u503c\u5f97\u6ce8\u610f\u7684\u662f\uff0c\u8fc7\u5f3a\u7b49\u53d8\u6027\u7ea6\u675f\u6709\u65f6\u53ef\u80fd\u8fc7\u4e8e\u9650\u5236\u6a21\u578b\uff0c\u6f5c\u5728\u5730\u635f\u5bb3\u5176\u6027\u80fd\u3002\u56e0\u6b64\uff0c\u5982\u4f55\u4f7f\u5f97\u6240\u8bbe\u8ba1\u7684\u6a21\u578b\u5728\u7b49\u53d8\u6027\u4e0e\u9002\u5e94\u80fd\u529b\u4e2d\u53d6\u5f97\u5e73\u8861\u662f\u4e00\u4e2a\u975e\u5e38\u6709\u8da3\u7684\u95ee\u9898\u3002\u8fd9\u65b9\u9762\u7684\u63a2\u7d22\u4e0d\u4ec5\u53ef\u4ee5\u4e30\u5bcc\u6211\u4eec\u5bf9\u6a21\u578b\u884c\u4e3a\u7684\u7406\u89e3\uff0c\u8fd8\u53ef\u4ee5\u4e3a\u5f00\u53d1\u66f4\u5177\u9c81\u68d2\u6027\u548c\u901a\u7528\u6027\u7684\u89e3\u51b3\u65b9\u6848\u94fa\u5e73\u9053\u8def\uff0c\u4f7f\u5176\u5177\u6709\u66f4\u5e7f\u6cdb\u7684\u9002\u7528\u6027\u3002<\/span><\/o:p><\/section>\n

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

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

\u53c2\u8003\u6587\u732e<\/span><\/strong><\/span><\/o:p><\/h2>\n
[1] Sch\u00fctt K, Kindermans P J, Sauceda Felix H E, et al. Schnet: A continuous-filter convolutional neural network for modeling quantum interactions[J]. Advances in neural information processing systems, 2017, 30.<\/span><\/o:p><\/section>\n
[2] Satorras V G, Hoogeboom E, Welling M. E (n) equivariant graph neural networks[C]\/\/International conference on machine learning. PMLR, 2021: 9323-9332.<\/span><\/o:p><\/section>\n
[3] Thomas N, Smidt T, Kearnes S, et al. Tensor field networks: Rotation-and translation-equivariant neural networks for 3d point clouds[J]. arXiv preprint arXiv:1802.08219, 2018.<\/span><\/o:p><\/section>\n
[4] Gasteiger J, Gro\u00df J, G\u00fcnnemann S. Directional Message Passing for Molecular Graphs[C]\/\/International Conference on Learning Representations. 2019.<\/span><\/o:p><\/section>\n
[5] Gasteiger J, Becker F, G\u00fcnnemann S. Gemnet: Universal directional graph neural networks for molecules[J]. Advances in Neural Information Processing Systems, 2021, 34: 6790-6802.<\/span><\/o:p><\/section>\n
[6] Merchant A, Batzner S, Schoenholz S S, et al. Scaling deep learning for materials discovery[J]. Nature, 2023, 624(7990): 80-85.<\/span><\/section>\n

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

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

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

\n


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

\u73b0\u5b9e\u4e16\u754c\u4e2d\u5927\u91cf\u95ee\u9898\u7684\u89e3\u51b3\u4f9d\u8d56\u4e8e\u7b97\u6cd5\u7684\u8bbe\u8ba1\u4e0e\u6c42\u89e3\u3002\u4f20\u7edf\u7b97\u6cd5\u7531\u4eba\u7c7b\u4e13\u5bb6\u8bbe\u8ba1\uff0c\u800c\u968f\u7740\u4eba\u5de5\u667a\u80fd\u6280\u672f\u4e0d\u65ad\u53d1\u5c55\uff0c\u7b97\u6cd5\u81ea\u52a8\u5b66\u4e60\u7b97\u6cd5\u7684\u6848\u4f8b\u65e5\u76ca\u589e\u591a\uff0c\u5982\u4ee5\u795e\u7ecf\u7f51\u7edc\u4e3a\u4ee3\u8868\u7684\u7684\u4eba\u5de5\u667a\u80fd\u7b97\u6cd5\uff0c\u8fd9\u662f\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u7684\u7f18\u7531\u3002\u5728\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u65b9\u5411\u4e0a\uff0c\u56fe\u795e\u7ecf\u7f51\u7edc\u662f\u4e00\u4e2a\u5f3a\u6709\u529b\u7684\u5de5\u5177\uff0c\u80fd\u591f\u5145\u5206\u5229\u7528\u56fe\u7ed3\u6784\u7684\u7279\u6027\uff0c\u5b9e\u73b0\u5bf9\u9ad8\u590d\u6742\u5ea6\u7b97\u6cd5\u7684\u9ad8\u6548\u8fd1\u4f3c\u6c42\u89e3\u3002\u57fa\u4e8e\u56fe\u795e\u7ecf\u7f51\u7edc\u7684\u590d\u6742\u7cfb\u7edf\u4f18\u5316\u4e0e\u63a7\u5236\u5c06\u4f1a\u662f\u5927\u6a21\u578b\u70ed\u6f6e\u4e4b\u540e\u65b0\u7684\u672a\u6765\u65b9\u5411\u3002<\/span><\/section>\n

<\/span><\/section>\n
\u4e3a\u4e86\u63a2\u8ba8\u56fe\u795e\u7ecf\u7f51\u7edc\u5728\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u7684\u53d1\u5c55\u4e0e\u73b0\u5b9e\u5e94\u7528\uff0c\u96c6\u667a\u4ff1\u4e50\u90e8\u8054\u5408\u56fd\u9632\u79d1\u6280\u5927\u5b66\u7cfb\u7edf\u5de5\u7a0b\u5b66\u9662\u526f\u6559\u6388\u8303\u957f\u4fca\u3001\u4e2d\u56fd\u4eba\u6c11\u5927\u5b66\u9ad8\u74f4\u4eba\u5de5\u667a\u80fd\u5b66\u9662\u526f\u6559\u6388\u9ec4\u6587\u70b3\uff0c\u5171\u540c\u53d1\u8d77\u300c\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7ec4\u5408\u4f18\u5316\u300d\u8bfb\u4e66\u4f1a\u3002\u8bfb\u4e66\u4f1a\u5c06\u805a\u7126\u4e8e\u56fe\u795e\u7ecf\u7f51\u7edc\u4e0e\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u7684\u76f8\u5173\u9886\u57df\uff0c\u5305\u62ec\u795e\u7ecf\u7b97\u6cd5\u63a8\u7406\u3001\u7ec4\u5408\u4f18\u5316\u95ee\u9898\u6c42\u89e3\u3001\u51e0\u4f55\u56fe\u795e\u7ecf\u7f51\u7edc\uff0c\u4ee5\u53ca\u7b97\u6cd5\u795e\u7ecf\u5316\u6c42\u89e3\u5728 AI for Science \u4e2d\u7684\u5e94\u7528\u7b49\u65b9\u9762\u3002<\/span>\u8bfb\u4e66\u4f1a\u5df2\u5b8c\u7ed3\uff0c\u73b0\u5728\u62a5\u540d\u53ef\u52a0\u5165\u793e\u7fa4\u5e76\u89e3\u9501<\/span>\u56de\u653e<\/span>\u89c6\u9891\u6743\u9650\u3002<\/span><\/span><\/span><\/section>\n

<\/span><\/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


<\/p>\n


<\/p>\n

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

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

1. <\/strong>\u524d\u6cbf\u63a2\u8ba8\uff1a\u56fe\u795e\u7ecf\u7f51\u7edc\u3001\u7ec4\u5408\u4f18\u5316\u3001\u5927\u6a21\u578b\u4e0eAI4Science\u5982\u4f55\u76f8\u4e92\u4fc3\u8fdb\uff1f<\/a><\/strong><\/span><\/section>\n
2.<\/strong>\u51e0\u4f55\u6df1\u5ea6\u5b66\u4e60\uff1a\u8ba9\u7269\u7406\u4e16\u754c\u62e5\u6709AI | \u9ec4\u6587\u70b3\u5206\u4eab\u6574\u7406<\/a><\/a><\/strong><\/span><\/section>\n
3. <\/strong>\u4eba\u5de5\u667a\u80fd\u524d\u6cbf\uff1a\u7ec4\u5408\u4f18\u5316\u95ee\u9898\u7684\u673a\u5668\u5b66\u4e60\u6c42\u89e3 | \u8303\u957f\u4fca\u5206\u4eab\u6574\u7406<\/a><\/strong><\/span><\/section>\n
4. <\/strong><\/span>\u5f20\u6c5f\uff1a\u7b2c\u4e09\u4ee3\u4eba\u5de5\u667a\u80fd\u6280\u672f\u57fa\u7840\u2014\u2014\u4ece\u53ef\u5fae\u5206\u7f16\u7a0b\u5230\u56e0\u679c\u63a8\u7406 | \u96c6\u667a\u5b66\u56ed\u5168\u65b0\u8bfe\u7a0b<\/a><\/strong><\/strong><\/span><\/section>\n
<\/strong><\/strong>5.<\/strong> \u9f99\u5e74\u5927\u8fd0\u8d77\uff0c\u5b66\u4e60\u6b63\u5f53\u65f6\uff01\u89e3\u9501\u96c6\u667a\u5168\u7ad9\u5185\u5bb9\uff0c\u5f00\u542f\u65b0\u5e74\u5b66\u4e60\u8ba1\u5212<\/a><\/strong><\/strong><\/strong><\/strong><\/span><\/section>\n
6. <\/strong>\u52a0\u5165\u96c6\u667a\uff0c\u4e00\u8d77\u590d\u6742\uff01<\/strong><\/span><\/a><\/section>\n


<\/p>\n


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

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

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

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

\u5bfc\u8bed \u8fd1\u65e5\uff0c\u4eba\u5927\u9ad8\u74f4\u8054\u5408\u817e\u8baf AI Lab\u3001\u6e05\u534e\u3001\u65af\u5766\u798f\u7b49\u673a\u6784\u53d1\u5e03\u7efc\u8ff0\u8bba\u6587\uff1a\u300aA Survey of Geometric Graph Neural Networks: Data Structures, Models and Applications\u300b\u3002\u8be5\u7efc\u8ff0\u5728\u7b80\u8981\u4ecb\u7ecd\u7fa4\u8bba\u3001\u5bf9\u79f0\u6027\u7b49\u7406\u8bba\u77e5\u8bc6\u7684\u57fa\u7840\u4e0a\uff0c…<\/p>\n","protected":false},"author":0,"featured_media":48769,"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\/48781"}],"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=48781"}],"version-history":[{"count":0,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/posts\/48781\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=\/wp\/v2\/media\/48769"}],"wp:attachment":[{"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=48781"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=48781"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=48781"},{"taxonomy":"special","embeddable":true,"href":"https:\/\/swarma.org\/index.php?rest_route=%2Fwp%2Fv2%2Fspecial&post=48781"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}