{"id":477443,"date":"2023-08-09T09:15:09","date_gmt":"2023-08-09T09:15:09","guid":{"rendered":""},"modified":"2023-09-05T11:14:43","modified_gmt":"2023-09-05T11:14:43","slug":"heterogeneous-graph-neural-networks","status":"publish","type":"wiki","link":"https:\/\/oneproxy.pro\/vn\/wiki\/heterogeneous-graph-neural-networks\/","title":{"rendered":"M\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t"},"content":{"rendered":"

M\u1ea1ng th\u1ea7n kinh \u0111\u1ed3 th\u1ecb (GNN) \u0111\u00e3 n\u1ed5i l\u00ean nh\u01b0 m\u1ed9t c\u00f4ng c\u1ee5 thi\u1ebft y\u1ebfu trong vi\u1ec7c bi\u1ec3u di\u1ec5n d\u1eef li\u1ec7u quan h\u1ec7 ph\u1ee9c t\u1ea1p trong nhi\u1ec1u l\u0129nh v\u1ef1c kh\u00e1c nhau. M\u1ed9t t\u1eadp h\u1ee3p con trong s\u1ed1 n\u00e0y, M\u1ea1ng th\u1ea7n kinh \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t (H-GNN), cung c\u1ea5p kh\u1ea3 n\u0103ng x\u1eed l\u00fd th\u00f4ng tin \u0111a d\u1ea1ng, nhi\u1ec1u m\u1eb7t h\u01a1n. Trong b\u00e0i vi\u1ebft n\u00e0y, ch\u00fang t\u00f4i \u0111i s\u00e2u v\u00e0o th\u1ebf gi\u1edbi c\u1ee7a H-GNN, kh\u00e1m ph\u00e1 s\u1ef1 ra \u0111\u1eddi, c\u1ea5u tr\u00fac, t\u00ednh n\u0103ng ch\u00ednh, lo\u1ea1i, \u1ee9ng d\u1ee5ng, so s\u00e1nh v\u1edbi c\u00e1c m\u00f4 h\u00ecnh t\u01b0\u01a1ng t\u1ef1 v\u00e0 tri\u1ec3n v\u1ecdng trong t\u01b0\u01a1ng lai. Cu\u1ed1i c\u00f9ng, ch\u00fang t\u00f4i kh\u00e1m ph\u00e1 m\u1ed1i quan h\u1ec7 gi\u1eefa H-GNN v\u00e0 m\u00e1y ch\u1ee7 proxy.<\/p>\n

Ngu\u1ed3n g\u1ed1c c\u1ee7a m\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t<\/h2>\n

H-GNN l\u00e0 nh\u1eefng b\u1ed5 sung t\u01b0\u01a1ng \u0111\u1ed1i m\u1edbi cho l\u0129nh v\u1ef1c deep learning v\u00e0 AI. Trong khi kh\u00e1i ni\u1ec7m v\u1ec1 m\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh c\u00f3 ngu\u1ed3n g\u1ed1c t\u1eeb nh\u1eefng n\u0103m 1940, \u00fd t\u01b0\u1edfng v\u1ec1 GNN m\u1edbi xu\u1ea5t hi\u1ec7n g\u1ea7n \u0111\u00e2y h\u01a1n nhi\u1ec1u, n\u1ea3y sinh v\u00e0o kho\u1ea3ng n\u0103m 2005 v\u1edbi c\u00f4ng tr\u00ecnh c\u1ee7a Scarselli et al. M\u1ea1ng n\u01a1-ron \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t th\u1eadm ch\u00ed c\u00f2n \u0111\u01b0\u1ee3c \u0111\u1ec1 xu\u1ea5t mu\u1ed9n h\u01a1n, v\u00e0o kho\u1ea3ng n\u0103m 2019, khi c\u00e1c nh\u00e0 nghi\u00ean c\u1ee9u nh\u1eadn ra s\u1ef1 c\u1ea7n thi\u1ebft c\u1ee7a c\u00e1c m\u00f4 h\u00ecnh c\u00f3 th\u1ec3 x\u1eed l\u00fd c\u00e1c ngu\u1ed3n d\u1eef li\u1ec7u ph\u1ee9c t\u1ea1p, nhi\u1ec1u m\u1eb7t v\u00e0 th\u1ec3 hi\u1ec7n c\u00e1c lo\u1ea1i n\u00fat v\u00e0 c\u1ea1nh kh\u00e1c nhau.<\/p>\n

\u0110i s\u00e2u v\u00e0o M\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t<\/h2>\n

Trong GNN ti\u00eau chu\u1ea9n, m\u1ecdi n\u00fat v\u00e0 c\u1ea1nh \u0111\u01b0\u1ee3c coi l\u00e0 c\u00f9ng lo\u1ea1i. H-GNN \u0111i ch\u1ec7ch kh\u1ecfi gi\u1ea3 \u0111\u1ecbnh n\u00e0y, nh\u1eadn ra r\u1eb1ng c\u00e1c n\u00fat v\u00e0 c\u1ea1nh kh\u00e1c nhau c\u00f3 th\u1ec3 t\u01b0\u01a1ng \u1ee9ng \u0111\u1ea1i di\u1ec7n cho c\u00e1c lo\u1ea1i th\u1ef1c th\u1ec3 v\u00e0 m\u1ed1i quan h\u1ec7 kh\u00e1c nhau. V\u00ed d\u1ee5: trong bi\u1ec3u \u0111\u1ed3 m\u1ea1ng x\u00e3 h\u1ed9i, c\u00e1c n\u00fat c\u00f3 th\u1ec3 \u0111\u1ea1i di\u1ec7n cho ng\u01b0\u1eddi d\u00f9ng, b\u00e0i \u0111\u0103ng, nh\u00f3m, v.v., trong khi c\u00e1c c\u1ea1nh c\u00f3 th\u1ec3 bi\u1ec3u th\u1ecb t\u00ecnh b\u1ea1n, l\u01b0\u1ee3t th\u00edch, l\u01b0\u1ee3t theo d\u00f5i, v.v. B\u1eb1ng c\u00e1ch xem x\u00e9t nh\u1eefng kh\u00e1c bi\u1ec7t n\u00e0y, H-GNN c\u00f3 th\u1ec3 n\u1eafm b\u1eaft \u0111\u01b0\u1ee3c c\u00e1i nh\u00ecn s\u1eafc th\u00e1i h\u01a1n v\u1ec1 c\u00e1c m\u1ea1ng ph\u1ee9c t\u1ea1p .<\/p>\n

Ho\u1ea1t \u0111\u1ed9ng b\u00ean trong c\u1ee7a m\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t<\/h2>\n

H-GNN ho\u1ea1t \u0111\u1ed9ng d\u1ef1a tr\u00ean nguy\u00ean t\u1eafc truy\u1ec1n tin nh\u1eafn ho\u1eb7c t\u1eadp h\u1ee3p v\u00f9ng l\u00e2n c\u1eadn. M\u1ed7i n\u00fat trong m\u1ea1ng thu th\u1eadp th\u00f4ng tin ho\u1eb7c \u201ctin nh\u1eafn\u201d t\u1eeb c\u00e1c n\u00fat l\u00e2n c\u1eadn v\u00e0 s\u1eed d\u1ee5ng th\u00f4ng tin n\u00e0y \u0111\u1ec3 c\u1eadp nh\u1eadt c\u00e1ch tr\u00ecnh b\u00e0y c\u1ee7a n\u00f3. Tuy nhi\u00ean, do t\u00ednh ch\u1ea5t kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t c\u1ee7a c\u00e1c n\u00fat v\u00e0 c\u1ea1nh, H-GNN s\u1eed d\u1ee5ng c\u00e1c h\u00e0m chuy\u1ec3n \u0111\u1ed5i theo lo\u1ea1i c\u1ee5 th\u1ec3 \u0111\u1ec3 x\u1eed l\u00fd c\u00e1c th\u00f4ng b\u00e1o n\u00e0y, \u0111\u1ea3m b\u1ea3o r\u1eb1ng c\u00e1c t\u00ednh n\u0103ng ri\u00eang bi\u1ec7t c\u1ee7a c\u00e1c lo\u1ea1i n\u00fat v\u00e0 c\u1ea1nh kh\u00e1c nhau \u0111\u01b0\u1ee3c b\u1ea3o to\u00e0n v\u00e0 k\u1ebft h\u1ee3p m\u1ed9t c\u00e1ch th\u00edch h\u1ee3p.<\/p>\n

C\u00e1c t\u00ednh n\u0103ng ch\u00ednh c\u1ee7a M\u1ea1ng th\u1ea7n kinh \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t<\/h2>\n
    \n
  1. T\u00ednh linh ho\u1ea1t<\/strong>: H-GNN c\u00f3 th\u1ec3 m\u00f4 h\u00ecnh h\u00f3a nhi\u1ec1u ngu\u1ed3n d\u1eef li\u1ec7u ph\u1ee9c t\u1ea1p, nhi\u1ec1u m\u1eb7t.<\/li>\n
  2. Quy\u1ec1n l\u1ef1c \u0111\u1ea1i di\u1ec7n<\/strong>: H\u1ecd c\u00f3 th\u1ec3 n\u1eafm b\u1eaft c\u00e1c m\u1ed1i quan h\u1ec7 s\u1eafc th\u00e1i gi\u1eefa c\u00e1c lo\u1ea1i th\u1ef1c th\u1ec3 kh\u00e1c nhau.<\/li>\n
  3. Kh\u1ea3 n\u0103ng gi\u1ea3i th\u00edch<\/strong>: H-GNN d\u1ec5 hi\u1ec3u h\u01a1n GNN ti\u00eau chu\u1ea9n do m\u00f4 h\u00ecnh h\u00f3a r\u00f5 r\u00e0ng c\u1ee7a ch\u00fang v\u1ec1 c\u00e1c lo\u1ea1i th\u1ef1c th\u1ec3 v\u00e0 m\u1ed1i quan h\u1ec7 kh\u00e1c nhau.<\/li>\n<\/ol>\n

    C\u00e1c lo\u1ea1i m\u1ea1ng th\u1ea7n kinh \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t<\/h2>\n

    Hi\u1ec7n c\u00f3 m\u1ed9t s\u1ed1 bi\u1ebfn th\u1ec3 c\u1ee7a H-GNN, m\u1ed7i bi\u1ebfn th\u1ec3 \u0111\u01b0\u1ee3c thi\u1ebft k\u1ebf \u0111\u1ec3 x\u1eed l\u00fd c\u00e1c t\u00e1c v\u1ee5 ho\u1eb7c lo\u1ea1i d\u1eef li\u1ec7u c\u1ee5 th\u1ec3. D\u01b0\u1edbi \u0111\u00e2y l\u00e0 m\u1ed9t v\u00e0i c\u00e1i n\u1ed5i b\u1eadt:<\/p>\n

      \n
    1. \n

      M\u1ea1ng ch\u00fa \u00fd \u0111\u1ed3 th\u1ecb (GAT)<\/strong>: GAT gi\u1edbi thi\u1ec7u c\u00e1c c\u01a1 ch\u1ebf ch\u00fa \u00fd v\u00e0o GNN, cho ph\u00e9p c\u00e1c l\u00e2n c\u1eadn kh\u00e1c nhau \u0111\u00f3ng g\u00f3p kh\u00e1c nhau v\u00e0o c\u00e1ch bi\u1ec3u di\u1ec5n c\u1ee7a n\u00fat m\u1ee5c ti\u00eau.<\/p>\n<\/li>\n

    2. \n

      M\u1ea1ng t\u00edch ch\u1eadp \u0111\u1ed3 th\u1ecb quan h\u1ec7 (R-GCN)<\/strong>: R-GCN m\u1edf r\u1ed9ng GNN \u0111\u1ec3 x\u1eed l\u00fd d\u1eef li\u1ec7u \u0111a quan h\u1ec7, \u0111i\u1ec1u n\u00e0y th\u01b0\u1eddng th\u1ea5y trong bi\u1ec3u \u0111\u1ed3 tri th\u1ee9c.<\/p>\n<\/li>\n

    3. \n

      M\u00e1y bi\u1ebfn \u0111\u1ed5i \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t (HGT)<\/strong>: HGT \u0111i\u1ec1u ch\u1ec9nh m\u00f4 h\u00ecnh m\u00e1y bi\u1ebfn \u00e1p cho ph\u00f9 h\u1ee3p v\u1edbi d\u1eef li\u1ec7u \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t, cho ph\u00e9p m\u00f4 h\u00ecnh h\u00f3a t\u01b0\u01a1ng t\u00e1c ph\u1ee9c t\u1ea1p h\u01a1n.<\/p>\n<\/li>\n<\/ol>\n

      \u1ee8ng d\u1ee5ng, v\u1ea5n \u0111\u1ec1 v\u00e0 gi\u1ea3i ph\u00e1p<\/h2>\n

      H-GNN \u0111\u01b0\u1ee3c s\u1eed d\u1ee5ng trong nhi\u1ec1u l\u0129nh v\u1ef1c, bao g\u1ed3m ph\u00e2n t\u00edch m\u1ea1ng x\u00e3 h\u1ed9i, h\u1ec7 th\u1ed1ng khuy\u1ebfn ngh\u1ecb v\u00e0 m\u1ea1ng sinh h\u1ecdc. Tuy nhi\u00ean, h\u1ecd ph\u1ea3i \u0111\u1ed1i m\u1eb7t v\u1edbi nh\u1eefng th\u00e1ch th\u1ee9c nh\u01b0 kh\u1ea3 n\u0103ng m\u1edf r\u1ed9ng v\u00e0 thi\u1ebft k\u1ebf ph\u1ee9c t\u1ea1p. C\u00e1c gi\u1ea3i ph\u00e1p bao g\u1ed3m ph\u00e1t tri\u1ec3n c\u00e1c ph\u01b0\u01a1ng ph\u00e1p \u0111\u00e0o t\u1ea1o hi\u1ec7u qu\u1ea3 h\u01a1n, thi\u1ebft k\u1ebf \u0111\u01a1n gi\u1ea3n h\u00f3a v\u00e0 t\u1eadn d\u1ee5ng kh\u1ea3 n\u0103ng t\u0103ng t\u1ed1c ph\u1ea7n c\u1ee9ng.<\/p>\n

      So s\u00e1nh v\u1edbi c\u00e1c m\u00f4 h\u00ecnh t\u01b0\u01a1ng t\u1ef1<\/h2>\n\n\n\n\n\n\n\n
      Ng\u01b0\u1eddi m\u1eabu<\/th>\nUy\u1ec3n chuy\u1ec3n<\/th>\n\u0110\u1ed9 ph\u1ee9c t\u1ea1p<\/th>\nKh\u1ea3 n\u0103ng m\u1edf r\u1ed9ng<\/th>\n<\/tr>\n<\/thead>\n
      GNN ti\u00eau chu\u1ea9n<\/td>\nTh\u1ea5p<\/td>\nV\u1eeba ph\u1ea3i<\/td>\nCao<\/td>\n<\/tr>\n
      GNN kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t<\/td>\nCao<\/td>\nCao<\/td>\nV\u1eeba ph\u1ea3i<\/td>\n<\/tr>\n
      M\u1ea1ng th\u1ea7n kinh t\u00edch ch\u1eadp<\/td>\nTh\u1ea5p<\/td>\nV\u1eeba ph\u1ea3i<\/td>\nCao<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

      Tri\u1ec3n v\u1ecdng t\u01b0\u01a1ng lai c\u1ee7a m\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t<\/h2>\n

      H-GNN l\u00e0 m\u1ed9t l\u0129nh v\u1ef1c \u0111ang ph\u00e1t tri\u1ec3n nhanh ch\u00f3ng, v\u1edbi nghi\u00ean c\u1ee9u \u0111ang \u0111\u01b0\u1ee3c ti\u1ebfn h\u00e0nh \u0111\u1ec3 t\u1ea1o ra c\u00e1c m\u00f4 h\u00ecnh m\u1ea1nh m\u1ebd h\u01a1n, kh\u1eafc ph\u1ee5c c\u00e1c v\u1ea5n \u0111\u1ec1 v\u1ec1 kh\u1ea3 n\u0103ng m\u1edf r\u1ed9ng v\u00e0 m\u1edf r\u1ed9ng c\u00e1c l\u0129nh v\u1ef1c \u1ee9ng d\u1ee5ng. C\u00e1c c\u00f4ng ngh\u1ec7 trong t\u01b0\u01a1ng lai c\u00f3 th\u1ec3 bao g\u1ed3m c\u00e1c c\u01a1 ch\u1ebf ch\u00fa \u00fd ti\u00ean ti\u1ebfn, ph\u01b0\u01a1ng ph\u00e1p h\u1ecdc t\u1eadp \u0111a ph\u01b0\u01a1ng th\u1ee9c v\u00e0 c\u00e1c k\u1ef9 thu\u1eadt \u0111\u00e0o t\u1ea1o hi\u1ec7u qu\u1ea3 h\u01a1n.<\/p>\n

      M\u1ea1ng th\u1ea7n kinh \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t v\u00e0 m\u00e1y ch\u1ee7 proxy<\/h2>\n

      M\u00e1y ch\u1ee7 proxy c\u00f3 th\u1ec3 \u0111\u00f3ng vai tr\u00f2 trong vi\u1ec7c tri\u1ec3n khai H-GNN b\u1eb1ng c\u00e1ch cung c\u1ea5p kh\u1ea3 n\u0103ng k\u1ebft n\u1ed1i v\u00e0 ki\u1ec3m so\u00e1t truy c\u1eadp \u0111\u01b0\u1ee3c c\u1ea3i thi\u1ec7n. Ch\u00fang c\u0169ng c\u00f3 th\u1ec3 gi\u00fap qu\u1ea3n l\u00fd t\u1ea3i trong c\u00e1c \u1ee9ng d\u1ee5ng H-GNN quy m\u00f4 l\u1edbn, ph\u00e2n ph\u1ed1i y\u00eau c\u1ea7u tr\u00ean nhi\u1ec1u m\u00e1y ch\u1ee7 \u0111\u1ec3 \u0111\u1ea3m b\u1ea3o hi\u1ec7u su\u1ea5t t\u1ed1i \u01b0u.<\/p>\n

      Li\u00ean k\u1ebft li\u00ean quan<\/h2>\n
        \n
      1. M\u1ed9t kh\u1ea3o s\u00e1t to\u00e0n di\u1ec7n v\u1ec1 m\u1ea1ng l\u01b0\u1edbi th\u1ea7n kinh \u0111\u1ed3 th\u1ecb<\/a><\/li>\n
      2. Bi\u1ebfn \u00e1p \u0111\u1ed3 th\u1ecb kh\u00f4ng \u0111\u1ed3ng nh\u1ea5t<\/a><\/li>\n
      3. M\u1ea1ng ch\u00fa \u00fd \u0111\u1ed3 th\u1ecb<\/a><\/li>\n
      4. M\u1ea1ng t\u00edch ch\u1eadp \u0111\u1ed3 th\u1ecb quan h\u1ec7<\/a><\/li>\n<\/ol>","protected":false},"featured_media":468537,"menu_order":0,"template":"","meta":{"_acf_changed":false,"content-type":"","inline_featured_image":false,"footnotes":""},"class_list":["post-477443","wiki","type-wiki","status-publish","has-post-thumbnail","hentry"],"acf":{"faq_title":"Frequently Asked Questions about Heterogeneous Graph Neural Networks: A Comprehensive Overview<\/mark>","faq_items":[{"question":"What are Heterogeneous Graph Neural Networks?","answer":"

        Heterogeneous Graph Neural Networks (H-GNNs) are a subset of Graph Neural Networks that handle diverse and multifaceted information. Unlike standard GNNs that assume all nodes and edges are of the same type, H-GNNs consider different nodes and edges to represent different types of entities and relationships.<\/p>"},{"question":"When did the concept of Heterogeneous Graph Neural Networks emerge?","answer":"

        The concept of Heterogeneous Graph Neural Networks emerged around 2019, following the introduction of Graph Neural Networks in 2005.<\/p>"},{"question":"How do Heterogeneous Graph Neural Networks function?","answer":"

        H-GNNs function based on the principle of message passing or neighborhood aggregation. Each node in the network collects information or \"messages\" from its neighboring nodes to update its representation. Given the heterogeneous nature of the nodes and edges, H-GNNs employ type-specific transformation functions to process these messages.<\/p>"},{"question":"What are some key features of Heterogeneous Graph Neural Networks?","answer":"

        H-GNNs are characterized by their versatility in modeling a wide range of complex, multifaceted data sources. They have high representation power, capturing nuanced relationships between different types of entities. H-GNNs also offer improved interpretability due to their explicit modeling of different types of entities and relationships.<\/p>"},{"question":"What types of Heterogeneous Graph Neural Networks exist?","answer":"

        Several variants of H-GNNs exist, including Graph Attention Networks (GATs), Relational Graph Convolutional Networks (R-GCNs), and Heterogeneous Graph Transformer (HGT).<\/p>"},{"question":"What are some applications and challenges of Heterogeneous Graph Neural Networks?","answer":"

        H-GNNs find applications in various domains such as social network analysis, recommendation systems, and biological networks. However, they face challenges like scalability and complex design, which are being addressed by developing more efficient training methods and simplified designs.<\/p>"},{"question":"How do Heterogeneous Graph Neural Networks compare with similar models?","answer":"

        Compared to standard GNNs and Convolutional Neural Networks, H-GNNs offer higher flexibility and complexity but face challenges in scalability.<\/p>"},{"question":"What is the future of Heterogeneous Graph Neural Networks?","answer":"

        The future of H-GNNs is promising with ongoing research into creating more powerful models, overcoming scalability issues, and expanding application areas. Future technologies might include advanced attention mechanisms, cross-modal learning approaches, and more efficient training techniques.<\/p>"},{"question":"How are proxy servers related to Heterogeneous Graph Neural Networks?","answer":"

        Proxy servers can play a role in deploying H-GNNs by providing improved connectivity and access control. They can also help manage the load in large-scale H-GNN applications by distributing requests across multiple servers for optimal performance.<\/p>"}]},"_links":{"self":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki\/477443","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki"}],"about":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/types\/wiki"}],"version-history":[{"count":0,"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/wiki\/477443\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media\/468537"}],"wp:attachment":[{"href":"https:\/\/oneproxy.pro\/vn\/wp-json\/wp\/v2\/media?parent=477443"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}