<p><span style="font-size:15px"><span>本文分享一篇多关系知识图谱表示学习汇报</span><span>ppt</span><span>，介绍近几年及</span><span>2020</span><span>新出的共七篇处理异质图的模型。欢迎关注公众号【AI机器学习与知识图谱】，先列出该汇报</span><span>ppt</span><span>中将要介绍的七篇论文：</span></span></p><p><span style="font-size:15px">
</span></p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-12bd44e7e0777032.jpeg" img-data="{"format":"jpeg","size":56214,"height":260,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p><strong style="font-size: 20px;">
</strong></p><p><strong style="font-size: 20px;">Motivation</strong></p><p>
</p><p><span style="font-size:15px"><span>异质知识图谱研究的对象便是如何处理多关系知识图谱，多关系知识图谱中模型在做节点表征时便需要充分考虑到关系</span><span>Relation</span><span>，也就是边</span><span>Edge</span><span>对于实体表征的作用，因此异质知识图谱模型便会在做节点表征时加入</span><span>Relation</span><span>关系信息，那么如何合理充分结合</span><span>node</span><span>和</span><span>relation</span><span>信息来提高表征能力便是下面模型关注的重点。应用场景也多用在图谱节点分类，以及知识图谱补全（</span><span>Link Prediction</span><span>）</span></span></p><p><span style="font-size:15px">
</span></p><p><span style="font-size:15px">
</span></p><p><span style="font-size:20px"><strong>Papers</strong></span></p><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-3de068c16baf0e36.jpeg" img-data="{"format":"jpeg","size":79740,"height":561,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p><span style="font-size:15px">
</span></p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-88560b0478c16bef.jpeg" img-data="{"format":"jpeg","size":66895,"height":562,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-87661faf2a2cf19f.jpeg" img-data="{"format":"jpeg","size":43751,"height":301,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-8133f78e46606217.jpeg" img-data="{"format":"jpeg","size":104213,"height":593,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-67e64f12f00217d1.jpeg" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-e2a975b9b8d41c78.jpeg" img-data="{"format":"jpeg","size":80352,"height":495,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-d64150a77ede57f2.jpeg" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-93d41844a357d949.jpeg" img-data="{"format":"jpeg","size":102046,"height":549,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-cf4ac9a232d05376.jpeg" img-data="{"format":"jpeg","size":97159,"height":580,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-5dce8cce68fcce11.jpeg" img-data="{"format":"jpeg","size":62638,"height":518,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-55956aa4bbc45f79.jpeg" img-data="{"format":"jpeg","size":75672,"height":589,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-a77d6f22cba88bcc.jpeg" img-data="{"format":"jpeg","size":83113,"height":540,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-378086b550d93b1c.jpeg" img-data="{"format":"jpeg","size":63795,"height":530,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-9edbaaa6099cbc67.jpeg" img-data="{"format":"jpeg","size":65827,"height":554,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-a8486048136d51ba.jpeg" img-data="{"format":"jpeg","size":68079,"height":585,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-c3776245c6ecdc8d.jpeg" img-data="{"format":"jpeg","size":101555,"height":558,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-fccd764e045af9b4.jpeg" img-data="{"format":"jpeg","size":41948,"height":553,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-8546de30d5cf288c.jpeg" img-data="{"format":"jpeg","size":74874,"height":582,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-5702d601643635ff.jpeg" img-data="{"format":"jpeg","size":79566,"height":586,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-d24be35d708ff0cb.jpeg" img-data="{"format":"jpeg","size":74371,"height":586,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-a12345c5eaac76d3.jpeg" img-data="{"format":"jpeg","size":64993,"height":556,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-008eab7bd371ba89.jpeg" img-data="{"format":"jpeg","size":67336,"height":594,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><div class="image-package"><img src="https://upload-images.jianshu.io/upload_images/26011021-3f761dc1b5ce9c33.jpeg" img-data="{"format":"jpeg","size":86321,"height":581,"width":1080}" class="uploaded-img" style="min-height:200px;min-width:200px;" width="auto" height="auto"/>
</div><p>
</p><p>
</p><p>
</p><p><span style="font-size:18px"><strong>往期精彩</strong></span></p><p>
</p><p><span style="font-size:14px">【知识图谱系列】知识图谱表示学习综述 | 近30篇优秀论文串讲</span></p><p><span>【知识图谱系列】动态时序知识图谱EvolveGCN</span></p><p>【面经系列】八位硕博大佬的字节之旅</p><p>【机器学习系列】机器学习中的两大学派</p><p/><p><span style="font-size:14px">干货 | NLP中的十个预训练模型</span></p><p/><p><span style="font-size:14px">FastText原理和文本分类实战，看这一篇就够了</span></p><p><span style="font-size:14px">GPT,GPT2,Bert,Transformer-XL,XLNet论文阅读速递</span></p><p><span style="font-size:14px">Word2vec, Fasttext, Glove, Elmo, Bert, Flair训练词向量教程+数据+源码</span></p><p>
</p>