• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Á¤±³ÇÑ ÀÌ¿ô ³ëµå ¼±ÅùýÀ» È°¿ëÇÑ ±×·¡ÇÁ ÇÕ¼º°ö ³×Æ®¿öÅ©
¿µ¹®Á¦¸ñ(English Title) Graph Convolutional Networks with Elaborate Neighborhood Selection
ÀúÀÚ(Author) Á¤¿¬¼º   ȲÁö¿µ   Yeonsung Jung   Joyce Jiyoung Whang  
¿ø¹®¼ö·Ïó(Citation) VOL 46 NO. 11 PP. 1193 ~ 1198 (2019. 11)
Çѱ۳»¿ë
(Korean Abstract)
±×·¡ÇÁ ÇÕ¼º°ö ³×Æ®¿öÅ©(GCNs)´Â ÇÕ¼º°ö ±¸Á¶¸¦ È°¿ëÇÏ¿© ÁÖº¯ ³ëµåµéÀÇ Á¤º¸¸¦ Á¾ÇÕÇÏ´Â ¹æ½ÄÀ¸·Î ´ë»ó ³ëµåÀÇ Ç¥Çö·ÂÀ» ³ôÀδÙ. ³ôÀº ¼º´ÉÀ» º¸À̱â À§Çؼ­´Â ¿ì¼±ÀûÀ¸·Î ´ë»ó ³ëµå¿¡°Ô ÇÊ¿äÇÑ Á¤º¸¸¦ Àü´ÞÇÒ ¼ö ÀÖ´Â ÁÖº¯ ³ëµå¸¦ ¼±º°ÇÏ°í, ÀÌÈÄ ÇнÀ½Ã ÀûÀýÇÑ ÇÊÅÍ(filter) °ªÀ» ½ÀµæÇÏ´Â °úÁ¤ÀÌ ¼ö¹ÝµÇ¾î¾ßÇÑ´Ù. ÃÖ±Ù GCNs ¾Ë°í¸®ÁòµéÀº 1-hop °Å¸®ÀÇ ³ëµåµéÀ» ¼±ÅÃÇÏ´Â µîÀÇ ºñ±³Àû °£´ÜÇÑ ÀÌ¿ô ³ëµåÁ¤ÀǸ¦ È°¿ëÇÏ°í ÀÖ´Ù. ÀÌ·¯ÇÑ °æ¿ì ºÒÇÊ¿äÇÑ Á¤º¸°¡ ´ë»ó ³ëµå¿¡ ÀüÆÄµÇ¾î ¼º´ÉÀ» ÀúÇÏÇÏ´Â ¹®Á¦°¡ ¹ß»ýÇÑ´Ù. º» ³í¹®¿¡¼­´Â ´ë»ó ³ëµå¿Í ÁÖº¯ ³ëµå°£ÀÇ À¯»çµµ °è»êÀ» ÅëÇØ À¯È¿ÇÑ ÀÌ¿ô ³ëµå¸¦ ¼±º°ÇÏ¿© È°¿ëÇÏ´Â GCN ¾Ë°í¸®ÁòÀ» Á¦¾ÈÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Graph Convolutional Networks (GCNs) utilize the convolutional structure to obtain an effective insight on representation by aggregating the information from neighborhoods. In order to demonstrate high performance, it is necessary to select neighborhoods that can propagate important information to target nodes, and acquire appropriate filter values during training. Recent GCNs algorithms adopt simple neighborhood selection methods, such as taking all 1-hop nodes. In the present case, unnecessary information was propagated to the target node, resulting in degradation of the performance of the model. In this paper, we propose a GCN algorithm that utilizes valid neighborhoods by calculating the similarity between the target node and neighborhoods.
Å°¿öµå(Keyword) ³ëµå ºÐ·ù   ±×·¡ÇÁ ÇÕ¼º°ö ³×Æ®¿öÅ©   ±×·¡ÇÁ ½Å°æ¸Á   ±×·¡ÇÁ ¸¶ÀÌ´×   node classification   graph convolutional network   graph neural network   graph mining  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå