所有文章 > 正文

IJCAI 50周年,近十年历届会议杰出论文奉上!

作者: GCT

时间: 2019-08-20 10:09

上周五(8月16日),随着各个奖项公布,今年的国际人工智能顶会IJCAI正式落下帷幕。今年的会议共计收到投稿论文4752篇,录用850篇,接受率为17.9%。虽然投稿和录用量都为历届最高,但许多学者对于本届的审稿过程颇为不满,学生审稿,审稿意见太水等貌似成为本届IJCAI的代名词。

虽然本届的审稿颇具争议,但较低的录用率,也从侧面反映了论文的含金量大大提升。据统计,从通讯作者所在地区来看,中国地区(包括香港)录用342篇,约40%,排名第一,美国169篇,约占20%,位列第二。从录用论文的研究领域来看,机器学习仍是主力军,录用438篇,约占51.5%,计算机视觉和机器学习应用位列二、三位。

下面我们就来了解一下近十年各届IJCAI会议的杰出论文。

2019年杰出论文

获奖论文:Boosting for Comparison-Based Learning

Abstract:We consider the problem of classification in a comparison-based setting: given a set of objects, we only have access to triplet comparisons of the form “object A is closer to object B than to object C.” In this paper we introduce TripletBoost, a new method that can learn a classifier just from such triplet comparisons. The main idea is to aggregate the triplets information into weak classifiers, which can subsequently be boosted to a strong classifier. Our method has two main advantages: (i) it is applicable to data from any metric space, and (ii) it can deal with large scale problems using only passively obtained and noisy triplets. We derive theoretical generalization guarantees and a lower bound on the number of necessary triplets, and we empirically show that our method is both competitive with state of the art approaches and resistant to noise.

作者:Michael Perrot,Ulrike von Luxburg

1r.png

图片来自GCT官网AI人才库

链接:https://gct.aminer.cn/eb/gallery/detail/eb/5cc3eeec6558b90bfabc4a96

在论文中作者们提出了 TripletBoost,这是可以仅仅使用三元组比较就可以学习到一个分类器的方法。方法的关键思路是把三元组信息集聚成为较弱的分类器,然后可以把它逐步提升为一个比较强的分类器。通过实验,这种方法能够更好的抵抗噪声。

2r.png

3r.png

论文地址:https://www.ijcai.org/proceedings/2019/0255.pdf

2018年杰出论文

2018年共有7篇入选最佳论文,北大、清华、武汉大学与北京理工大学都榜上有名,小编整理论文信息下:

题目:Reasoning about Consensus when Opinions Diffuse through Majority Dynamics

作者:Vincenzo Auletta、Diodato Ferraioli、Gianluigi Greco

论文地址:https://www.ijcai.org/proceedings/2018/0007.pdf

题目:R-SVM+: Robust Learning with Privileged Information

作者:Xue Li、Bo Du、Chang Xu、Yipeng Zhang、 Lefei Zhang、

论文地址:https://www.ijcai.org/proceedings/2018/0334.pdf

题目:SentiGAN: Generating Sentimental Texts via Mixture Adversarial Networks

作者:Ke Wang、万小军

论文地址:https://www.ijcai.org/proceedings/2018/0618.pdf

题目:A Degeneracy Framework for Graph Similarity

作者:Giannis Nikolentzos、Polykarpos Meladianos、Stratis Limnios、Michalis Vazirgiannis

论文地址:https://www.lix.polytechnique.fr/~nikolentzos/files/nikolentzos_ijcai18

题目:What Game are We Playing End-to-end Learning in Normal and Extensive from Games

作者:C. K. Ling、J. Z. Kolter、方飞

论文地址:https://www.ijcai.org/proceedings/2018/0055.pdf

题目:From Conjunctive Queries to Instance Queries in Ontology-Mediated Querying

作者:Cristina Feier、Carsten Lutz、Frank Wolter

论文地址:https://www.ijcai.org/proceedings/2018/0250.pdf

题目:Commonsense Knowledge Aware Conversation Generation with Graph Attention

作者:Hao Zhou、Tom Young、Minlie Huang、Haizhou Zhao、Jingfang Xu

论文链接:https://www.ijcai.org/proceedings/2018/0643.pdf

2017年杰出论文(3篇入围)

题目:Tag Disentangled Generative Adversarial Networks for Object Image Re-rendering

作者:Chaoyue Wang , Chaohui Wang , Chang Xu, Dacheng Tao

论文链接:https://www.ijcai.org/proceedings/2017/0404.pdf

题目:Foundations of Declarative Data Analysis Using Limit Datalog Programs

作者:Mark Kaminski, Bernardo Cuenca Grau, Egor V. Kostylev, Boris Motik and Ian Horrocks

论文链接:https://arxiv.org/pdf/1705.06927.pdf

题目:Constraint-Based Symmetry Detection in General Game Playing

作者:Fred eric Koriche, Sylvain Lagrue,Eric Piette and Sebastien Tabary

论文链接:https://www.ijcai.org/proceedings/2017/0040.pdf

2016年杰出论文

题目:Hierarchical Finite State Controllers for Generalized Planning

作者:Javier Segovia-Aguas,Sergio Jimenez ,Anders Jonsson

论文链接 :http://ijcai.org/Proceedings/16/Papers/458.pdf

题目:Using Task Features for Zero-Shot Knowledge Transfer in Lifelong Learning

作者:David Isele,Mohammad Rostami,Eric Eaton

论文链接 :https://www.ijcai.org/Proceedings/16/Papers/232.pdf

2015年杰出论文

题目:Bayesian active learning for posterior estimation

作者:Kirthevasan Kandasamy,Jeff Schneider

论文链接 :https://www.ijcai.org/Proceedings/15/Papers/507.pdf

题目:Recursive Decomposition for Nonconvex Optimization

作者:Abram L. Friesen,Pedro Domingos

论文链接 :https://www.ijcai.org/Proceedings/15/Papers/042.pdf

2013年杰出论文

题目:Bayesian Optimization in High Dimensions via Random Embeddings

作者:Ziyu Wang,Masrour Zoghi,Frank Hutter

论文链接 :https://www.ijcai.org/Proceedings/13/Papers/263.pdf

题目:Flexibility and Decoupling in the Simple Temporal Problem

作者:Michel Wilson, Tomas Klos, Cees Witteveen

论文链接 :https://pdfs.semanticscholar.org/e397/a3f207862ce7c80d164cf24864b55d194fbc.pdf?_ga=2.101749769.941201194.1566199751-161340960.1565919090

2011年杰出论文

题目:Unweighted Coalitional Manipulation Under the Borda Rule is NP-Hard

作者:Nadja Betzler,Rolf Niedermeier,Gerhard J. Woeginger

论文链接 :http://ijcai.org/Proceedings/11/Papers/021.pdf

题目:Nested Rollout Policy Adaptation for Monte Carlo Tree Search

作者:Christopher D. Rosin

论文链接 :https://www.ijcai.org/Proceedings/11/Papers/115.pdf

2009年杰出论文

题目:Consequence-Driven Reasoning for Horn SHIQ Ontologies

作者:Yevgeny Kazakov

论文链接 :http://ijcai.org/Proceedings/09/Papers/336.pdf

[关于转载]:本文为“AMiner”官网文章。转载本文请联系原作者获取授权,转载仅限全文转载并保留文章标题及内容,不得删改、添加内容绕开原创保护,且文章开头必须注明:转自“AMiner”官网。谢谢您的合作。

二维码 扫码微信阅读
推荐阅读 更多