no code implementations • Findings (EMNLP) 2021 • Jingwen Xu, Jing Zhang, Xirui Ke, Yuxiao Dong, Hong Chen, Cuiping Li, Yongbin Liu
Its general process is to first encode the implicit relation of an entity pair and then match the relation of a query entity pair with the relations of the reference entity pairs.
no code implementations • 24 May 2023 • Kejuan Yang, Xiao Liu, Kaiwen Men, Aohan Zeng, Yuxiao Dong, Jie Tang
We identify two crucial limitations in the evaluation of recent parallel-integrated method Parallel Context Windows (PCW), which extends the maximum context lengths of language models, e. g., 2048 for LLaMA, by harnessing window-wise attention and positional embedding techniques.
2 code implementations • 12 Apr 2023 • Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, Yuxiao Dong
We present ImageReward -- the first general-purpose text-to-image human preference reward model -- to address various prevalent issues in generative models and align them with human values and preferences.
2 code implementations • 10 Apr 2023 • Zhenyu Hou, Yufei He, Yukuo Cen, Xiao Liu, Yuxiao Dong, Evgeny Kharlamov, Jie Tang
Graph self-supervised learning (SSL), including contrastive and generative approaches, offers great potential to address the fundamental challenge of label scarcity in real-world graph data.
1 code implementation • 30 Mar 2023 • Qinkai Zheng, Xiao Xia, Xu Zou, Yuxiao Dong, Shan Wang, Yufei Xue, Zihan Wang, Lei Shen, Andi Wang, Yang Li, Teng Su, Zhilin Yang, Jie Tang
Large pre-trained code generation models, such as OpenAI Codex, can generate syntax- and function-correct code, making the coding of programmers more productive and our pursuit of artificial general intelligence closer.
Ranked #19 on Code Generation on HumanEval
no code implementations • 26 Mar 2023 • Ji Qi, Jifan Yu, Teng Tu, Kunyu Gao, Yifan Xu, Xinyu Guan, Xiaozhi Wang, Yuxiao Dong, Bin Xu, Lei Hou, Juanzi Li, Jie Tang, Weidong Guo, Hui Liu, Yu Xu
Despite the recent emergence of video captioning models, how to generate vivid, fine-grained video descriptions based on the background knowledge (i. e., long and informative commentary about the domain-specific scenes with appropriate reasoning) is still far from being solved, which however has great applications such as automatic sports narrative.
no code implementations • 23 Feb 2023 • Bo Chen, Jing Zhang, Fanjin Zhang, Tianyi Han, Yuqing Cheng, Xiaoyan Li, Yuxiao Dong, Jie Tang
Name disambiguation -- a fundamental problem in online academic systems -- is now facing greater challenges with the increasing growth of research papers.
5 code implementations • 5 Oct 2022 • Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, Weng Lam Tam, Zixuan Ma, Yufei Xue, Jidong Zhai, WenGuang Chen, Peng Zhang, Yuxiao Dong, Jie Tang
We introduce GLM-130B, a bilingual (English and Chinese) pre-trained language model with 130 billion parameters.
Ranked #1 on Language Modelling on CLUE (CMRC2018)
1 code implementation • 16 Aug 2022 • Xiao Liu, Shiyu Zhao, Kai Su, Yukuo Cen, Jiezhong Qiu, Mengdi Zhang, Wei Wu, Yuxiao Dong, Jie Tang
In this work, we present the Knowledge Graph Transformer (kgTransformer) with masked pre-training and fine-tuning strategies.
2 code implementations • 14 Jul 2022 • Weng Lam Tam, Xiao Liu, Kaixuan Ji, Lilong Xue, Xingjian Zhang, Yuxiao Dong, Jiahua Liu, Maodi Hu, Jie Tang
By updating only 0. 1% of the model parameters, the prompt tuning strategy can help retrieval models achieve better generalization performance than traditional methods in which all parameters are updated.
3 code implementations • 22 May 2022 • Zhenyu Hou, Xiao Liu, Yukuo Cen, Yuxiao Dong, Hongxia Yang, Chunjie Wang, Jie Tang
Despite this, contrastive learning-which heavily relies on structural data augmentation and complicated training strategies-has been the dominant approach in graph SSL, while the progress of generative SSL on graphs, especially graph autoencoders (GAEs), has thus far not reached the potential as promised in other fields.
Ranked #1 on Node Classification on Cora: fixed 20 node per class
no code implementations • NAACL 2022 • Zhuofeng Wu, Sinong Wang, Jiatao Gu, Rui Hou, Yuxiao Dong, V. G. Vinod Vydiswaran, Hao Ma
Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage.
1 code implementation • 12 Mar 2022 • Wenzheng Feng, Yuxiao Dong, Tinglin Huang, Ziqi Yin, Xu Cheng, Evgeny Kharlamov, Jie Tang
In this work, we present a scalable and high-performance GNN framework GRAND+ for semi-supervised graph learning.
Ranked #1 on Node Classification on MAG-scholar-C
1 code implementation • 2 Mar 2022 • Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen, Evgeny Kharlamov, Yuxiao Dong, Jie Tang
We present SelfKG with efficient strategies to optimize this objective for aligning entities without label supervision.
1 code implementation • 15 Feb 2022 • Namyong Park, Fuchen Liu, Purvanshi Mehta, Dana Cristofor, Christos Faloutsos, Yuxiao Dong
How can we perform knowledge reasoning over temporal knowledge graphs (TKGs)?
1 code implementation • 30 Dec 2021 • Qingsong Lv, Ming Ding, Qiang Liu, Yuxiang Chen, Wenzheng Feng, Siming He, Chang Zhou, Jianguo Jiang, Yuxiao Dong, Jie Tang
Heterogeneous graph neural networks (HGNNs) have been blossoming in recent years, but the unique data processing and evaluation setups used by each work obstruct a full understanding of their advancements.
4 code implementations • 8 Dec 2021 • Chenhui Zhang, Yufei He, Yukuo Cen, Zhenyu Hou, Wenzheng Feng, Yuxiao Dong, Xu Cheng, Hongyun Cai, Feng He, Jie Tang
However, it is unclear how to best design the generalization strategies in GNNs, as it works in a semi-supervised setting for graph data.
Ranked #3 on Node Property Prediction on ogbn-papers100M
no code implementations • NeurIPS 2021 • Jialin Zhao, Yuxiao Dong, Ming Ding, Evgeny Kharlamov, Jie Tang
Notably, message passing based GNNs, e. g., graph convolutional networks, leverage the immediate neighbors of each node during the aggregation process, and recently, graph diffusion convolution (GDC) is proposed to expand the propagation neighborhood by leveraging generalized graph diffusion.
1 code implementation • 8 Nov 2021 • Qinkai Zheng, Xu Zou, Yuxiao Dong, Yukuo Cen, Da Yin, Jiarong Xu, Yang Yang, Jie Tang
To bridge this gap, we present the Graph Robustness Benchmark (GRB) with the goal of providing a scalable, unified, modular, and reproducible evaluation for the adversarial robustness of GML models.
2 code implementations • 17 Aug 2021 • Bo Chen, Jing Zhang, Xiaokang Zhang, Yuxiao Dong, Jian Song, Peng Zhang, Kaibo Xu, Evgeny Kharlamov, Jie Tang
To achieve the contrastive objective, we design a graph neural network encoder that can infer and further remove suspicious links during message passing, as well as learn the global context of the input graph.
1 code implementation • 17 Jun 2021 • Xiao Liu, Haoyun Hong, Xinghao Wang, Zeyi Chen, Evgeny Kharlamov, Yuxiao Dong, Jie Tang
We present SelfKG by leveraging this discovery to design a contrastive learning strategy across two KGs.
1 code implementation • 12 Jun 2021 • Xu Zou, Qinkai Zheng, Yuxiao Dong, Xinyu Guan, Evgeny Kharlamov, Jialiang Lu, Jie Tang
In the GIA scenario, the adversary is not able to modify the existing link structure and node attributes of the input graph, instead the attack is performed by injecting adversarial nodes into it.
5 code implementations • 17 Mar 2021 • Weihua Hu, Matthias Fey, Hongyu Ren, Maho Nakata, Yuxiao Dong, Jure Leskovec
Enabling effective and efficient machine learning (ML) over large-scale graph data (e. g., graphs with billions of edges) can have a great impact on both industrial and scientific applications.
Ranked #1 on Knowledge Graphs on WikiKG90M-LSC
1 code implementation • 4 Mar 2021 • Fanjin Zhang, Jie Tang, Xueyi Liu, Zhenyu Hou, Yuxiao Dong, Jing Zhang, Xiao Liu, Ruobing Xie, Kai Zhuang, Xu Zhang, Leyu Lin, Philip S. Yu
"Top Stories" is a novel friend-enhanced recommendation engine in WeChat, in which users can read articles based on preferences of both their own and their friends.
Graph Representation Learning Social and Information Networks
1 code implementation • 3 Mar 2021 • Xiao Liu, Da Yin, Jingnan Zheng, Xingjian Zhang, Peng Zhang, Hongxia Yang, Yuxiao Dong, Jie Tang
Academic knowledge services have substantially facilitated the development of the science enterprise by providing a plenitude of efficient research tools.
1 code implementation • 1 Mar 2021 • Yukuo Cen, Zhenyu Hou, Yan Wang, Qibin Chen, Yizhen Luo, Zhongming Yu, Hengrui Zhang, Xingcheng Yao, Aohan Zeng, Shiguang Guo, Yuxiao Dong, Yang Yang, Peng Zhang, Guohao Dai, Yu Wang, Chang Zhou, Hongxia Yang, Jie Tang
In CogDL, we propose a unified design for the training and evaluation of GNN models for various graph tasks, making it unique among existing graph learning libraries.
1 code implementation • 15 Feb 2021 • Yu Zhang, Zhihong Shen, Yuxiao Dong, Kuansan Wang, Jiawei Han
Multi-label text classification refers to the problem of assigning each given document its most relevant labels from the label set.
1 code implementation • 1 Jan 2021 • Jialin Zhao, Yuxiao Dong, Jie Tang, Ming Ding, Kuansan Wang
Graph convolutional networks (GCNs) have emerged as a powerful framework for mining and learning with graphs.
1 code implementation • NeurIPS 2020 • Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie Tang
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
2 code implementations • 16 Nov 2020 • Scott Freitas, Yuxiao Dong, Joshua Neil, Duen Horng Chau
With the rapid emergence of graph representation learning, the construction of new large-scale datasets is necessary to distinguish model capabilities and accurately assess the strengths and weaknesses of each technique.
3 code implementations • 27 Jun 2020 • Ziniu Hu, Yuxiao Dong, Kuansan Wang, Kai-Wei Chang, Yizhou Sun
Graph neural networks (GNNs) have been demonstrated to be powerful in modeling graph-structured data.
4 code implementations • 17 Jun 2020 • Jiezhong Qiu, Qibin Chen, Yuxiao Dong, Jing Zhang, Hongxia Yang, Ming Ding, Kuansan Wang, Jie Tang
Graph representation learning has emerged as a powerful technique for addressing real-world problems.
6 code implementations • 22 May 2020 • Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie Tang
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.
16 code implementations • NeurIPS 2020 • Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, Jure Leskovec
We present the Open Graph Benchmark (OGB), a diverse set of challenging and realistic benchmark datasets to facilitate scalable, robust, and reproducible graph machine learning (ML) research.
Ranked #1 on Link Property Prediction on ogbl-citation2
4 code implementations • 3 Mar 2020 • Ziniu Hu, Yuxiao Dong, Kuansan Wang, Yizhou Sun
Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data.
Ranked #17 on Node Property Prediction on ogbn-mag
no code implementations • 25 Sep 2019 • Jie Zhang, Yuxiao Dong, Jie Tang
In this paper, we revisit the mathematical foundation of GCNs and study how to extend their representation capacity.
1 code implementation • 26 Jun 2019 • Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Chi Wang, Kuansan Wang, Jie Tang
Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing a matrix with a closed form, and 2)the explicit factorization of such matrix generates more powerful embeddings than existing methods.
1 code implementation • 15 Jul 2018 • Jiezhong Qiu, Jian Tang, Hao Ma, Yuxiao Dong, Kuansan Wang, Jie Tang
Inspired by the recent success of deep neural networks in a wide range of computing applications, we design an end-to-end framework, DeepInf, to learn users' latent feature representation for predicting social influence.
no code implementations • 13 Feb 2018 • Xian Wu, Baoxu Shi, Yuxiao Dong, Chao Huang, Nitesh Chawla
Neural collaborative filtering (NCF) and recurrent recommender systems (RRN) have been successful in modeling user-item relational data.
no code implementations • ICLR 2018 • Jiezhong Qiu, Hao Ma, Yuxiao Dong, Kuansan Wang, Jie Tang
We study the problem of knowledge base (KB) embedding, which is usually addressed through two frameworks---neural KB embedding and tensor decomposition.
4 code implementations • 9 Oct 2017 • Jiezhong Qiu, Yuxiao Dong, Hao Ma, Jian Li, Kuansan Wang, Jie Tang
This work lays the theoretical foundation for skip-gram based network embedding methods, leading to a better understanding of latent network representation learning.
1 code implementation • KDD 17 2017 • Yuxiao Dong, Nitesh Vijay Chawla, Ananthram Swami
We study the problem of representation learning in heterogeneous networks.
Ranked #5 on Link Prediction on MovieLens 25M
no code implementations • 17 Apr 2017 • Yuxiao Dong, Hao Ma, Zhihong Shen, Kuansan Wang
We find that science has benefited from the shift from individual work to collaborative effort, with over 90% of the world-leading innovations generated by collaborations in this century, nearly four times higher than they were in the 1900s.
Digital Libraries Social and Information Networks Physics and Society
2 code implementations • 15 Dec 2014 • Yuxiao Dong, Reid A. Johnson, Nitesh V. Chawla
The effectiveness of such predictions, however, is fundamentally limited by the power-law distribution of citations, whereby publications with few citations are extremely common and publications with many citations are relatively rare.
Social and Information Networks Digital Libraries Physics and Society H.2.8; H.3.7
no code implementations • 14 Apr 2014 • Yuxiao Dong, Jie Tang, Nitesh Chawla, Tiancheng Lou, Yang Yang, Bai Wang
Our model can predict social status of individuals with 93% accuracy.