1 code implementation • ACL 2022 • Zhe Li, Luoyi Fu, Xinbing Wang, Haisong Zhang, Chenghu Zhou
However, most existing works either ignore the semantic information of relations or predict subjects and objects sequentially.
1 code implementation • 11 Feb 2025 • Lin Zhu, Xinbing Wang, Chenghu Zhou, Qinying Gu, Nanyang Ye
Given a style-reference image as the additional image condition, text-to-image diffusion models have demonstrated impressive capabilities in generating images that possess the content of text prompts while adopting the visual style of the reference image.
no code implementations • 6 Dec 2024 • Peng Yu, Cheng Deng, Beiya Dai, Xinbing Wang, Ying Wen
This paper proposes \textbf{KaLM}, a \textit{Knowledge-aligned Language Modeling} approach, which fine-tunes autoregressive LLMs to align with KG knowledge via the joint objective of explicit knowledge alignment and implicit knowledge alignment.
no code implementations • 3 Dec 2024 • Nanyang Ye, Qiao Sun, Yifei Wang, Liujia Yang, Jundong Zhou, Lei Wang, Guang-Zhong Yang, Xinbing Wang, Chenghu Zhou, Wei Ren, Leilei Gu, Huaqiang Wu, Qinying Gu
Here, we propose a synergistic methodology to concurrently optimize perovskite memristor fabrication and develop robust analog DNNs that effectively address the inherent non-idealities of these memristors.
1 code implementation • 16 Sep 2024 • Huawei Ji, Cheng Deng, Bo Xue, Zhouyang Jin, Jiaxin Ding, Xiaoying Gan, Luoyi Fu, Xinbing Wang, Chenghu Zhou
With the development of data-centric AI, the focus has shifted from model-driven approaches to improving data quality.
no code implementations • 13 Sep 2024 • Shao Zhang, Xihuai Wang, WenHao Zhang, Yongshan Chen, Landi Gao, Dakuo Wang, Weinan Zhang, Xinbing Wang, Ying Wen
Theory of Mind (ToM) significantly impacts human collaboration and communication as a crucial capability to understand others.
no code implementations • 7 Sep 2024 • Yi Xu, Bo Xue, Shuqian Sheng, Cheng Deng, Jiaxin Ding, Zanwei Shen, Luoyi Fu, Xinbing Wang, Chenghu Zhou
Our findings suggest that the representations of large language models hold more potential in quantifying the value of ideas than their generative outputs, demonstrating a promising avenue for automating the idea assessment process.
no code implementations • 13 Aug 2024 • Bo Xue, Yi Xu, Yunchong Song, Yiming Pang, Yuyang Ren, Jiaxin Ding, Luoyi Fu, Xinbing Wang
Traditional knowledge graph completion (KGC) methods rely solely on structural information, struggling with the inherent sparsity of knowledge graphs (KGs).
1 code implementation • 11 Aug 2024 • Jianping Zhou, Junhao Li, Guanjie Zheng, Xinbing Wang, Chenghu Zhou
A key research question is how to ensure imputation consistency, i. e., intra-consistency between observed and imputed values, and inter-consistency between adjacent windows after imputation.
1 code implementation • 22 Jul 2024 • Shiqing Gao, Jiaxin Ding, Luoyi Fu, Xinbing Wang, Chenghu Zhou
The penalty function method has recently been studied as an effective approach for handling constraints, which imposes constraints penalties on the objective to transform the constrained problem into an unconstrained one.
no code implementations • 5 Jun 2024 • Jianping Zhou, Bin Lu, Zhanyu Liu, Siyu Pan, Xuejun Feng, Hua Wei, Guanjie Zheng, Xinbing Wang, Chenghu Zhou
Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data.
1 code implementation • 26 May 2024 • Lin Zhu, Yifeng Yang, Qinying Gu, Xinbing Wang, Chenghu Zhou, Nanyang Ye
In this paper, we propose a novel objective function of OOD detection that also serves to improve OOD generalization.
no code implementations • 12 May 2024 • Bin Lu, Ze Zhao, Luyu Han, Xiaoying Gan, Yuntao Zhou, Lei Zhou, Luoyi Fu, Xinbing Wang, Chenghu Zhou, Jing Zhang
Accurately reconstructing the global ocean deoxygenation over a century is crucial for assessing and protecting marine ecosystem.
1 code implementation • 30 Apr 2024 • Shuqian Sheng, Yi Xu, Tianhang Zhang, Zanwei Shen, Luoyi Fu, Jiaxin Ding, Lei Zhou, Xiaoying Gan, Xinbing Wang, Chenghu Zhou
Besides, previous LLM-based metrics ignore the fact that, within the space of LLM representations, there exist direction vectors that indicate the estimation of text quality.
no code implementations • 11 Apr 2024 • Kailong Wu, Yule Xie, Jiaxin Ding, Yuxiang Ren, Luoyi Fu, Xinbing Wang, Chenghu Zhou
Graph neural networks (GNN) have achieved remarkable success in a wide range of tasks by encoding features combined with topology to create effective representations.
no code implementations • 7 Apr 2024 • Bin Lu, Tingyan Ma, Xiaoying Gan, Xinbing Wang, Yunqiang Zhu, Chenghu Zhou, Shiyu Liang
In synthetic random graphs, we further refine the former lower bound to show the inevitable distortion over time and empirically observe that Smart achieves good estimation performance.
1 code implementation • 23 Mar 2024 • Chensheng Peng, Zhaoyu Zeng, Jinling Gao, Jundong Zhou, Masayoshi Tomizuka, Xinbing Wang, Chenghu Zhou, Nanyang Ye
Multiple object tracking is a critical task in autonomous driving.
no code implementations • 21 Mar 2024 • Shuqian Sheng, Yi Xu, Luoyi Fu, Jiaxin Ding, Lei Zhou, Xinbing Wang, Chenghu Zhou
The majority of automatic metrics for evaluating NLG systems are reference-based.
1 code implementation • 16 Mar 2024 • Hang Yin, Liyao Xiang, Dong Ding, Yuheng He, Yihan Wu, Xinbing Wang, Chenghu Zhou
We investigate the entity alignment (EA) problem with unlabeled dangling cases, meaning that partial entities have no counterparts in the other knowledge graph (KG), and this type of entity remains unlabeled.
no code implementations • 5 Mar 2024 • Xinbing Wang, Luoyi Fu, Xiaoying Gan, Ying Wen, Guanjie Zheng, Jiaxin Ding, Liyao Xiang, Nanyang Ye, Meng Jin, Shiyu Liang, Bin Lu, Haiwen Wang, Yi Xu, Cheng Deng, Shao Zhang, Huquan Kang, Xingli Wang, Qi Li, Zhixin Guo, Jiexing Qi, Pan Liu, Yuyang Ren, Lyuwen Wu, Jungang Yang, Jianping Zhou, Chenghu Zhou
The exponential growth of scientific literature requires effective management and extraction of valuable insights.
2 code implementations • 22 Feb 2024 • Yunchong Song, Siyuan Huang, Xinbing Wang, Chenghu Zhou, Zhouhan Lin
GPN benefits from the discrete assignments generated by the graph parsing algorithm, allowing good memory efficiency while preserving node information intact.
1 code implementation • 7 Feb 2024 • Fan Wu, Jinling Gao, Lanqing Hong, Xinbing Wang, Chenghu Zhou, Nanyang Ye
To address this issue, we propose the Generalizable loss (G-loss), which is an OoD-aware objective, preventing NAS from over-fitting by using gradient descent to optimize parameters not only on a subset of easy-to-learn features but also the remaining predictive features for generalization, and the overall framework is named G-NAS.
1 code implementation • 14 Jan 2024 • Shiming Wang, Zhe Ji, Liyao Xiang, Hao Zhang, Xinbing Wang, Chenghu Zhou, Bo Li
However, such methods can not defend against adaptive attacks, in which an attacker takes a countermove against a known defence strategy.
1 code implementation • 31 Dec 2023 • Zhouhan Lin, Cheng Deng, Le Zhou, Tianhang Zhang, Yi Xu, Yutong Xu, Zhongmou He, Yuanyuan Shi, Beiya Dai, Yunchong Song, Boyi Zeng, Qiyuan Chen, Yuxun Miao, Bo Xue, Shu Wang, Luoyi Fu, Weinan Zhang, Junxian He, Yunqiang Zhu, Xinbing Wang, Chenghu Zhou
To our best knowledge, it is the largest language model for the geoscience domain.
1 code implementation • 18 Dec 2023 • Xilong Zhao, Siyuan Bian, Yaoyun Zhang, Yuliang Zhang, Qinying Gu, Xinbing Wang, Chenghu Zhou, Nanyang Ye
We further demonstrate the effectiveness of the DIL-GP Bayesian optimization method on a PID parameters tuning experiment for a quadrotor.
1 code implementation • 8 Dec 2023 • Boyi Zeng, Lizheng Wang, Yuncong Hu, Yi Xu, Chenghu Zhou, Xinbing Wang, Yu Yu, Zhouhan Lin
In this study, we introduce HuRef, a human-readable fingerprint for LLMs that uniquely identifies the base model without interfering with training or exposing model parameters to the public.
no code implementations • 8 Dec 2023 • Zhixin Guo, Jianping Zhou, Jiexing Qi, Mingxuan Yan, Ziwei He, Guanjie Zheng, Zhouhan Lin, Xinbing Wang, Chenghu Zhou
The sheer volume of scientific experimental results and complex technical statements, often presented in tabular formats, presents a formidable barrier to individuals acquiring preferred information.
1 code implementation • 22 Nov 2023 • Tianhang Zhang, Lin Qiu, Qipeng Guo, Cheng Deng, Yue Zhang, Zheng Zhang, Chenghu Zhou, Xinbing Wang, Luoyi Fu
Large Language Models (LLMs) have gained significant popularity for their impressive performance across diverse fields.
no code implementations • 29 Aug 2023 • Yi Xu, Junjie Ou, Hui Xu, Luoyi Fu, Lei Zhou, Xinbing Wang, Chenghu Zhou
To this end, we investigate the limits of historical information for temporal knowledge graph extrapolation and propose a new event forecasting model called Contrastive Event Network (CENET) based on a novel training framework of historical contrastive learning.
no code implementations • 16 Aug 2023 • Bin Lu, Xiaoying Gan, Ze Zhao, Shiyu Liang, Luoyi Fu, Xinbing Wang, Chenghu Zhou
The spurious correlations over hybrid distribution deviation degrade the performance of previous GNN methods and show large instability among different datasets.
1 code implementation • 8 Jun 2023 • Cheng Deng, Tianhang Zhang, Zhongmou He, Yi Xu, Qiyuan Chen, Yuanyuan Shi, Luoyi Fu, Weinan Zhang, Xinbing Wang, Chenghu Zhou, Zhouhan Lin, Junxian He
Large language models (LLMs) have achieved great success in general domains of natural language processing.
1 code implementation • 5 Jun 2023 • Yang Li, Shao Zhang, Jichen Sun, WenHao Zhang, Yali Du, Ying Wen, Xinbing Wang, Wei Pan
In order to solve cooperative incompatibility in learning and effectively address the problem in the context of ZSC, we introduce the Cooperative Open-ended LEarning (COLE) framework, which formulates open-ended objectives in cooperative games with two players using perspectives of graph theory to evaluate and pinpoint the cooperative capacity of each strategy.
1 code implementation • 4 Jun 2023 • Yi Xu, Shuqian Sheng, Bo Xue, Luoyi Fu, Xinbing Wang, Chenghu Zhou
The results demonstrate that our system has broad prospects and can assist researchers in expediting the process of discovering new ideas.
1 code implementation • 24 May 2023 • Ziwei He, Meng Yang, Minwei Feng, Jingcheng Yin, Xinbing Wang, Jingwen Leng, Zhouhan Lin
Many researchers have focused on designing new forms of self-attention or introducing new parameters to overcome this limitation, however a large portion of them prohibits the model to inherit weights from large pretrained models.
Ranked #1 on
Open-Domain Question Answering
on ELI5
no code implementations • 18 May 2023 • Yichen Zhu, Jian Yuan, Bo Jiang, Tao Lin, Haiming Jin, Xinbing Wang, Chenghu Zhou
We focus on the case where the underlying joint distribution of complete features and label is invariant, but the missing pattern, i. e., mask distribution may shift agnostically between training and testing.
no code implementations • 14 Apr 2023 • Cheng Deng, Jiaxin Ding, Luoyi Fu, Weinan Zhang, Xinbing Wang, Chenghu Zhou
In this work, we propose Covidia, COVID-19 interdisciplinary academic knowledge graph to bridge the gap between knowledge of COVID-19 on different domains.
1 code implementation • 10 Apr 2023 • Yusheng Huang, Jiexing Qi, Xinbing Wang, Zhouhan Lin
We further employ the asymmetric focusing mechanism to decouple the gradient contribution from the negative and positive samples.
no code implementations • 3 Apr 2023 • Cheng Deng, Fan Xu, Jiaxing Ding, Luoyi Fu, Weinan Zhang, Xinbing Wang
Graph representation learning has been widely studied and demonstrated effectiveness in various graph tasks.
2 code implementations • 2 Apr 2023 • Cheng Deng, Bo Tong, Luoyi Fu, Jiaxin Ding, Dexing Cao, Xinbing Wang, Chenghu Zhou
In the research of end-to-end dialogue systems, using real-world knowledge to generate natural, fluent, and human-like utterances with correct answers is crucial.
1 code implementation • 24 Feb 2023 • Zhixin Guo, Minyxuan Yan, Jiexing Qi, Jianping Zhou, Ziwei He, Guanjie Zheng, Xinbing Wang
Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks.
1 code implementation • 19 Feb 2023 • Jiexing Qi, Shuhao Li, Zhixin Guo, Yusheng Huang, Chenghu Zhou, Weinan Zhang, Xinbing Wang, Zhouhan Lin
In this work, we first collect a large-scale institution name normalization dataset LoT-insts1, which contains over 25k classes that exhibit a naturally long-tailed distribution.
Ranked #1 on
Long-tail Learning
on Lot-insts
no code implementations • 9 Feb 2023 • Zhixin Guo, Minyxuan Yan, Jiexing Qi, Jianping Zhou, Ziwei He, Zhouhan Lin, Guanjie Zheng, Xinbing Wang
The design of our framework consists of two aspects: a prompt planner and a knowledge adapter.
1 code implementation • 9 Feb 2023 • Yang Li, Shao Zhang, Jichen Sun, Yali Du, Ying Wen, Xinbing Wang, Wei Pan
However, these approaches can result in a loss of learning and an inability to cooperate with certain strategies within the population, known as cooperative incompatibility.
1 code implementation • 3 Feb 2023 • Yunchong Song, Chenghu Zhou, Xinbing Wang, Zhouhan Lin
This is achieved by aligning the hierarchy of the rooted-tree of a central node with the ordered neurons in its node representation.
Ranked #5 on
Node Classification
on Cornell
1 code implementation • 21 Oct 2022 • Shengyuan Hou, Jushi Kai, Haotian Xue, Bingyu Zhu, Bo Yuan, Longtao Huang, Xinbing Wang, Zhouhan Lin
Recent works have revealed that Transformers are implicitly learning the syntactic information in its lower layers from data, albeit is highly dependent on the quality and scale of the training data.
1 code implementation • 6 Oct 2022 • Shao Zhang, Yuting Jia, Hui Xu, Dakuo Wang, Toby Jia-Jun Li, Ying Wen, Xinbing Wang, Chenghu Zhou
Constructing a comprehensive, accurate, and useful scientific knowledge base is crucial for human researchers synthesizing scientific knowledge and for enabling Al-driven scientific discovery.
no code implementations • 27 Sep 2022 • Qi Li, Yuyang Ren, Xingli Wang, Luoyi Fu, Jiaxin Ding, Xinde Cao, Xinbing Wang, Chenghu Zhou
Understanding the origin and influence of the publication's idea is critical to conducting scientific research.
no code implementations • 22 Sep 2022 • Yi Xu, Luoyi Fu, Zhouhan Lin, Jiexing Qi, Xinbing Wang
As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks.
no code implementations • 4 Sep 2022 • Yuyang Ren, Haonan Zhang, Qi Li, Luoyi Fu, Jiaxin Ding, Xinde Cao, Xinbing Wang, Chenghu Zhou
In review-based recommendation methods, review data is considered as auxiliary information that can improve the quality of learned user/item or interaction representations for the user rating prediction task.
1 code implementation • 27 May 2022 • Bin Lu, Xiaoying Gan, Weinan Zhang, Huaxiu Yao, Luoyi Fu, Xinbing Wang
To address this challenge, cross-city knowledge transfer has shown its promise, where the model learned from data-sufficient cities is leveraged to benefit the learning process of data-scarce cities.
1 code implementation • 27 May 2022 • Bin Lu, Xiaoying Gan, Lina Yang, Weinan Zhang, Luoyi Fu, Xinbing Wang
Instead of replacing and retraining the fully connected neural network classifer, Geometer predicts the label of a node by finding the nearest class prototype.
class-incremental learning
Few-Shot Class-Incremental Learning
+4
1 code implementation • 14 May 2022 • Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Yu Cheng, Chenghu Zhou, Xinbing Wang, Quanshi Zhang, Zhouhan Lin
Our model can incorporate almost all types of existing relations in the literature, and in addition, we propose introducing co-reference relations for the multi-turn scenario.
Ranked #1 on
Dialogue State Tracking
on CoSQL
1 code implementation • ACL 2022 • Xichen Pan, Peiyu Chen, Yichen Gong, Helong Zhou, Xinbing Wang, Zhouhan Lin
In particular, audio and visual front-ends are trained on large-scale unimodal datasets, then we integrate components of both front-ends into a larger multimodal framework which learns to recognize parallel audio-visual data into characters through a combination of CTC and seq2seq decoding.
Ranked #3 on
Automatic Speech Recognition (ASR)
on LRS2
Audio-Visual Speech Recognition
Automatic Speech Recognition (ASR)
+7
no code implementations • 21 Feb 2022 • Shao Zhang, Yuting Jia, Hui Xu, Ying Wen, Dakuo Wang, Xinbing Wang
Geoscientists, as well as researchers in many fields, need to read a huge amount of literature to locate, extract, and aggregate relevant results and data to enable future research or to build a scientific database, but there is no existing system to support this use case well.
1 code implementation • Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2021 • Dixi Yao, Liyao Xiang, Zifan Wang, Jiayu Xu, Chao Li, Xinbing Wang
Experimental results show that our system not only adapts well to, but also draws on the varying contexts, delivering a practical and efficient solution to edge-cloud model training.
Ranked #2 on
Recommendation Systems
on MovieLens 1M
(Precision metric)
4 code implementations • 10 Nov 2021 • Zhaoxing Yang, Rong Ding, Haiming Jin, Yifei Wei, Haoyi You, Guiyun Fan, Xiaoying Gan, Xinbing Wang
In addition, with such modularization, the training algorithm of DeCOM separates the original constrained optimization into an unconstrained optimization on reward and a constraints satisfaction problem on costs.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
no code implementations • 5 Oct 2021 • Yichen Zhu, Bo Jiang, Haiming Jin, Mengtian Zhang, Feng Gao, Jianqiang Huang, Tao Lin, Xinbing Wang
An important task in such applications is to predict the future values of a NETS based on its historical values and the underlying graph.
no code implementations • 24 Jun 2021 • Yuchen Li, Yifan Bao, Liyao Xiang, Junhan Liu, Cen Chen, Li Wang, Xinbing Wang
Federated learning is emerging as a machine learning technique that trains a model across multiple decentralized parties.
no code implementations • 30 Apr 2021 • Jungang Yang, Liyao Xiang, Weiting Li, Wei Liu, Xinbing Wang
The wide deployment of machine learning in recent years gives rise to a great demand for large-scale and high-dimensional data, for which the privacy raises serious concern.
no code implementations • 13 Jan 2021 • Shuhan Yan, Yuting Jia, Xinbing Wang
Analyzing the groups in the network based on same attributes, functions or connections between nodes is a way to understand network information.
no code implementations • 1 Jan 2021 • Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing Wang
We focus on certified robustness of smoothed classifiers in this work, and propose to use the worst-case population loss over noisy inputs as a robustness metric.
no code implementations • International Conference on Distributed Computing Systems 2020 • Lingdong Wang, Liyao Xiang, Jiayu Xu, Jiaju Chen, Xing Zhao, Dixi Yao, Xinbing Wang, Baochun Li
While deep neural networks (DNNs) have led to a paradigm shift, its exorbitant computational requirement has always been a roadblock in its deployment to the edge, such as wearable devices and smartphones.
Ranked #186 on
Image Classification
on CIFAR-10
no code implementations • 21 Oct 2020 • Jungang Yang, Liyao Xiang, Ruidong Chen, Yukun Wang, Wei Wang, Xinbing Wang
For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate.
no code implementations • 9 Oct 2020 • Hui Xu, Liyao Xiang, Youmin Le, Xiaoying Gan, Yuting Jia, Luoyi Fu, Xinbing Wang
Iterated line graphs are introduced for the first time to describe such high-order information, based on which we present a new graph matching method, called High-order Graph Matching Network (HGMN), to learn not only the local structural correspondence, but also the hyperedge relations across graphs.
no code implementations • 4 Sep 2020 • Chang Liu, Jiahui Sun, Haiming Jin, Meng Ai, Qun Li, Cheng Zhang, Kehua Sheng, Guobin Wu, XiaoHu Qie, Xinbing Wang
Thus, in this paper, we exploit adaptive dispatching intervals to boost the platform's profit under a guarantee of the maximum passenger waiting time.
no code implementations • 2 Apr 2019 • Yuting Jia, Haiwen Wang, Shuo Shao, Huan Long, Yunsong Zhou, Xinbing Wang
Based on this new algorithm, four common geometric properties shared by the activation spaces are concluded, which gives a rather clear description of the activation spaces.
1 code implementation • 20 Jan 2019 • Yuting Jia, Qinqin Zhang, Wei-Nan Zhang, Xinbing Wang
In this paper, we propose CommunityGAN, a novel community detection framework that jointly solves overlapping community detection and graph representation learning.
Ranked #1 on
Clique Prediction
on arXiv-GrQc 3-clique
no code implementations • 23 Jul 2018 • Ruijie Wang, Yuchen Yan, Jialu Wang, Yuting Jia, Ye Zhang, Wei-Nan Zhang, Xinbing Wang
Most existing knowledge graphs (KGs) in academic domains suffer from problems of insufficient multi-relational information, name ambiguity and improper data format for large-scale machine processing.
no code implementations • 2 Oct 2016 • Junxian He, Ying Huang, Changfeng Liu, Jiaming Shen, Yuting Jia, Xinbing Wang
A text network refers to a data type that each vertex is associated with a text document and the relationship between documents is represented by edges.