1 code implementation • EMNLP (insights) 2021 • Qi Zhu, Yuxian Gu, Lingxiao Luo, Bing Li, Cheng Li, Wei Peng, Minlie Huang, Xiaoyan Zhu
Further pre-training language models on in-domain data (domain-adaptive pre-training, DAPT) or task-relevant data (task-adaptive pre-training, TAPT) before fine-tuning has been shown to improve downstream tasks’ performances.
no code implementations • 22 Jun 2022 • Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina McMillan-Major, Anna Shvets, Ashish Upadhyay, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez-Beltrachini, Leonardo F. R. Ribeiro, Lewis Tunstall, Li Zhang, Mahima Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
no code implementations • 27 May 2022 • Ruochen Jiao, Xiangguo Liu, Takami Sato, Qi Alfred Chen, Qi Zhu
Predicting the trajectories of surrounding objects is a critical task in self-driving and many other autonomous systems.
no code implementations • 20 May 2022 • Bowen Jin, Yu Zhang, Qi Zhu, Jiawei Han
We study node representation learning on heterogeneous text-rich networks, where nodes and edges are multi-typed and some types of nodes are associated with text information.
no code implementations • 11 Apr 2022 • Haonan Wang, Jieyu Zhang, Qi Zhu, Wei Huang
Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data.
no code implementations • 26 Mar 2022 • Zhilu Wang, Chao Huang, Qi Zhu
The robustness of deep neural networks has received significant interest recently, especially when being deployed in safety-critical systems, as it is important to analyze how sensitive the model output is under input perturbations.
1 code implementation • CVPR 2022 • Jiahua Dong, Lixu Wang, Zhen Fang, Gan Sun, Shichao Xu, Xiao Wang, Qi Zhu
It makes the global model suffer from significant catastrophic forgetting on old classes in real-world scenarios, where local clients often collect new classes continuously and have very limited storage memory to store old classes.
1 code implementation • ACL 2022 • Qi Zhu, Bing Li, Fei Mi, Xiaoyan Zhu, Minlie Huang
A desirable dialog system should be able to continually learn new skills without forgetting old ones, and thereby adapt to new domains or tasks in its life cycle.
no code implementations • 7 Mar 2022 • Qi Zhu, Chao Zhang, Chanyoung Park, Carl Yang, Jiawei Han
Then a shift-robust classifier is optimized on training graph and adversarial samples on target graph, which are generated by cluster GNN.
no code implementations • 2 Mar 2022 • Ruochen Jiao, Xiangguo Liu, Bowen Zheng, Dave Liang, Qi Zhu
Our model addresses trajectory generation and prediction in a unified architecture and benefits both tasks: the model can generate diverse, controllable and realistic trajectories to enhance planner optimization in safety-critical and long-tailed scenarios, and it can provide prediction of critical behavior in addition to the final trajectories for decision making.
no code implementations • 28 Jan 2022 • YiXuan Wang, Chao Huang, Zhaoran Wang, Zhuoran Yang, Qi Zhu
In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e. g., safety, stability) under the learned controller.
1 code implementation • NeurIPS 2021 • Qi Zhu, Natalia Ponomareva, Jiawei Han, Bryan Perozzi
In this work we present a method, Shift-Robust GNN (SR-GNN), designed to account for distributional differences between biased training data and the graph's true inference distribution.
1 code implementation • 18 Jul 2021 • Rumia Masburah, Sayan Sinha, Rajib Lochan Jana, Soumyajit Dey, Qi Zhu
Building loads consume roughly 40% of the energy produced in developed countries, a significant part of which is invested towards building temperature-control infrastructure.
no code implementations • 27 Jun 2021 • Shichao Xu, Yangyang Fu, YiXuan Wang, Zheng O'Neill, Qi Zhu
As people spend up to 87% of their time indoors, intelligent Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings are essential for maintaining occupant comfort and reducing energy consumption.
1 code implementation • 25 Jun 2021 • Chao Huang, Jiameng Fan, Xin Chen, Wenchao Li, Qi Zhu
We propose POLAR, a \textbf{pol}ynomial \textbf{ar}ithmetic framework that leverages polynomial overapproximations with interval remainders for bounded-time reachability analysis of neural network-controlled systems (NNCSs).
1 code implementation • ICLR 2022 • Lixu Wang, Shichao Xu, Ruiqi Xu, Xiao Wang, Qi Zhu
Our NTL-based authorization approach instead provides data-centric protection, which we call applicability authorization, by significantly degrading the performance of the model on unauthorized data.
no code implementations • 6 Jun 2021 • YiXuan Wang, Chao Huang, Zhaoran Wang, Zhilu Wang, Qi Zhu
Specifically, we leverage the verification results (computed reachable set of the system state) to construct feedback metrics for control learning, which measure how likely the current design of control parameters can meet the required reach-avoid property for safety and goal-reaching.
no code implementations • 30 Apr 2021 • Chenyu Gao, Qi Zhu, Peng Wang, Qi Wu
Based on this observation, we design a dynamic chopping module that can automatically remove heads and layers of the VisualBERT at an instance level when dealing with different questions.
no code implementations • 27 Feb 2021 • Ruochen Jiao, Hengyi Liang, Takami Sato, Junjie Shen, Qi Alfred Chen, Qi Zhu
The experiment results demonstrate that our approach can effectively mitigate the impact of adversarial attacks and can achieve 55% to 90% improvement over the original OpenPilot.
no code implementations • 15 Feb 2021 • Shichao Xu, Lixu Wang, YiXuan Wang, Qi Zhu
Data quantity and quality are crucial factors for data-driven learning methods.
no code implementations • 15 Feb 2021 • Xiangguo Liu, Baiting Luo, Ahmed Abdo, Nael Abu-Ghazaleh, Qi Zhu
While connected vehicle (CV) applications have the potential to revolutionize traditional transportation system, cyber and physical attacks on them could be devastating.
Cryptography and Security
no code implementations • ICCV 2021 • Shichao Xu, Lixu Wang, YiXuan Wang, Qi Zhu
Data quantity and quality are crucial factors for data-driven learning methods.
1 code implementation • 9 Dec 2020 • Qi Zhu, Chenyu Gao, Peng Wang, Qi Wu
Texts appearing in daily scenes that can be recognized by OCR (Optical Character Recognition) tools contain significant information, such as street name, product brand and prices.
1 code implementation • 12 Nov 2020 • Chulaka Gunasekara, Seokhwan Kim, Luis Fernando D'Haro, Abhinav Rastogi, Yun-Nung Chen, Mihail Eric, Behnam Hedayatnia, Karthik Gopalakrishnan, Yang Liu, Chao-Wei Huang, Dilek Hakkani-Tür, Jinchao Li, Qi Zhu, Lingxiao Luo, Lars Liden, Kaili Huang, Shahin Shayandeh, Runze Liang, Baolin Peng, Zheng Zhang, Swadheen Shukla, Minlie Huang, Jianfeng Gao, Shikib Mehri, Yulan Feng, Carla Gordon, Seyed Hossein Alavi, David Traum, Maxine Eskenazi, Ahmad Beirami, Eunjoon, Cho, Paul A. Crook, Ankita De, Alborz Geramifard, Satwik Kottur, Seungwhan Moon, Shivani Poddar, Rajen Subba
Interactive evaluation of dialog, and 4.
1 code implementation • NeurIPS 2021 • Qi Zhu, Carl Yang, Yidan Xu, Haonan Wang, Chao Zhang, Jiawei Han
Graph neural networks (GNNs) have achieved superior performance in various applications, but training dedicated GNNs can be costly for large-scale graphs.
2 code implementations • 14 Aug 2020 • Lixu Wang, Shichao Xu, Xiao Wang, Qi Zhu
Our experiments demonstrate the importance of acknowledging class imbalance and taking measures as early as possible in FL training, and the effectiveness of our method in mitigating the impact.
1 code implementation • 10 Aug 2020 • Shuyue Lan, Zhilu Wang, Amit K. Roy-Chowdhury, Ermin Wei, Qi Zhu
In many intelligent systems, a network of agents collaboratively perceives the environment for better and more efficient situation awareness.
no code implementations • 9 Aug 2020 • Shichao Xu, Yi-Xuan Wang, Yanzhi Wang, Zheng O'Neill, Qi Zhu
Traditional HVAC control methods are typically based on creating explicit physical models for building thermal dynamics, which often require significant effort to develop and are difficult to achieve sufficient accuracy and efficiency for runtime building control and scalability for field implementations.
1 code implementation • 7 Jun 2020 • Chanyoung Park, Carl Yang, Qi Zhu, Donghyun Kim, Hwanjo Yu, Jiawei Han
To capture the multiple aspects of each node, existing studies mainly rely on offline graph clustering performed prior to the actual embedding, which results in the cluster membership of each node (i. e., node aspect distribution) fixed throughout training of the embedding model.
2 code implementations • 1 Jun 2020 • Chenyu Gao, Qi Zhu, Peng Wang, Hui Li, Yuliang Liu, Anton Van Den Hengel, Qi Wu
In this paper, we propose an end-to-end structured multimodal attention (SMA) neural network to mainly solve the first two issues above.
no code implementations • SIGDIAL (ACL) 2020 • Ryuichi Takanobu, Qi Zhu, Jinchao Li, Baolin Peng, Jianfeng Gao, Minlie Huang
There is a growing interest in developing goal-oriented dialog systems which serve users in accomplishing complex tasks through multi-turn conversations.
no code implementations • 17 Mar 2020 • Zheng Zhang, Ryuichi Takanobu, Qi Zhu, Minlie Huang, Xiaoyan Zhu
Due to the significance and value in human-computer interaction and natural language processing, task-oriented dialog systems are attracting more and more attention in both academic and industrial communities.
2 code implementations • TACL 2020 • Qi Zhu, Kaili Huang, Zheng Zhang, Xiaoyan Zhu, Minlie Huang
To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset.
1 code implementation • ACL 2020 • Qi Zhu, Zheng Zhang, Yan Fang, Xiang Li, Ryuichi Takanobu, Jinchao Li, Baolin Peng, Jianfeng Gao, Xiaoyan Zhu, Minlie Huang
We present ConvLab-2, an open-source toolkit that enables researchers to build task-oriented dialogue systems with state-of-the-art models, perform an end-to-end evaluation, and diagnose the weakness of systems.
no code implementations • 14 Oct 2019 • Lixu Wang, Shichao Xu, Xiao Wang, Qi Zhu
Federated learning (FL) has recently emerged as a new form of collaborative machine learning, where a common model can be learned while keeping all the training data on local devices.
1 code implementation • 4 Sep 2019 • Yu Shi, Jiaming Shen, Yuchen Li, Naijing Zhang, Xinwei He, Zhengzhi Lou, Qi Zhu, Matthew Walker, Myunghwan Kim, Jiawei Han
Extensive experiments on two large real-world datasets demonstrate the effectiveness of HyperMine and the utility of modeling context granularity.
1 code implementation • ACL 2020 • Yuning Mao, Liyuan Liu, Qi Zhu, Xiang Ren, Jiawei Han
In this paper, we present a facet-aware evaluation setup for better assessment of the information coverage in extracted summaries.
no code implementations • 15 Jul 2019 • Shichao Xu, Shuyue Lan, Qi Zhu
Instance segmentation is a promising yet challenging topic in computer vision.
1 code implementation • 25 Jun 2019 • Chao Huang, Jiameng Fan, Wenchao Li, Xin Chen, Qi Zhu
In this work, we propose a new reachability analysis approach based on Bernstein polynomials that can verify neural-network controlled systems with a more general form of activation functions, i. e., as long as they ensure that the neural networks are Lipschitz continuous.
1 code implementation • 4 Jun 2019 • Chanyoung Park, Donghyun Kim, Qi Zhu, Jiawei Han, Hwanjo Yu
In this paper, we propose a novel task-guided pair embedding framework in heterogeneous network, called TaPEm, that directly models the relationship between a pair of nodes that are related to a specific task (e. g., paper-author relationship in author identification).
2 code implementations • ACL 2019 • Sungjin Lee, Qi Zhu, Ryuichi Takanobu, Xiang Li, Yaoqin Zhang, Zheng Zhang, Jinchao Li, Baolin Peng, Xiujun Li, Minlie Huang, Jianfeng Gao
We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems to end-to-end neural models, in common environments.
1 code implementation • 10 Jul 2018 • Yu Shi, Qi Zhu, Fang Guo, Chao Zhang, Jiawei Han
To cope with the challenges in the comprehensive transcription of HINs, we propose the HEER algorithm, which embeds HINs via edge representations that are further coupled with properly-learned heterogeneous metrics.
1 code implementation • CVPR 2018 • Shuyue Lan, Rameswar Panda, Qi Zhu, Amit K. Roy-Chowdhury
The first group is supported by video summarization techniques, which require processing of the entire video to select an important subset for showing to users.
1 code implementation • 26 Apr 2018 • Qi Zhu, Xiang Ren, Jingbo Shang, Yu Zhang, Ahmed El-Kishky, Jiawei Han
However, current Open IE systems focus on modeling local context information in a sentence to extract relation tuples, while ignoring the fact that global statistics in a large corpus can be collectively leveraged to identify high-quality sentence-level extractions.
no code implementations • 9 Mar 2018 • Huan Gui, Qi Zhu, Liyuan Liu, Aston Zhang, Jiawei Han
We study the task of expert finding in heterogeneous bibliographical networks based on two aspects: textual content analysis and authority ranking.
no code implementations • 5 Mar 2018 • Yu Shi, Huan Gui, Qi Zhu, Lance Kaplan, Jiawei Han
Therefore, we are motivated to propose a novel embedding learning framework---AspEm---to preserve the semantic information in HINs based on multiple aspects.
no code implementations • 10 Oct 2017 • Hongjia Li, Tianshu Wei, Ao Ren, Qi Zhu, Yanzhi Wang
The recent breakthroughs of deep reinforcement learning (DRL) technique in Alpha Go and playing Atari have set a good example in handling large state and actions spaces of complicated control problems.
1 code implementation • EMNLP 2017 • Liyuan Liu, Xiang Ren, Qi Zhu, Shi Zhi, Huan Gui, Heng Ji, Jiawei Han
These annotations, referred as heterogeneous supervision, often conflict with each other, which brings a new challenge to the original relation extraction task: how to infer the true label from noisy labels for a given instance.
no code implementations • 21 May 2016 • Shu Zhang, Qi Zhu, Amit Roy-Chowdhury
In this paper, we focus on this problem and propose a framework to adaptively select the "best" algorithm-parameter combination and the computation platform under performance and cost constraints at design time, and adapt the algorithms at runtime based on real-time inputs.