Search Results for author: Jing Jiang

Found 136 papers, 57 papers with code

Coupled Hierarchical Transformer for Stance-Aware Rumor Verification in Social Media Conversations

no code implementations EMNLP 2020 Jianfei Yu, Jing Jiang, Ling Min Serena Khoo, Hai Leong Chieu, Rui Xia

The prevalent use of social media enables rapid spread of rumors on a massive scale, which leads to the emerging need of automatic rumor verification (RV).

Multi-Task Learning Stance Classification

Learning and Evaluating Chinese Idiom Embeddings

1 code implementation RANLP 2021 Minghuan Tan, Jing Jiang

We find that our method substantially outperforms existing methods on the evaluation dataset we have constructed.

Continual Task Allocation in Meta-Policy Network via Sparse Prompting

1 code implementation29 May 2023 Yijun Yang, Tianyi Zhou, Jing Jiang, Guodong Long, Yuhui Shi

We address it by "Continual Task Allocation via Sparse Prompting (CoTASP)", which learns over-complete dictionaries to produce sparse masks as prompts extracting a sub-network for each task from a meta-policy network.

Modularized Zero-shot VQA with Pre-trained Models

no code implementations27 May 2023 Rui Cao, Jing Jiang

We propose a modularized zero-shot network that explicitly decomposes questions into sub reasoning steps and is highly interpretable.

object-detection Object Detection +3

Spatial-temporal Prompt Learning for Federated Weather Forecasting

no code implementations23 May 2023 Shengchao Chen, Guodong Long, Tao Shen, Tianyi Zhou, Jing Jiang

Federated weather forecasting is a promising collaborative learning framework for analyzing meteorological data across participants from different countries and regions, thus embodying a global-scale real-time weather data predictive analytics platform to tackle climate change.

Weather Forecasting

Does Continual Learning Equally Forget All Parameters?

no code implementations9 Apr 2023 Haiyan Zhao, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

In this paper, we study which modules in neural networks are more prone to forgetting by investigating their training dynamics during CL.

Continual Learning

Adaptive Policy Learning for Offline-to-Online Reinforcement Learning

no code implementations14 Mar 2023 Han Zheng, Xufang Luo, Pengfei Wei, Xuan Song, Dongsheng Li, Jing Jiang

In this paper, we consider an offline-to-online setting where the agent is first learned from the offline dataset and then trained online, and propose a framework called Adaptive Policy Learning for effectively taking advantage of offline and online data.

Continuous Control Offline RL +2

Prompting for Multimodal Hateful Meme Classification

no code implementations8 Feb 2023 Rui Cao, Roy Ka-Wei Lee, Wen-Haw Chong, Jing Jiang

Specifically, we construct simple prompts and provide a few in-context examples to exploit the implicit knowledge in the pre-trained RoBERTa language model for hateful meme classification.

Classification Language Modelling +1

Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks

no code implementations27 Jan 2023 Haiyan Zhao, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

To address these challenges, we create a small model for a new task from the pruned models of similar tasks.

Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data

1 code implementation22 Jan 2023 Shengchao Chen, Guodong Long, Tao Shen, Jing Jiang

To relieve the data exposure concern across regions, a novel federated learning approach has been proposed to collaboratively learn a brand-new spatio-temporal Transformer-based foundation model across participants with heterogeneous meteorological data.

Federated Learning Time Series Analysis +1

P-Transformer: Towards Better Document-to-Document Neural Machine Translation

no code implementations12 Dec 2022 Yachao Li, Junhui Li, Jing Jiang, Shimin Tao, Hao Yang, Min Zhang

To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative position information in both self-attention and cross-attention.

Machine Translation NMT +1

Federated Learning on Non-IID Graphs via Structural Knowledge Sharing

1 code implementation23 Nov 2022 Yue Tan, Yixin Liu, Guodong Long, Jing Jiang, Qinghua Lu, Chengqi Zhang

Inspired by this, we propose FedStar, an FGL framework that extracts and shares the common underlying structure information for inter-graph federated learning tasks.

Federated Learning Graph Learning

CCPrompt: Counterfactual Contrastive Prompt-Tuning for Many-Class Classification

no code implementations11 Nov 2022 Yang Li, Canran Xu, Tao Shen, Jing Jiang, Guodong Long

The sharing task description is unable to stimulate the unique task-related information in each training sample, especially for tasks with the finite-label space.

Classification Entity Typing +5

ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation

no code implementations COLING 2022 Cunxiao Du, Zhaopeng Tu, Longyue Wang, Jing Jiang

Recently, a new training oaxe loss has proven effective to ameliorate the effect of multimodality for non-autoregressive translation (NAT), which removes the penalty of word order errors in the standard cross-entropy loss.

Machine Translation Translation

Federated Learning from Pre-Trained Models: A Contrastive Learning Approach

no code implementations21 Sep 2022 Yue Tan, Guodong Long, Jie Ma, Lu Liu, Tianyi Zhou, Jing Jiang

To prevent these issues from hindering the deployment of FL systems, we propose a lightweight framework where clients jointly learn to fuse the representations generated by multiple fixed pre-trained models rather than training a large-scale model from scratch.

Contrastive Learning Federated Learning

Improving Compositional Generalization in Math Word Problem Solving

1 code implementation3 Sep 2022 Yunshi Lan, Lei Wang, Jing Jiang, Ee-Peng Lim

To improve the compositional generalization in MWP solving, we propose an iterative data augmentation method that includes diverse compositional variation into training data and could collaborate with MWP methods.

Data Augmentation Math Word Problem Solving

Disentangling Identity and Pose for Facial Expression Recognition

no code implementations17 Aug 2022 Jing Jiang, Weihong Deng

Combining identity and pose feature, a neutral face of input individual should be generated by the decoder.

Disentanglement Face Recognition +1

Unsupervised Video Domain Adaptation: A Disentanglement Perspective

1 code implementation15 Aug 2022 Pengfei Wei, Lingdong Kong, Xinghua Qu, Xiang Yin, Zhiqiang Xu, Jing Jiang, Zejun Ma

Specifically, we consider the generation of cross-domain videos from two sets of latent factors, one encoding the static domain-related information and another encoding the temporal and semantic-related information.

Disentanglement Unsupervised Domain Adaptation +1

Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher

no code implementations28 May 2022 Jing Jiang, Weihong Deng

On the one hand, PT introduces semi-supervised learning method to relieve the shortage of data in FER.

Facial Expression Recognition (FER)

FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels

no code implementations20 May 2022 Zhuowei Wang, Tianyi Zhou, Guodong Long, Bo Han, Jing Jiang

Federated learning (FL) aims at training a global model on the server side while the training data are collected and located at the local devices.

Federated Learning Learning with noisy labels

An Empirical Study of Memorization in NLP

1 code implementation ACL 2022 Xiaosen Zheng, Jing Jiang

We empirically show that our memorization attribution method is faithful, and share our interesting finding that the top-memorized parts of a training instance tend to be features negatively correlated with the class label.


Personalized Federated Learning With Graph

1 code implementation2 Mar 2022 Fengwen Chen, Guodong Long, Zonghan Wu, Tianyi Zhou, Jing Jiang

We propose a novel structured federated learning (SFL) framework to learn both the global and personalized models simultaneously using client-wise relation graphs and clients' private data.

Personalized Federated Learning

Applications of blockchain and artificial intelligence technologies for enabling prosumers in smart grids: A review

no code implementations21 Feb 2022 Weiqi Hua, Ying Chen, Meysam Qadrdan, Jing Jiang, Hongjian Sun, Jianzhong Wu

The blockchain and artificial intelligence (AI) are innovative technologies to fulfil these two factors, by which the blockchain provides decentralised trading platforms for energy markets and the AI supports the optimal operational control of power systems.

Decision Making

On the Convergence of Clustered Federated Learning

1 code implementation13 Feb 2022 Jie Ma, Guodong Long, Tianyi Zhou, Jing Jiang, Chengqi Zhang

Knowledge sharing and model personalization are essential components to tackle the non-IID challenge in federated learning (FL).

Federated Learning

CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum

1 code implementation NeurIPS 2021 Shuang Ao, Tianyi Zhou, Guodong Long, Qinghua Lu, Liming Zhu, Jing Jiang

Next, a bottom-up traversal of the tree trains the RL agent from easier sub-tasks with denser rewards on bottom layers to harder ones on top layers and collects its cost on each sub-task train the planner in the next episode.

Continuous Control reinforcement-learning +1

SCORE: Spurious COrrelation REduction for Offline Reinforcement Learning

1 code implementation24 Oct 2021 Zhihong Deng, Zuyue Fu, Lingxiao Wang, Zhuoran Yang, Chenjia Bai, Zhaoran Wang, Jing Jiang

Offline reinforcement learning (RL) aims to learn the optimal policy from a pre-collected dataset without online interactions.

Offline RL reinforcement-learning +1

Pareto Policy Pool for Model-based Offline Reinforcement Learning

no code implementations ICLR 2022 Yijun Yang, Jing Jiang, Tianyi Zhou, Jie Ma, Yuhui Shi

Model-based offline RL instead trains an environment model using a dataset of pre-collected experiences so online RL methods can learn in an offline manner by solely interacting with the model.

D4RL Offline RL +2

Uncertainty Regularized Policy Learning for Offline Reinforcement Learning

no code implementations29 Sep 2021 Han Zheng, Jing Jiang, Pengfei Wei, Guodong Long, Xuan Song, Chengqi Zhang

URPL adds an uncertainty regularization term in the policy learning objective to enforce to learn a more stable policy under the offline setting.

D4RL Offline RL +2

Vote for Nearest Neighbors Meta-Pruning of Self-Supervised Networks

no code implementations29 Sep 2021 Haiyan Zhao, Tianyi Zhou, Guodong Long, Jing Jiang, Liming Zhu, Chengqi Zhang

Can we find a better initialization for a new task, e. g., a much smaller network closer to the final pruned model, by exploiting its similar tasks?

Digital Twins based Day-ahead Integrated Energy System Scheduling under Load and Renewable Energy Uncertainties

no code implementations29 Sep 2021 Minglei You, Qian Wang, Hongjian Sun, Ivan Castro, Jing Jiang

By constructing digital twins (DT) of an integrated energy system (IES), one can benefit from DT's predictive capabilities to improve coordinations among various energy converters, hence enhancing energy efficiency, cost savings and carbon emission reduction.


EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning

no code implementations29 Sep 2021 Shuang Ao, Tianyi Zhou, Jing Jiang, Guodong Long, Xuan Song, Chengqi Zhang

They are complementary in acquiring more informative feedback for RL: the planning policy provides dense reward of finishing easier sub-tasks while the environment policy modifies these sub-tasks to be adequately challenging and diverse so the RL agent can quickly adapt to different tasks/environments.

reinforcement-learning Reinforcement Learning (RL)

Adaptive Q-learning for Interaction-Limited Reinforcement Learning

no code implementations29 Sep 2021 Han Zheng, Xufang Luo, Pengfei Wei, Xuan Song, Dongsheng Li, Jing Jiang

Specifically, we explicitly consider the difference between the online and offline data and apply an adaptive update scheme accordingly, i. e., a pessimistic update strategy for the offline dataset and a greedy or no pessimistic update scheme for the online dataset.

Offline RL Q-Learning +2

NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset

1 code implementation Findings (EMNLP) 2021 Qiyuan Zhang, Lei Wang, Sicheng Yu, Shuohang Wang, Yang Wang, Jing Jiang, Ee-Peng Lim

While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects.

Graph Question Answering Question Answering

Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision

no code implementations Findings (NAACL) 2022 Yang Li, Guodong Long, Tao Shen, Jing Jiang

It consists of (1) a pairwise type-enriched sentence encoding module injecting both context-free and -related backgrounds to alleviate sentence-level wrong labeling, and (2) a hierarchical type-sentence alignment module enriching a sentence with the triple fact's basic attributes to support long-tail relations.

Knowledge Graphs Relation Extraction +1

Sequential Diagnosis Prediction with Transformer and Ontological Representation

1 code implementation7 Sep 2021 Xueping Peng, Guodong Long, Tao Shen, Sen Wang, Jing Jiang

Sequential diagnosis prediction on the Electronic Health Record (EHR) has been proven crucial for predictive analytics in the medical domain.

Sequential Diagnosis

Federated Learning for Privacy-Preserving Open Innovation Future on Digital Health

no code implementations24 Aug 2021 Guodong Long, Tao Shen, Yue Tan, Leah Gerrard, Allison Clarke, Jing Jiang

Implementing an open innovation framework in the healthcare industry, namely open health, is to enhance innovation and creative capability of health-related organisations by building a next-generation collaborative framework with partner organisations and the research community.

Federated Learning Privacy Preserving

Federated Learning for Open Banking

no code implementations24 Aug 2021 Guodong Long, Yue Tan, Jing Jiang, Chengqi Zhang

In the near future, it is foreseeable to have decentralized data ownership in the finance sector using federated learning.

Federated Learning

Multi-Center Federated Learning: Clients Clustering for Better Personalization

1 code implementation19 Aug 2021 Guodong Long, Ming Xie, Tao Shen, Tianyi Zhou, Xianzhi Wang, Jing Jiang, Chengqi Zhang

By comparison, a mixture of multiple global models could capture the heterogeneity across various clients if assigning the client to different global models (i. e., centers) in FL.

Decision Making Federated Learning

Disentangling Hate in Online Memes

no code implementations9 Aug 2021 Rui Cao, Ziqing Fan, Roy Ka-Wei Lee, Wen-Haw Chong, Jing Jiang

Our experiment results show that DisMultiHate is able to outperform state-of-the-art unimodal and multimodal baselines in the hateful meme classification task.

Classification Meme Classification

COSY: COunterfactual SYntax for Cross-Lingual Understanding

1 code implementation ACL 2021 Sicheng Yu, Hao Zhang, Yulei Niu, Qianru Sun, Jing Jiang

Pre-trained multilingual language models, e. g., multilingual-BERT, are widely used in cross-lingual tasks, yielding the state-of-the-art performance.

Natural Language Inference POS +2

Modeling Transitions of Focal Entities for Conversational Knowledge Base Question Answering

1 code implementation ACL 2021 Yunshi Lan, Jing Jiang

We propose a novel graph-based model to capture the transitions of focal entities and apply a graph neural network to derive a probability distribution of focal entities for each question, which is then combined with a standard KBQA module to perform answer ranking.

Knowledge Base Question Answering

MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning

1 code implementation20 Jul 2021 Xueping Peng, Guodong Long, Sen Wang, Jing Jiang, Allison Clarke, Clement Schlegel, Chengqi Zhang

Hence, some recent works train healthcare representations by incorporating medical ontology, by self-supervised tasks like diagnosis prediction, but (1) the small-scale, monotonous ontology is insufficient for robust learning, and (2) critical contexts or dependencies underlying patient journeys are barely exploited to enhance ontology learning.

Graph Embedding Ontology Embedding

Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation

1 code implementation9 Jun 2021 Cunxiao Du, Zhaopeng Tu, Jing Jiang

We propose a new training objective named order-agnostic cross entropy (OaXE) for fully non-autoregressive translation (NAT) models.

Machine Translation Translation

FedProto: Federated Prototype Learning across Heterogeneous Clients

2 code implementations1 May 2021 Yue Tan, Guodong Long, Lu Liu, Tianyi Zhou, Qinghua Lu, Jing Jiang, Chengqi Zhang

Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients' knowledge occurs in the gradient space.

Federated Learning

Cross-Topic Rumor Detection using Topic-Mixtures

no code implementations EACL 2021 Xiaoying Ren, Jing Jiang, Ling Min Serena Khoo, Hai Leong Chieu

After deriving a vector representation for each topic, given an instance, we derive a {``}topic mixture{''} vector for the instance based on its topic distribution.

A Low-Complexity ADMM-based Massive MIMO Detectors via Deep Neural Networks

no code implementations27 Feb 2021 Isayiyas Nigatu Tiba, Quan Zhang, Jing Jiang, Yongchao Wang

An alternate direction method of multipliers (ADMM)-based detectors can achieve good performance in both small and large-scale multiple-input multiple-output (MIMO) systems.

Isometric Propagation Network for Generalized Zero-shot Learning

no code implementations ICLR 2021 Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Xuanyi Dong, Chengqi Zhang

To resolve this problem, we propose Isometric Propagation Network (IPN), which learns to strengthen the relation between classes within each space and align the class dependency in the two spaces.

Generalized Zero-Shot Learning

Episodic memory governs choices: An RNN-based reinforcement learning model for decision-making task

no code implementations24 Jan 2021 Xiaohan Zhang, Lu Liu, Guodong Long, Jing Jiang, Shenquan Liu

Typical methods to study cognitive function are to record the electrical activities of animal neurons during the training of animals performing behavioral tasks.

Decision Making Hippocampus +2

Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization

no code implementations ICML Workshop AML 2021 Jie Wang, Zhaoxia Yin, Jing Jiang, Yang Du

In this paper, we propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA.

Adversarial Attack

PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack

no code implementations19 Jan 2021 Jie Wang, Zhaoxia Yin, Jin Tang, Jing Jiang, Bin Luo

The studies on black-box adversarial attacks have become increasingly prevalent due to the intractable acquisition of the structural knowledge of deep neural networks (DNNs).

Adversarial Attack

Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals

1 code implementation11 Jan 2021 Gaole He, Yunshi Lan, Jing Jiang, Wayne Xin Zhao, Ji-Rong Wen

In our approach, the student network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network.

Knowledge Base Question Answering Semantic Parsing

MASP: Model-Agnostic Sample Propagation for Few-shot learning

no code implementations1 Jan 2021 Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Xuanyi Dong, Chengqi Zhang

Few-shot learning aims to train a classifier given only a few samples per class that are highly insufficient to describe the whole data distribution.

Few-Shot Learning

Extract Local Inference Chains of Deep Neural Nets

no code implementations1 Jan 2021 Haiyan Zhao, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

In this paper, we introduce an efficient method, \name, to extract the local inference chains by optimizing a differentiable sparse scoring for the filters and layers to preserve the outputs on given data from a local region.

Interpretable Machine Learning Network Pruning

SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning

no code implementations2 Dec 2020 Zhuowei Wang, Jing Jiang, Bo Han, Lei Feng, Bo An, Gang Niu, Guodong Long

We also instantiate our framework with different combinations, which set the new state of the art on benchmark-simulated and real-world datasets with noisy labels.

Learning with noisy labels

Confusable Learning for Large-class Few-Shot Classification

no code implementations6 Nov 2020 Bingcong Li, Bo Han, Zhuowei Wang, Jing Jiang, Guodong Long

Specifically, our method maintains a dynamically updating confusion matrix, which analyzes confusable classes in the dataset.

Classification Few-Shot Image Classification +2

A BERT-based Dual Embedding Model for Chinese Idiom Prediction

1 code implementation COLING 2020 Minghuan Tan, Jing Jiang

Specifically, we first match the embedding of each candidate idiom with the hidden representation corresponding to the blank in the context.

Cloze Test

MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler

2 code implementations NeurIPS 2020 Zhining Liu, Pengfei Wei, Jing Jiang, Wei Cao, Jiang Bian, Yi Chang

This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks.

imbalanced classification Meta-Learning

Counterfactual Variable Control for Robust and Interpretable Question Answering

1 code implementation12 Oct 2020 Sicheng Yu, Yulei Niu, Shuohang Wang, Jing Jiang, Qianru Sun

We then conduct two novel CVC inference methods (on trained models) to capture the effect of comprehensive reasoning as the final prediction.

Causal Inference Multiple-choice +2

Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention

2 code implementations COLING 2020 Yang Li, Tao Shen, Guodong Long, Jing Jiang, Tianyi Zhou, Chengqi Zhang

Then, facilitated by the proposed base model, we introduce collaborating relation features shared among relations in the hierarchies to promote the relation-augmenting process and balance the training data for long-tail relations.

Relation Extraction

Cross-Thought for Sentence Encoder Pre-training

1 code implementation EMNLP 2020 Shuohang Wang, Yuwei Fang, Siqi Sun, Zhe Gan, Yu Cheng, Jing Jiang, Jingjing Liu

In this paper, we propose Cross-Thought, a novel approach to pre-training sequence encoder, which is instrumental in building reusable sequence embeddings for large-scale NLP tasks such as question answering.

Information Retrieval Language Modelling +4

Context Modeling with Evidence Filter for Multiple Choice Question Answering

no code implementations6 Oct 2020 Sicheng Yu, Hao Zhang, Wei Jing, Jing Jiang

In addition to the effective reduction of human efforts of our approach compared, through extensive experiments on OpenbookQA, we show that the proposed approach outperforms the models that use the same backbone and more training data; and our parameter analysis also demonstrates the interpretability of our approach.

Machine Reading Comprehension Multiple-choice +1

BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes

1 code implementation24 Sep 2020 Xueping Peng, Guodong Long, Tao Shen, Sen Wang, Jing Jiang, Chengqi Zhang

Electronic health records (EHRs) are longitudinal records of a patient's interactions with healthcare systems.


Attribute Propagation Network for Graph Zero-shot Learning

no code implementations24 Sep 2020 Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

To address this challenging task, most ZSL methods relate unseen test classes to seen(training) classes via a pre-defined set of attributes that can describe all classes in the same semantic space, so the knowledge learned on the training classes can be adapted to unseen classes.

Meta-Learning Zero-Shot Learning

Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases

no code implementations ACL 2020 Yunshi Lan, Jing Jiang

Previous work on answering complex questions from knowledge bases usually separately addresses two types of complexity: questions with constraints and questions with multiple hops of relations.

Graph Generation

Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy

1 code implementation28 Jun 2020 Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings.

Few-Shot Learning

Self-Attention Enhanced Patient Journey Understanding in Healthcare System

1 code implementation15 Jun 2020 Xueping Peng, Guodong Long, Tao Shen, Sen Wang, Jing Jiang

The key challenge of patient journey understanding is to design an effective encoding mechanism which can properly tackle the aforementioned multi-level structured patient journey data with temporal sequential visits and a set of medical codes.

Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks

2 code implementations24 May 2020 Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Xiaojun Chang, Chengqi Zhang

Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic.

Graph Learning Multivariate Time Series Forecasting +1

Online non-convex learning for river pollution source identification

no code implementations22 May 2020 Wenjie Huang, Jing Jiang, Xiao Liu

In this paper, novel gradient-based online learning algorithms are developed to investigate an important environmental application: real-time river pollution source identification, which aims at estimating the released mass, location, and time of a river pollution source based on downstream sensor data monitoring the pollution concentration.

Multi-Center Federated Learning: Clients Clustering for Better Personalization

3 code implementations3 May 2020 Guodong Long, Ming Xie, Tao Shen, Tianyi Zhou, Xianzhi Wang, Jing Jiang, Chengqi Zhang

However, due to the diverse nature of user behaviors, assigning users' gradients to different global models (i. e., centers) can better capture the heterogeneity of data distributions across users.

Federated Learning

Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder

no code implementations13 Apr 2020 Yufei Tian, Jianfei Yu, Jing Jiang

In this paper, we study abstractive review summarization. Observing that review summaries often consist of aspect words, opinion words and context words, we propose a two-stage reinforcement learning approach, which first predicts the output word type from the three types, and then leverages the predicted word type to generate the final word distribution. Experimental results on two Amazon product review datasets demonstrate that our method can consistently outperform several strong baseline approaches based on ROUGE scores.

reinforcement-learning Reinforcement Learning (RL)

Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification

3 code implementations ICLR 2022 Wensi Tang, Guodong Long, Lu Liu, Tianyi Zhou, Michael Blumenstein, Jing Jiang

Particularly, it is a set of kernel sizes that can efficiently cover the best RF size across different datasets via consisting of multiple prime numbers according to the length of the time series.

General Classification Time Series Analysis +1

Interpretable Rumor Detection in Microblogs by Attending to User Interactions

1 code implementation29 Jan 2020 Ling Min Serena Khoo, Hai Leong Chieu, Zhong Qian, Jing Jiang

We propose a post-level attention model (PLAN) to model long distance interactions between tweets with the multi-head attention mechanism in a transformer network.

Multimodal Story Generation on Plural Images

no code implementations16 Jan 2020 Jing Jiang

In this work, we propose the architecture to use images instead of text as the input of the text generation model, called StoryGen.

Story Generation

What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?

no code implementations28 Oct 2019 Chenglei Si, Shuohang Wang, Min-Yen Kan, Jing Jiang

Based on our experiments on the 5 key MCRC datasets - RACE, MCTest, MCScript, MCScript2. 0, DREAM - we observe that 1) fine-tuned BERT mainly learns how keywords lead to correct prediction, instead of learning semantic understanding and reasoning; and 2) BERT does not need correct syntactic information to solve the task; 3) there exists artifacts in these datasets such that they can be solved even without the full context.

Multiple-choice Reading Comprehension

Temporal Self-Attention Network for Medical Concept Embedding

1 code implementation15 Sep 2019 Xueping Peng, Guodong Long, Tao Shen, Sen Wang, Jing Jiang, Michael Blumenstein

In this paper, we propose a medical concept embedding method based on applying a self-attention mechanism to represent each medical concept.


Graph WaveNet for Deep Spatial-Temporal Graph Modeling

7 code implementations31 May 2019 Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Chengqi Zhang

Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system.

Temporal Sequences Traffic Prediction

MahiNet: A Neural Network for Many-Class Few-Shot Learning with Class Hierarchy

no code implementations ICLR 2019 Lu Liu, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

It addresses the ``many-class'' problem by exploring the class hierarchy, e. g., the coarse-class label that covers a subset of fine classes, which helps to narrow down the candidates for the fine class and is cheaper to obtain.

Few-Shot Learning General Classification

DAGCN: Dual Attention Graph Convolutional Networks

1 code implementation4 Apr 2019 Fengwen Chen, Shirui Pan, Jing Jiang, Huan Huo, Guodong Long

In this paper, we propose a novel framework called, dual attention graph convolutional networks (DAGCN) to address these problems.

General Classification Graph Classification +1

Learning Graph Embedding with Adversarial Training Methods

no code implementations4 Jan 2019 Shirui Pan, Ruiqi Hu, Sai-fu Fung, Guodong Long, Jing Jiang, Chengqi Zhang

Based on this framework, we derive two variants of adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively.

Clustering Graph Clustering +3

Learning Private Neural Language Modeling with Attentive Aggregation

4 code implementations17 Dec 2018 Shaoxiong Ji, Shirui Pan, Guodong Long, Xue Li, Jing Jiang, Zi Huang

Federated learning (FL) provides a promising approach to learning private language modeling for intelligent personalized keyboard suggestion by training models in distributed clients rather than training in a central server.

Federated Learning Language Modelling

Global Inference for Aspect and Opinion Terms Co-Extraction Based on Multi-Task Neural Networks

no code implementations IEEE 2018 Jianfei Yu, Jing Jiang, Rui Xia

However, most existing methods fail to explicitly consider the syntactic relations among aspect terms and opinion terms, which may lead to the inconsistencies between the model predictions and the syntactic constraints.

Aspect Term Extraction and Sentiment Classification Multi-Task Learning +2

Did you take the pill? - Detecting Personal Intake of Medicine from Twitter

no code implementations3 Aug 2018 Debanjan Mahata, Jasper Friedrichs, Rajiv Ratn Shah, Jing Jiang

We believe that the developed classifier has direct uses in the areas of psychology, health informatics, pharmacovigilance and affective computing for tracking moods, emotions and sentiments of patients expressing intake of medicine in social media.

Embedding WordNet Knowledge for Textual Entailment

no code implementations COLING 2018 Yunshi Lan, Jing Jiang

In this paper, we study how we can improve a deep learning approach to textual entailment by incorporating lexical entailment relations from WordNet.

Feature Engineering Lexical Entailment +1

A Co-Matching Model for Multi-choice Reading Comprehension

1 code implementation ACL 2018 Shuohang Wang, Mo Yu, Shiyu Chang, Jing Jiang

Multi-choice reading comprehension is a challenging task, which involves the matching between a passage and a question-answer pair.

Reading Comprehension

Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together

2 code implementations NAACL 2019 Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies.

Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling

1 code implementation ICLR 2018 Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

In this paper, we propose a model, called "bi-directional block self-attention network (Bi-BloSAN)", for RNN/CNN-free sequence encoding.

Adversarially Regularized Graph Autoencoder for Graph Embedding

4 code implementations13 Feb 2018 Shirui Pan, Ruiqi Hu, Guodong Long, Jing Jiang, Lina Yao, Chengqi Zhang

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics.

Clustering Graph Clustering +2

Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling

1 code implementation31 Jan 2018 Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, Sen Wang, Chengqi Zhang

In this paper, we integrate both soft and hard attention into one context fusion model, "reinforced self-attention (ReSA)", for the mutual benefit of each other.

Hard Attention Natural Language Inference

Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce

1 code implementation23 Nov 2017 Jianfei Yu, Minghui Qiu, Jing Jiang, Jun Huang, Shuangyong Song, Wei Chu, Haiqing Chen

In this paper, we study transfer learning for the PI and NLI problems, aiming to propose a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource- poor target domain.

Chatbot Natural Language Inference +4

Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification

no code implementations IJCNLP 2017 Jianfei Yu, Jing Jiang

In this paper, we study domain adaptation with a state-of-the-art hierarchical neural network for document-level sentiment classification.

Classification Denoising +6

DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding

1 code implementation14 Sep 2017 Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, Shirui Pan, Chengqi Zhang

Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively.

Natural Language Inference Sentence Embedding +1

Can Syntax Help? Improving an LSTM-based Sentence Compression Model for New Domains

no code implementations ACL 2017 Liangguo Wang, Jing Jiang, Hai Leong Chieu, Chen Hui Ong, D. Song, an, Lejian Liao

In this paper, we study how to improve the domain adaptability of a deletion-based Long Short-Term Memory (LSTM) neural network model for sentence compression.

Sentence Compression

A Compare-Aggregate Model for Matching Text Sequences

2 code implementations6 Nov 2016 Shuohang Wang, Jing Jiang

We particularly focus on the different comparison functions we can use to match two vectors.

Answer Selection Reading Comprehension

Cannot find the paper you are looking for? You can Submit a new open access paper.