no code implementations • 17 Apr 2024 • Haotian Xu, Zhaorui Zhang, Sheng Di, Benben Liu, Khalid Ayed Alharthi, Jiannong Cao
We propose a full asynchronous training paradigm, called FedFa, which can guarantee model convergence and eliminate the waiting time completely for federated learning by using a few buffered results on the server for parameter updating.
no code implementations • 14 Apr 2024 • Changlin Song, Divya Saxena, Jiannong Cao, Yuqing Zhao
This paper introduces FedDistill, a framework enhancing the knowledge transfer from the global model to local models, focusing on the issue of imbalanced class distribution.
no code implementations • 3 Apr 2024 • Zhiyuan Wen, Jiannong Cao, Jiaxing Shen, Ruosong Yang, Shuaiqi Liu, Maosong Sun
Therefore, we propose a new task, Personality-affected Emotion Generation, to generate emotion based on the personality given to the dialog system and further investigate a solution through the personality-affected mood transition.
1 code implementation • 3 Apr 2024 • Zhiyuan Wen, Jiannong Cao, Yu Yang, Ruosong Yang, Shuaiqi Liu
To utilize affectivity within dialog content for accurate personality recognition, we fine-tuned a pre-trained language model specifically for emotion recognition in conversations, facilitating real-time affective annotations for utterances.
no code implementations • 13 Mar 2024 • Xiangchun Chen, Jiannong Cao, Zhixuan Liang, Yuvraj Sahni, Mingjin Zhang
To address this challenge, we formulate an online joint microservice offloading and bandwidth allocation problem, JMOBA, to minimize the average completion time of services.
no code implementations • 7 Mar 2024 • Shuaiqi Liu, Jiannong Cao, Yicong Li, Ruosong Yang, Zhiyuan Wen
Current summarization datasets are insufficient to satisfy the demands of summarizing precedents across multiple jurisdictions, especially when labeled data are scarce for many jurisdictions.
no code implementations • 19 Feb 2024 • Chengyi Ju, Jiannong Cao, Yu Yang, Zhen-Qun Yang, Ho Man Lee
In response, we propose HFRec, a heterogeneity-aware hybrid federated recommender system designed for cross-school elective course recommendations.
no code implementations • 1 Nov 2023 • Jiangnan Xia, Yu Yang, Senzhang Wang, Hongzhi Yin, Jiannong Cao, Philip S. Yu
To this end, we investigate a novel problem of robust POI recommendation by considering the uncertainty factors of the user check-ins, and proposes a Bayes-enhanced Multi-view Attention Network.
no code implementations • 23 Oct 2023 • Xiaoyun Liu, Divya Saxena, Jiannong Cao, Yuqing Zhao, Penghui Ruan
However, existing DAS methods fail to trade off between model performance and model size.
1 code implementation • 4 Sep 2023 • Zhihao Ding, Jieming Shi, Qing Li, Jiannong Cao
Extensive experiments, comparing against 14 existing solutions on 4 large cryptocurrency datasets of Bitcoin and Ethereum, demonstrate that DIAM consistently achieves the best performance to accurately detect illicit accounts, while being efficient.
no code implementations • 20 Jul 2023 • Hanchen Yang, Wengen Li, Shuyu Wang, Hui Li, Jihong Guan, Shuigeng Zhou, Jiannong Cao
Compared with typical ST data (e. g., traffic data), ST ocean data is more complicated but with unique characteristics, e. g., diverse regionality and high sparsity.
1 code implementation • 9 Feb 2023 • Shuaiqi Liu, Jiannong Cao, Ruosong Yang, Zhiyuan Wen
Existing MDS datasets usually focus on producing the structureless summary covering a few input documents.
1 code implementation • 8 Feb 2023 • Shuaiqi Liu, Jiannong Cao, Ruosong Yang, Zhiyuan Wen
Within a report document, the salient information can be scattered in the textual and non-textual content.
1 code implementation • CVPR 2023 • Divya Saxena, Jiannong Cao, Jiahao Xu, Tarun Kulshrestha
Re-GAN stabilizes the GANs models with less data and offers an alternative to the existing GANs tickets and progressive growing methods.
1 code implementation • 22 Jul 2022 • Yuqing Zhao, Divya Saxena, Jiannong Cao
Managing heterogeneous datasets that vary in complexity, size, and similarity in continual learning presents a significant challenge.
no code implementations • 1 Jul 2022 • Yu Yang, Hongzhi Yin, Jiannong Cao, Tong Chen, Quoc Viet Hung Nguyen, Xiaofang Zhou, Lei Chen
Meanwhile, we treat each edge sequence as a whole and embed its ToV of the first vertex to further encode the time-sensitive information.
no code implementations • 25 Jun 2022 • Zhixuan Liang, Jiannong Cao, Shan Jiang, Divya Saxena, Huafeng Xu
To tackle the issues, we propose a hierarchical reinforcement learning approach with high-level decision-making and low-level individual control for efficient policy search.
no code implementations • 20 Jun 2022 • Zhiuxan Liang, Jiannong Cao, Shan Jiang, Divya Saxena, Jinlin Chen, Huafeng Xu
Precisely, SMART consists of two components: 1) a simulation environment that provides a variety of complex interaction scenarios for training and 2) a real-world multi-robot system for realistic performance evaluation.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 14 Oct 2021 • Rohan Kabra, Divya Saxena, Dhaval Patel, Jiannong Cao
Human behavior modeling deals with learning and understanding behavior patterns inherent in humans' daily routines.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Ruosong Yang, Jiannong Cao, Zhiyuan Wen, Youzheng Wu, Xiaodong He
However, to solve the AES task, previous works utilize shallow neural networks to learn essay representations and constrain calculated scores with regression loss or ranking loss, respectively.
no code implementations • 4 Aug 2020 • Lei Yang, Yanyan Lu, Jiannong Cao, Jiaming Huang, Mingjin Zhang
In this paper, we propose a novel decentralized model learning approach, namely E-Tree, which makes use of a well-designed tree structure imposed on the edge devices.
no code implementations • 6 Jun 2020 • Yu Yang, Zhiyuan Wen, Jiannong Cao, Jiaxing Shen, Hongzhi Yin, Xiaofang Zhou
We propose a novel algorithm (EPARS) that could early predict STAR in a semester by modeling online and offline learning behaviors.
no code implementations • LREC 2020 • Zhiyuan Wen, Jiannong Cao, Ruosong Yang, Senzhang Wang
The two major challenges in existing works lie in (1) effectively disentangling the original sentiment from input sentences; and (2) preserving the semantic content while transferring the sentiment.
no code implementations • LREC 2020 • Ruosong Yang, Jiannong Cao, Zhiyuan Wen
To enhance corpus based word embedding models, researchers utilize domain knowledge to learn more distinguishable representations via joint optimization and post-processing based models.
no code implementations • 30 Apr 2020 • Divya Saxena, Jiannong Cao
In this study, we perform a comprehensive survey of the advancements in GANs design and optimization solutions proposed to handle GANs challenges.
no code implementations • 29 Nov 2019 • YongJie Ye, Jingjing Zhang, Weigang Wu, Xiapu Luo, Jiannong Cao
In this paper, we design and develop a novel off-chain system to shorten the routing path for the payment network.
Cryptography and Security
no code implementations • 19 Jul 2019 • Divya Saxena, Jiannong Cao
However, it is still very challenging (1) to adequately learn the complex and non-linear ST relationships; (2) to model the high variations in the ST data volumes as it is inherently dynamic, changing over time (i. e., irregular) and highly influenced by many external factors, such as adverse weather, accidents, traffic control, PoI, etc.
no code implementations • 11 Jun 2019 • Senzhang Wang, Jiannong Cao, Philip S. Yu
Next we classify existing literatures based on the types of ST data, the data mining tasks, and the deep learning models, followed by the applications of deep learning for STDM in different domains including transportation, climate science, human mobility, location based social network, crime analysis, and neuroscience.
1 code implementation • 3 Dec 2017 • Hongwei Wang, Jia Wang, Miao Zhao, Jiannong Cao, Minyi Guo
JTS-MF model calculates similarity among users and votings by combining their TEWE representation and structural information of social networks, and preserves this topic-semantic-social similarity during matrix factorization.