1 code implementation • 14 Jan 2024 • Ting Jiang, Shaohan Huang, Shengyue Luo, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang, Deqing Wang, Fuzhen Zhuang
To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method.
no code implementations • 29 Nov 2023 • Wenjun Xie, Enqi Zhang, Lizhao You, Deqing Wang, Zhaorui Wang, Liqun Fu
Linear chirp-based underwater acoustic communication has been widely used due to its reliability and long-range transmission capability.
no code implementations • 29 Aug 2023 • Meng Yuan, Fuzhen Zhuang, Zhao Zhang, Deqing Wang, Jin Dong
Specifically, in hyperbolic space, we set smaller margins in the area near to the origin, which is conducive to distinguishing between highly similar positive items and negative ones.
1 code implementation • 10 Aug 2023 • Tao Zou, Le Yu, Leilei Sun, Bowen Du, Deqing Wang, Fuzhen Zhuang
Finally, we combine the contextual information of patent texts that contains the semantics of IPC codes, and assignees' sequential preferences to make predictions.
1 code implementation • 4 Aug 2023 • Tao Zou, Le Yu, Leilei Sun, Bowen Du, Deqing Wang, Fuzhen Zhuang
Finally, the patent application trend is predicted by aggregating the representations of the target company and classification codes from static, dynamic, and hierarchical perspectives.
1 code implementation • 31 Jul 2023 • Ting Jiang, Shaohan Huang, Zhongzhi Luan, Deqing Wang, Fuzhen Zhuang
We also fine-tune LLMs with current contrastive learning approach, and the 2. 7B OPT model, incorporating our prompt-based method, surpasses the performance of 4. 8B ST5, achieving the new state-of-the-art results on STS tasks.
Ranked #1 on Semantic Textual Similarity on STS12
no code implementations • 27 May 2023 • Hao Geng, Deqing Wang, Fuzhen Zhuang, Xuehua Ming, Chenguang Du, Ting Jiang, Haolong Guo, Rui Liu
To cope with this problem, we propose a Dynamic heterogeneous Graph and Node Importance network (DGNI) learning framework, which fully leverages the dynamic heterogeneous graph and node importance information to predict future citation trends of newly published papers.
1 code implementation • 18 May 2023 • Chenguang Du, Kaichun Yao, HengShu Zhu, Deqing Wang, Fuzhen Zhuang, Hui Xiong
However, existing HGNNs usually represent each node as a single vector in the multi-layer graph convolution calculation, which makes the high-level graph convolution layer fail to distinguish information from different relations and different orders, resulting in the information loss in the message passing.
no code implementations • 21 Mar 2023 • Huishi Luo, Fuzhen Zhuang, Ruobing Xie, HengShu Zhu, Deqing Wang
Recently, causal inference has attracted increasing attention from researchers of recommender systems (RS), which analyzes the relationship between a cause and its effect and has a wide range of real-world applications in multiple fields.
1 code implementation • 20 Nov 2022 • Ziming Wan, Deqing Wang, Xuehua Ming, Fuzhen Zhuang, Chenguang Du, Ting Jiang, Zhengyang Zhao
To address these problems, we propose a novel Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning (RHCO) for large-scale heterogeneous graph representation learning.
1 code implementation • 12 Oct 2022 • Ting Jiang, Deqing Wang, Fuzhen Zhuang, Ruobing Xie, Feng Xia
These methods, such as movement pruning, use first-order information to prune PLMs while fine-tuning the remaining weights.
1 code implementation • 8 Aug 2022 • Hanwen Du, Hui Shi, Pengpeng Zhao, Deqing Wang, Victor S. Sheng, Yanchi Liu, Guanfeng Liu, Lei Zhao
Contrastive learning with Transformer-based sequence encoder has gained predominance for sequential recommendation.
1 code implementation • 5 May 2022 • Ting Jiang, Deqing Wang, Leilei Sun, Zhongzhi Chen, Fuzhen Zhuang, Qinghong Yang
Existing methods encode label hierarchy in a global view, where label hierarchy is treated as the static hierarchical structure containing all labels.
Multi Label Text Classification Multi-Label Text Classification +1
no code implementations • 21 Apr 2022 • Yongjing Hao, Pengpeng Zhao, Xuefeng Xian, Guanfeng Liu, Deqing Wang, Lei Zhao, Yanchi Liu, Victor S. Sheng
To this end, in this paper, we propose a Learnable Model Augmentation self-supervised learning for sequential Recommendation (LMA4Rec).
1 code implementation • 12 Jan 2022 • Ting Jiang, Jian Jiao, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Denvy Deng, Qi Zhang
We propose PromptBERT, a novel contrastive learning method for learning better sentence representation.
1 code implementation • 4 Jan 2022 • Yongchun Zhu, Fuzhen Zhuang, Deqing Wang
However, in the practical scenario, labeled data can be typically collected from multiple diverse sources, and they might be different not only from the target domain but also from each other.
1 code implementation • 21 Oct 2021 • Ting Jiang, Shaohan Huang, Zihan Zhang, Deqing Wang, Fuzhen Zhuang, Furu Wei, Haizhen Huang, Liangjie Zhang, Qi Zhang
While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge.
1 code implementation • 9 Jan 2021 • Ting Jiang, Deqing Wang, Leilei Sun, Huayi Yang, Zhengyang Zhao, Fuzhen Zhuang
In LightXML, we use generative cooperative networks to recall and rank labels, in which label recalling part generates negative and positive labels, and label ranking part distinguishes positive labels from these labels.
no code implementations • 27 Dec 2018 • Deqing Wang, Feng-Yu Cong, Tapani Ristaniemi
In addition, we proposed an accelerated method to compute the objective function and relative error of sparse NCP, which has significantly improved the computation of tensor decomposition especially for higher-order tensor.
1 code implementation • 16 Sep 2018 • Baoyu Jing, Chenwei Lu, Deqing Wang, Fuzhen Zhuang, Cheng Niu
To this end, we embed the group alignment and a partial supervision into a cross-domain topic model, and propose a Cross-Domain Labeled LDA (CDL-LDA).
no code implementations • 3 May 2013 • Deqing Wang, HUI ZHANG, Rui Liu, Weifeng Lv
Much work has been done on feature selection.
2 code implementations • 13 Dec 2010 • Deqing Wang, HUI ZHANG
Term weighting schemes often dominate the performance of many classifiers, such as kNN, centroid-based classifier and SVMs.
Ranked #1 on Multi-class Classification on Reuters-52