no code implementations • CCL 2022 • Houli Ma, Ling Dong, Wenjun Wang, Jian Wang, Shengxiang Gao, Zhengtao Yu
“语音翻译的编码器需要同时编码语音中的声学和语义信息, 单一的Fbank或Wav2vec2语音特征表征能力存在不足。本文通过分析人工的Fbank特征与自监督的Wav2vec2特征间的差异性, 提出基于交叉注意力机制的声学特征融合方法, 并探究了不同的自监督特征和融合方式, 加强模型对语音中声学和语义信息的学习。结合越南语语音特点, 以Fbank特征为主、Pitch特征为辅混合编码Fbank表征, 构建多特征融合的越-英语音翻译模型。实验表明, 使用多特征的语音翻译模型相比单特征翻译效果更优, 与简单的特征拼接方法相比更有效, 所提的多特征融合方法在越-英语音翻译任务上提升了1. 97个BLEU值。”
no code implementations • 25 Mar 2024 • Qin Tian, Wenjun Wang, Chen Zhao, Minglai Shao, Wang Zhang, Dong Li
Traditional machine learning methods heavily rely on the independent and identically distribution assumption, which imposes limitations when the test distribution deviates from the training distribution.
no code implementations • 19 Dec 2023 • Qiyao Peng, Hongtao Liu, Hongyan Xu, Yinghui Wang, Wenjun Wang
For alleviating this, we present a personalized pre-training and fine-tuning paradigm, which could effectively learn expert interest and expertise simultaneously.
no code implementations • 4 Sep 2023 • Yiwen Cao, Yukun Su, Wenjun Wang, Yanxia Liu, Qingyao Wu
Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision.
no code implementations • 31 Aug 2023 • Dong Li, Wenjun Wang, Minglai Shao, Chen Zhao
As the basic element of graph-structured data, node has been recognized as the main object of study in graph representation learning.
no code implementations • ICCV 2023 • Cheng Yan, Shiyu Zhang, Yang Liu, Guansong Pang, Wenjun Wang
Motivated by the impressive generative and anti-noise capacity of diffusion model (DM), in this work, we introduce a novel DM-based method to predict the features of video frames for anomaly detection.
Ranked #8 on Anomaly Detection on UBnormal
no code implementations • 27 May 2022 • Nannan Wu, Ning Zhang, Wenjun Wang, Lixin Fan, Qiang Yang
The proposed algorithm FadMan is a vertical federated learning framework for public node aligned with many private nodes of different features, and is validated on two tasks correlated anomaly detection on multiple attributed networks and anomaly detection on an attributeless network using five real-world datasets.
no code implementations • 11 Mar 2022 • Buyun Zhang, Liang Luo, Xi Liu, Jay Li, Zeliang Chen, Weilin Zhang, Xiaohan Wei, Yuchen Hao, Michael Tsang, Wenjun Wang, Yang Liu, Huayu Li, Yasmine Badr, Jongsoo Park, Jiyan Yang, Dheevatsa Mudigere, Ellie Wen
To overcome the challenge brought by DHEN's deeper and multi-layer structure in training, we propose a novel co-designed training system that can further improve the training efficiency of DHEN.
1 code implementation • 18 Jan 2022 • Xuan Guo, Pengfei Jiao, Ting Pan, Wang Zhang, Mengyu Jia, Danyang Shi, Wenjun Wang
Capturing structural similarity has been a hot topic in the field of network embedding recently due to its great help in understanding the node functions and behaviors.
no code implementations • 13 Apr 2021 • Yingfang Yuan, Wenjun Wang, Wei Pang
In this research, we focus on the impact of selecting two types of GNN hyperparameters, those belonging to graph-related layers and those of task-specific layers, on the performance of GNN for molecular property prediction.
Hyperparameter Optimization Molecular Property Prediction +1
no code implementations • 24 Feb 2021 • Yingfang Yuan, Wenjun Wang, Wei Pang
In particular, the genetic algorithm (GA) for HPO has been explored, which treats GNNs as a black-box model, of which only the outputs can be observed given a set of hyperparameters.
no code implementations • 8 Feb 2021 • Yingfang Yuan, Wenjun Wang, Wei Pang
In this paper, we conducted a theoretical analysis of common and specific features for two state-of-the-art and popular algorithms for HPO: TPE and CMA-ES, and we compared them with random search (RS), which is used as a baseline.
Hyperparameter Optimization Molecular Property Prediction +1
no code implementations • 22 Jan 2021 • Yingfang Yuan, Wenjun Wang, George M. Coghill, Wei Pang
While in the proposed fast evaluation process, the training will be interrupted at an early stage, the difference of RMSE values between the starting and interrupted epochs will be used as a fast score, which implies the potential of the GNN being considered.
5 code implementations • 29 May 2019 • Hongtao Liu, Fangzhao Wu, Wenjun Wang, Xianchen Wang, Pengfei Jiao, Chuhan Wu, Xing Xie
In this paper we propose a neural recommendation approach with personalized attention to learn personalized representations of users and items from reviews.
no code implementations • 29 May 2019 • Xianchen Wang, Hongtao Liu, Peiyi Wang, Fangzhao Wu, Hongyan Xu, Wenjun Wang, Xing Xie
In this paper, we propose a hierarchical attention model fusing latent factor model for rating prediction with reviews, which can focus on important words and informative reviews.