no code implementations • 16 Apr 2024 • Zhengyang Liang, Meiyu Liang, Wei Huang, Yawen Li, Zhe Xue
Our methodology streamlines pre-trained multimodal large models using only their output features and original image-level information, requiring minimal computational resources.
no code implementations • 2 Nov 2023 • Junfu Wang, Yawen Li, Zhe Xue, Ang Li
Academic networks in the real world can usually be described by heterogeneous information networks composed of multi-type nodes and relationships.
no code implementations • 1 Nov 2023 • Runze Fang, Yawen Li, Yingxia Shao, Zeli Guan, Zhe Xue
The entity alignment of science and technology patents aims to link the equivalent entities in the knowledge graph of different science and technology patent data sources.
no code implementations • 1 Nov 2023 • Hongrui Gao, Yawen Li, Meiyu Liang, Zeli Guan, Zhe Xue
At the same time, in order to enrich the features of scientific literature, a learning method of semantic representation of scientific literature based on adaptive features and graph neural network is proposed.
no code implementations • 1 Nov 2023 • Chengjie Ma, Yawen Li, Meiyu Liang, Ang Li
The first method involves slow pruning throughout the entire model training process, which has limited acceleration effect on the model training process, but can ensure that the pruned model achieves higher accuracy.
no code implementations • 4 Sep 2023 • Jin Zhang, Defu Lian, Hong Xie, Yawen Li, Enhong Chen
Furthermore, we employ Bayesian meta-learning methods to effectively address the cold-start problem and derive theoretical regret bounds for our proposed method, ensuring a robust performance guarantee.
no code implementations • 22 Jun 2023 • Jie Gao, Yawen Li, Zhe Xue, Zeli Guan
It can also ensure the load balancing of distributed storage while maintaining spatio-temporal proximity of the data partitioning results.
no code implementations • 11 Feb 2023 • Deyu Bo, Xiao Wang, Yang Liu, Yuan Fang, Yawen Li, Chuan Shi
Graph neural networks (GNNs) have attracted considerable attention from the research community.
no code implementations • 3 Jan 2023 • Bingyan Liu, Nuoyan Lv, Yuanchun Guo, Yawen Li
In this paper, we provide a systematic survey on federated learning, aiming to review the recent advanced federated methods and applications from different aspects.
no code implementations • 24 Dec 2022 • Cuiying Huo, Di Jin, Yawen Li, Dongxiao He, Yu-Bin Yang, Lingfei Wu
A key premise for the remarkable performance of GNNs relies on complete and trustworthy initial graph descriptions (i. e., node features and graph structure), which is often not satisfied since real-world graphs are often incomplete due to various unavoidable factors.
no code implementations • 1 Nov 2022 • Yingxia Shao, Hongzheng Li, Xizhi Gu, Hongbo Yin, Yawen Li, Xupeng Miao, Wentao Zhang, Bin Cui, Lei Chen
In recent years, many efforts have been made on distributed GNN training, and an array of training algorithms and systems have been proposed.
no code implementations • 12 Oct 2022 • Yuxin Liu, Yawen Li, Yingxia Shao, Zeli Guan
Therefore, a hypergraph neural network model based on dual channel convolution is proposed.
no code implementations • 7 Oct 2022 • Hongrui Gao, Yawen Li, Meiyu Liang, Zeli Guan
Therefore, an unsupervised semantic representation learning method of scientific literature based on graph attention mechanism and maximum mutual information (GAMMI) is proposed.
no code implementations • 7 Oct 2022 • Junfu Wang, Yawen Li, Meiyu Liang, Ang Li
To solve the above challenges, aiming at the data information of scientific research teams closely related to science and technology, we proposed an academic heterogeneous information network embedding representation learning method based on federated learning (FedAHE), which utilizes node attention and meta path attention mechanism to learn low-dimensional, dense and real-valued vector representations while preserving the rich topological information and meta-path-based semantic information of nodes in network.
no code implementations • 6 Jun 2022 • Xingchen Liu, Yawen Li, Yingxia Shao, Ang Li, Jian Liang
Based on this, we propose a car review text sentiment analysis model based on adversarial training and whole word mask BERT(ATWWM-BERT).
no code implementations • 30 Apr 2022 • Cuiying Huo, Dongxiao He, Yawen Li, Di Jin, Jianwu Dang, Weixiong Zhang, Witold Pedrycz, Lingfei Wu
However, the existing contrastive learning methods are inadequate for heterogeneous graphs because they construct contrastive views only based on data perturbation or pre-defined structural properties (e. g., meta-path) in graph data while ignore the noises that may exist in both node attributes and graph topologies.
no code implementations • 21 Mar 2022 • Runyu Yu, Yawen Li, Ang Li
Aiming at the problem that the current general-purpose semantic text similarity calculation methods are difficult to use the semantic information of scientific academic conference data, a semantic similarity calculation algorithm for scientific academic conferences by fusion with domain features is proposed.
no code implementations • 21 Mar 2022 • Yue Wang, Yawen Li, Ang Li
We propose an attention-based hierarchical multi-label classification algorithm of academic texts (AHMCA) by integrating features such as text, keywords, and hierarchical structure, the academic documents are classified into the most relevant categories.
Document Embedding Hierarchical Multi-label Classification +2
1 code implementation • Science China Information Sciences 2021 • Shitao Xiao, Yingxia Shao, Yawen Li, Hongzhi Yin, Yanyan Shen & Bin Cui
In this paper, we model an interaction between user and item as an edge and propose a novel CF framework, called learnable edge collaborative filtering (LECF).
no code implementations • The VLDB Journal 2021 • Yingxia Shao, Shiyue Huang, Yawen Li, Xupeng Miao, Bin Cui & Lei Chen
In this paper, to clearly compare the efficiency of various node sampling methods, we first design a cost model and propose two new node sampling methods: one follows the acceptance-rejection paradigm to achieve a better balance between memory and time cost, and the other is optimized for fast sampling the skewed probability distributions existed in natural graphs.