arXiv subjects

Zhe Xue

Publications and source records attributed to Zhe Xue.

31 records · Page 2Linked to original sources

arXiv2024

Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning

In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required for their training present significant hurdles for deployment in environments with limited computational resources. To address this challenge, we propose a novel dynamic self-adaptive multiscale distillation from pre-trained multimodal large model for efficient cross-modal representation learning for the first time. Unlike existing distillation methods, our strategy employs a multiscale perspective, enabling the extraction structural knowledge across from the pre-trained multimodal large model. Ensuring that the student model inherits a comprehensive and nuanced understanding of the teacher knowledge. To optimize each distillation loss in a balanced and efficient manner, we propose a dynamic self-adaptive distillation loss balancer, a novel component eliminating the need for manual loss weight adjustments and dynamically balances each loss item during the distillation process. Our methodology streamlines pre-trained multimodal large models using only their output features and original image-level information, requiring minimal computational resources. This efficient approach is suited for various applications and allows the deployment of advanced multimodal technologies even in resource-limited settings. Extensive experiments has demonstrated that our method maintains high performance while significantly reducing model complexity and training costs. Moreover, our distilled student model utilizes only image-level information to achieve state-of-the-art performance on cross-modal retrieval tasks, surpassing previous methods that relied on region-level information.

cs.CV↗

arXiv2023

Epidemic Decision-making System Based Federated Reinforcement Learning

Epidemic decision-making can effectively help the government to comprehensively consider public security and economic development to respond to public health and safety emergencies. Epidemic decision-making can effectively help the government to comprehensively consider public security and economic development to respond to public health and safety emergencies. Some studies have shown that intensive learning can effectively help the government to make epidemic decision, thus achieving the balance between health security and economic development. Some studies have shown that intensive learning can effectively help the government to make epidemic decision, thus achieving the balance between health security and economic development. However, epidemic data often has the characteristics of limited samples and high privacy. However, epidemic data often has the characteristics of limited samples and high privacy. This model can combine the epidemic situation data of various provinces for cooperative training to use as an enhanced learning model for epidemic situation decision, while protecting the privacy of data. The experiment shows that the enhanced federated learning can obtain more optimized performance and return than the enhanced learning, and the enhanced federated learning can also accelerate the training convergence speed of the training model. accelerate the training convergence speed of the client. At the same time, through the experimental comparison, A2C is the most suitable reinforcement learning model for the epidemic situation decision-making. learning model for the epidemic situation decision-making scenario, followed by the PPO model, and the performance of DDPG is unsatisfactory.

cs.LG↗

arXiv2023

Transition behavior of the waiting time distribution in a jumping model with the internal state

It has been noticed that when the waiting time distribution exhibits a transition from an intermediate time power law decay to a long-time exponential decay in the continuous time random walk model, a transition from anomalous diffusion to normal diffusion can be observed at the population level. However, the mechanism behind the transition of waiting time distribution is rarely studied. In this paper, we provide one possible mechanism to explain the origin of such transition. A jump model terminated by a state-dependent Poisson clock is studied by a formal asymptotic analysis for the time evolutionary equation of its probability density function. The waiting time behavior under a more relaxed setting can be rigorously characterized by probability tools. Both approaches show the transition phenomenon of the waiting time $T$, which is further verified numerically by particle simulations. Our results indicate that a small drift and strong noise in the state equation and a stiff response in the Poisson rate are crucial to the transitional phenomena.

math.AP↗

arXiv2022

Research Scholar Interest Mining Method based on Load Centrality

In the era of big data, it is possible to carry out cooperative research on the research results of researchers through papers, patents and other data, so as to study the role of researchers, and produce results in the analysis of results. For the important problems found in the research and application of reality, this paper also proposes a research scholar interest mining algorithm based on load centrality (LCBIM), which can accurately solve the problem according to the researcher's research papers and patent data. Graphs of creative algorithms in various fields of the study aggregated ideas, generated topic graphs by aggregating neighborhoods, used the generated topic information to construct with similar or similar topic spaces, and utilize keywords to construct one or more topics. The regional structure of each topic can be used to closely calculate the weight of the centrality research model of the node, which can analyze the field in the complete coverage principle. The scientific research cooperation based on the load rate center proposed in this paper can effectively extract the interests of scientific research scholars from papers and corpus.

cs.DL↗

arXiv2022

Scientific Paper Classification Based on Graph Neural Network with Hypergraph Self-attention Mechanism

The number of scientific papers has increased rapidly in recent years. How to make good use of scientific papers for research is very important. Through the high-quality classification of scientific papers, researchers can quickly find the resource content they need from the massive scientific resources. The classification of scientific papers will effectively help researchers filter redundant information, obtain search results quickly and accurately, and improve the search quality, which is necessary for scientific resource management. This paper proposed a science-technique paper classification method based on hypergraph neural network(SPHNN). In the heterogeneous information network of scientific papers, the repeated high-order subgraphs are modeled as hyperedges composed of multiple related nodes. Then the whole heterogeneous information network is transformed into a hypergraph composed of different hyperedges. The graph convolution operation is carried out on the hypergraph structure, and the hyperedges self-attention mechanism is introduced to aggregate different types of nodes in the hypergraph, so that the final node representation can effectively maintain high-order nearest neighbor relationships and complex semantic information. Finally, by comparing with other methods, we proved that the model proposed in this paper has improved its performance.

cs.IR↗

arXiv2022

Scientific and Technological News Recommendation Based on Knowledge Graph with User Perception

Existing research usually utilizes side information such as social network or item attributes to improve the performance of collaborative filtering-based recommender systems. In this paper, the knowledge graph with user perception is used to acquire the source of side information. We proposed KGUPN to address the limitations of existing embedding-based and path-based knowledge graph-aware recommendation methods, an end-to-end framework that integrates knowledge graph and user awareness into scientific and technological news recommendation systems. KGUPN contains three main layers, which are the propagation representation layer, the contextual information layer and collaborative relation layer. The propagation representation layer improves the representation of an entity by recursively propagating embeddings from its neighbors (which can be users, news, or relationships) in the knowledge graph. The contextual information layer improves the representation of entities by encoding the behavioral information of entities appearing in the news. The collaborative relation layer complements the relationship between entities in the news knowledge graph. Experimental results on real-world datasets show that KGUPN significantly outperforms state-of-the-art baselines in scientific and technological news recommendation.

cs.IR↗

arXiv2022

Aspect-Based Sentiment Analysis using Local Context Focus Mechanism with DeBERTa

Text sentiment analysis, also known as opinion mining, is research on the calculation of people's views, evaluations, attitude and emotions expressed by entities. Text sentiment analysis can be divided into text-level sentiment analysis, sen-tence-level sentiment analysis and aspect-level sentiment analysis. Aspect-Based Sentiment Analysis (ABSA) is a fine-grained task in the field of sentiment analysis, which aims to predict the polarity of aspects. The research of pre-training neural model has significantly improved the performance of many natural language processing tasks. In recent years, pre training model (PTM) has been applied in ABSA. Therefore, there has been a question, which is whether PTMs contain sufficient syntactic information for ABSA. In this paper, we explored the recent DeBERTa model (Decoding-enhanced BERT with disentangled attention) to solve Aspect-Based Sentiment Analysis problem. DeBERTa is a kind of neural language model based on transformer, which uses self-supervised learning to pre-train on a large number of original text corpora. Based on the Local Context Focus (LCF) mechanism, by integrating DeBERTa model, we purpose a multi-task learning model for aspect-based sentiment analysis. The experiments result on the most commonly used the laptop and restaurant datasets of SemEval-2014 and the ACL twitter dataset show that LCF mechanism with DeBERTa has significant improvement.

cs.CL↗

arXiv2022

Chinese Word Sense Embedding with SememeWSD and Synonym Set

Word embedding is a fundamental natural language processing task which can learn feature of words. However, most word embedding methods assign only one vector to a word, even if polysemous words have multi-senses. To address this limitation, we propose SememeWSD Synonym (SWSDS) model to assign a different vector to every sense of polysemous words with the help of word sense disambiguation (WSD) and synonym set in OpenHowNet. We use the SememeWSD model, an unsupervised word sense disambiguation model based on OpenHowNet, to do word sense disambiguation and annotate the polysemous word with sense id. Then, we obtain top 10 synonyms of the word sense from OpenHowNet and calculate the average vector of synonyms as the vector of the word sense. In experiments, We evaluate the SWSDS model on semantic similarity calculation with Gensim's wmdistance method. It achieves improvement of accuracy. We also examine the SememeWSD model on different BERT models to find the more effective model.

cs.CL↗

arXiv2022

Bi-convolution matrix factorization algorithm based on improved ConvMF

With the rapid development of information technology, "information overload" has become the main theme that plagues people's online life. As an effective tool to help users quickly search for useful information, a personalized recommendation is more and more popular among people. In order to solve the sparsity problem of the traditional matrix factorization algorithm and the problem of low utilization of review document information, this paper proposes a Bicon-vMF algorithm based on improved ConvMF. This algorithm uses two parallel convolutional neural networks to extract deep features from the user review set and item review set respectively and fuses these features into the decomposition of the rating matrix, so as to construct the user latent model and the item latent model more accurately. The experimental results show that compared with traditional recommendation algorithms like PMF, ConvMF, and DeepCoNN, the method proposed in this paper has lower prediction error and can achieve a better recommendation effect. Specifically, compared with the previous three algorithms, the prediction errors of the algorithm proposed in this paper are reduced by 45.8%, 16.6%, and 34.9%, respectively.

cs.IR↗

arXiv2022

Research on accurate stereo portrait generation algorithm of scientific research team

In order to smoothly promote the establishment of scientific research projects, accurately identify the excellent scientific research team, and intuitively and comprehensively describe the scientific research team, it is of great significance for the scientific research management department to comprehensively understand and objectively evaluate the scientific research team. At present, the research work on the construction of accurate three-dimensional portrait of scientific research team is relatively less. In view of the practical demand of scientific research management department, this paper proposes an accurate stereo portrait generation algorithm of scientific research team. The algorithm includes three modules: research team identification, research topic extraction and research team portrait generation. Firstly, the leader of the scientific research team is identified based on the iterative middle centrality ranking method, and the members of the scientific research team are identified through the 2-faction and snowball methods, so as to realize the identification of the scientific research team. Then, considering the statistical information of words and the co-occurrence features of words in the research team, the research topics of the research team are extracted to improve the accuracy of research topic extraction. Finally, the research team portrait generation module generates the accurate three-dimensional portrait of the research team through the generation of the research team profile, the construction of the research cooperation relationship, and the construction of the research team topic cloud. The research team is identified on the data set of scientific research achievements, and the accurate three-dimensional portraits of the research team are generated and visualized. Experiments verify the effectiveness of the proposed algorithm.

cs.DL↗

arXiv2022

An unsupervised cluster-level based method for learning node representations of heterogeneous graphs in scientific papers

Learning knowledge representation of scientific paper data is a problem to be solved, and how to learn the representation of paper nodes in scientific paper heterogeneous network is the core to solve this problem. This paper proposes an unsupervised cluster-level scientific paper heterogeneous graph node representation learning method (UCHL), aiming at obtaining the representation of nodes (authors, institutions, papers, etc.) in the heterogeneous graph of scientific papers. Based on the heterogeneous graph representation, this paper performs link prediction on the entire heterogeneous graph and obtains the relationship between the edges of the nodes, that is, the relationship between papers and papers. Experiments results show that the proposed method achieves excellent performance on multiple evaluation metrics on real scientific paper datasets.

cs.LG↗

arXiv2022

Research topic trend prediction of scientific papers based on spatial enhancement and dynamic graph convolution network

In recent years, with the increase of social investment in scientific research, the number of research results in various fields has increased significantly. Accurately and effectively predicting the trends of future research topics can help researchers discover future research hotspots. However, due to the increasingly close correlation between various research themes, there is a certain dependency relationship between a large number of research themes. Viewing a single research theme in isolation and using traditional sequence problem processing methods cannot effectively explore the spatial dependencies between these research themes. To simultaneously capture the spatial dependencies and temporal changes between research topics, we propose a deep neural network-based research topic hotness prediction algorithm, a spatiotemporal convolutional network model. Our model combines a graph convolutional neural network (GCN) and Temporal Convolutional Network (TCN), specifically, GCNs are used to learn the spatial dependencies of research topics a and use space dependence to strengthen spatial characteristics. TCN is used to learn the dynamics of research topics' trends. Optimization is based on the calculation of weighted losses based on time distance. Compared with the current mainstream sequence prediction models and similar spatiotemporal models on the paper datasets, experiments show that, in research topic prediction tasks, our model can effectively capture spatiotemporal relationships and the predictions outperform state-of-art baselines.

cs.IR↗

arXiv2021

NDPNet: A novel non-linear data projection network for few-shot fine-grained image classification

Metric-based few-shot fine-grained image classification (FSFGIC) aims to learn a transferable feature embedding network by estimating the similarities between query images and support classes from very few examples. In this work, we propose, for the first time, to introduce the non-linear data projection concept into the design of FSFGIC architecture in order to address the limited sample problem in few-shot learning and at the same time to increase the discriminability of the model for fine-grained image classification. Specifically, we first design a feature re-abstraction embedding network that has the ability to not only obtain the required semantic features for effective metric learning but also re-enhance such features with finer details from input images. Then the descriptors of the query images and the support classes are projected into different non-linear spaces in our proposed similarity metric learning network to learn discriminative projection factors. This design can effectively operate in the challenging and restricted condition of a FSFGIC task for making the distance between the samples within the same class smaller and the distance between samples from different classes larger and for reducing the coupling relationship between samples from different categories. Furthermore, a novel similarity measure based on the proposed non-linear data project is presented for evaluating the relationships of feature information between a query image and a support set. It is worth to note that our proposed architecture can be easily embedded into any episodic training mechanisms for end-to-end training from scratch. Extensive experiments on FSFGIC tasks demonstrate the superiority of the proposed methods over the state-of-the-art benchmarks.

cs.CV↗