检索结果-内蒙古大学图书馆

Dynamic Prompt Optimizing for Text-to-Image Generation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mo, Wenyi Zhang, Tianyu Bai, Yalong Su, Bing Wen, Ji-Rong Yang, Qing Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China Du Xiaoman Technology

Text-to-image generative models, specifically those based on diffusion models like Imagen and Stable Diffusion, have made substantial advancements. Recently, there has been a surge of interest in the delicate refinement of text prompts. Users assign weights or alter the injection time steps of certain words in the text prompts to improve the quality of generated images. However, the success of fine-control prompts depends on the accuracy of the text prompts and the careful selection of weights and time steps, which requires significant manual intervention. To address this, we introduce the Prompt Auto-Editing (PAE) method. Besides refining the original prompts for image generation, we further employ an online reinforcement learning strategy to explore the weights and injection time steps of each word, leading to the dynamic fine-control prompts. The reward function during training encourages the model to consider aesthetic score, semantic consistency, and user preferences. Experimental results demonstrate that our proposed method effectively improves the original prompts, generating visually more appealing images while maintaining semantic alignment. Code is available at this https URL. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Unraveling Intricacies: A Decomposition Approach for Few-Shot Multi-Intent Spoken Language Understanding

学校读者我要写书评

暂无评论

Unraveling Intricacies: A Decomposition Approach for Few-Sho...

2024 IEEE International Conference on big data, bigdata 2024

作者： Hua, Wenbin Wang, Yufan Fan, Rui Tu, Xinhui He, Tingting Central China Normal University Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning National Language Resources Monitor Research Center for Network Media Wuhan China Central China Normal University School of Computer Wuhan China Shenzhen Technology University College of Big Data and Internet Shenzhen China Central China Normal University Faculty of Artificial Intelligence in Education Wuhan China

ISBN: (纸本)9798350362480

Few-shot multi-intent spoken language understanding (SLU) aims to detect user's multiple intents and key slots using a tiny amount of annotated data. Prevailing multi-intent SLU models typically rely on abundant data for effective training, enabling them to capture corresponding relationships between intents and slots. However, in few-shot scenarios, establishing these connections becomes challenging, especially in situations involving multiple intents, which may result in confused relationships between intents and slots. To overcome the challenge, we propose decomposing the multi-label intent detection task into several single-label tasks, which reduces the complexity of model training while preserving the constraint relationships between intents and their related slots. We design description templates for each intent and respectively predict the correlation between the utterance and each intent description while completing the slot filling task under the corresponding intent. Therefore, each intent can independently guide the slot filling process, mitigating potentially confused relationships between multiple intents and slots. Experimental results on public datasets indicate that the performance of our model is better than ChatGPT and achieves state-of-the-art results. © 2024 IEEE.

关键词： Zero-shot learning

Quiz-based Knowledge Tracing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Shen, Shuanghong Chen, Enhong Xu, Bihan Liu, Qi Huang, Zhenya Zhu, Linbo Su, Yu Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science School of Computer Science and Techonology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Anhui Hefei230026 China Anhui Province Key Laboratory of Big Data Analysis and Application School of Data Science School of Computer Science and Techonology University of Science and Technology of China State Key Laboratory of Cognitive Intelligence Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230026 China School of Computer Science and Technology Hefei Normal University Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei230026 China

Knowledge tracing (KT) aims to assess individuals’ evolving knowledge states according to their learning interactions with different exercises in online learning systems (OIS), which is critical in supporting decision-making for subsequent intelligent services, such as personalized learning source recommendation. Existing researchers have broadly studied KT and developed many effective methods. However, most of them assume that students’ historical interactions are uniformly distributed in a continuous sequence, ignoring the fact that actual interaction sequences are organized based on a series of quizzes with clear boundaries, where interactions within a quiz are consecutively completed, but interactions across different quizzes are discrete and may be spaced over days. In this paper, we present the Quiz-based Knowledge Tracing (QKT) model to monitor students’ knowledge states according to their quiz-based learning interactions. Specifically, as students’ interactions within a quiz are continuous and have the same or similar knowledge concepts, we design the adjacent gate followed by a global average pooling layer to capture the intra-quiz short-term knowledge influence. Then, as various quizzes tend to focus on different knowledge concepts, we respectively measure the inter-quiz knowledge substitution by the gated recurrent unit and the inter-quiz knowledge complementarity by the self-attentive encoder with a novel recency-aware attention mechanism. Finally, we integrate the inter-quiz long-term knowledge substitution and complementarity across different quizzes to output students’ evolving knowledge states. Extensive experimental results on three public real-world datasets demonstrate that QKT achieves state-of-the-art performance compared to existing methods. Further analyses confirm that QKT is promising in designing more effective quizzes. Copyright © 2023, The Authors. All rights reserved.

关键词： Students

Partitioned Inverted Index Compression Using Hierarchical Dirichlet Process

学校读者我要写书评

暂无评论

Partitioned Inverted Index Compression Using Hierarchical Di...

Neural Networks, Information and Communication Engineering (NNICE), International Conference on

作者： Runzhu He Youli Qu Dept. Key Laboratory of Big Data & Artifcial Intelligence in Transportation Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China

In large-scale search engines, the core data structure is the inverted index, essentially a collection of integer sequences within inverted lists. Precise partitioning of these sequences enables efficient query processing. The concept of partitioning by quantity and universe has been established for years in the field of inverted index compression algorithms. The volume of data within a post-partitioned area, defined as density, is a key determinant of the compression efficiency of partitioned inverted index algorithms. Previous studies have focused on creating denser partitioned areas atop existing inverted file indexes to improve compression efficiency. This paper proposes a novel approach that utilizes the Hierarchical Dirichlet Process model to extract document themes, categorizes documents based on these themes, and then constructs file indexes accordingly to create denser partitioned areas. Compared with other inverted index compression methods, this algorithm achieves a favorable balance between time and space efficiency.

关键词：

An Efficient Continuous Control Perspective for Reinforcement-Learning-based Sequential Recommendation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Jun Wu, Likang Liu, Qi Yang, Yu School of Data Science City University of Hong Kong Kowloon Hong Kong College of Management and Economics Tianjin University Tianjin China Anhui Province Key Laboratory of Big Data Analysis and Application University of Science and Technology of China Anhui Hefei China State Key Laboratory of Cognitive Intelligence Anhui Hefei China

Sequential recommendation, where user preference is dynamically inferred from sequential historical behaviors, is a critical task in recommender systems (RSs). To further optimize long-term user engagement, offline reinforcement-learning-based RSs have become a mainstream technique as they provide an additional advantage in avoiding global explorations that may harm online users’ experiences. However, previous studies mainly focus on discrete action and policy spaces, which might have difficulties in handling dramatically growing items efficiently. To mitigate this issue, in this paper, we aim to design an algorithmic framework applicable to continuous policies. To facilitate the control in the low-dimensional but dense user preference space, we propose an Efficient Continuous Control framework (ECoC). Based on a statistically tested assumption, we first propose the novel unified action representation abstracted from normalized user and item spaces. Then, we develop the corresponding policy evaluation and policy improvement procedures. During this process, strategic exploration and directional control in terms of unified actions are carefully designed and crucial to final recommendation decisions. Moreover, beneficial from unified actions, the conservatism regularization for policies and value functions are combined and perfectly compatible with the continuous framework. The resulting dual regularization ensures the successful offline training of RL-based recommendation policies. Finally, we conduct extensive experiments to validate the effectiveness of our framework. The results show that compared to the discrete baselines, our ECoC is trained far more efficiently. Meanwhile, the final policies outperform baselines in both capturing the offline data and gaining long-term rewards. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

Research on Point-of-Interest Recommendation Method based on Graph Autoencoders and Long Short-Term Preferences 4

学校读者我要写书评

暂无评论

Research on Point-of-Interest Recommendation Method based on...

4th International Conference on Artificial intelligence and Computer Engineering, ICAICE 2023

作者： Lian, Xiaoqin Mi, Jiachen Gao, Chao Chen, Xiang Mai, Weimin Guan, Wenyang Gong, Yonggang Li, Jin School of Computer and Artificial Intelligence Beijing Technology and Business University Beijing100048 China School of Electronics and Information Technology Sun Yat-sen University Guangdong Province Guangzhou510006 China Key Laboratory of Industrial Internet and Big Data China National Light Industry Beijing Technology and Business University Beijing100048 China

ISBN: (纸本)9798400708831

Point-of-Interest (POI) recommendation is one of the most important tasks in the research of Location-based Social Networks (LBSNs). To solve the spatial sparsity problem in POI recommendation, this study proposed a recommendation model based on graph autoencoder (GAE) and long short-term preferences applied to location recommendation. Firstly, the POI transfer map of the check-in sequence is constructed, from which the hidden links between each POI are extracted using GAE to alleviate the troubles caused by data sparsity. Secondly, a long short-term preference extraction module is incorporated into the model, considering the influence of user preferences on user decisions. Finally, the proposed GELS model was tested on the Foursquare dataset and compared with results from other models. The GELS model in this study achieved Recall@10 scores of 0.6933 and 0.5099 on two different datasets, surpassing other models and demonstrating its superior performance in POI recommendation. The results show that GELS model can provide new ideas for POI recommendations. © 2023 ACM.

关键词： Recommender systems

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching

学校读者我要写书评

暂无评论

MoCha-Stereo: Motif Channel Attention Network for Stereo Mat...

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Ziyang Chen Wei Long He Yao Yongjun Zhang Bingshu Wang Yongbin Qin Jia Wu The State Key Laboratory of Public Big Data College of Computer Science and Technology Institute of Artificial Intelligence Guizhou University College of Software Northwest Polytechnical University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mis-matches. In this paper, the Motif Channel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif channels, which capture common geometric structures in feature channels, onto feature maps and cost volumes. In addition, edge variations in the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation. REMP integrates the frequency information of typical channel features from the re-construction error. MoCha-Stereo ranks 1st on the KITTI-2015 and KITTI-2012 Reflective leaderboards. Our structure also shows excellent performance in Multi- View Stereo.

关键词： Computer vision Costs Correlation Accuracy Estimation Pattern matching

datasets of Visualization for Machine Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Can Jiang, Ruike Tan, Shaocong Yu, Jiacheng Yang, Chaofan Shao, Hanning Yuan, Xiaoru Key Laboratory of Machine Perception Ministry of Education School of Intelligence Science and Technology Peking University China National Engineering Laboratory for Big Data Analysis and Application Peking University China

datasets of visualization play a crucial role in automating data-driven visualization pipelines, serving as the foundation for supervised model training and algorithm benchmarking. In this paper, we survey the literature on visualization datasets and provide a comprehensive overview of existing visualization datasets, including their data types, formats, supported tasks, and openness. We propose a what-why-how model for visualization datasets, considering the content of the dataset (what), the supported tasks (why), and the dataset construction process (how). This model provides a clear understanding of the diversity and complexity of visualization datasets. Additionally, we highlight the challenges faced by existing visualization datasets, including the lack of standardization in data types and formats and the limited availability of large-scale datasets. To address these challenges, we suggest future research directions. © 2024, CC BY.

关键词： Machine learning

Generative-Contrastive Graph Learning for Recommendation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Yonghui Wu, Zhengwei Wu, Le Zhang, Kun Hong, Richang Zhang, Zhiqiang Zhou, Jun Wang, Meng Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology China Ant Group China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

By treating users’ interactions as a user-item graph, graph learning models have been widely deployed in Collaborative Filtering (CF) based recommendation. Recently, researchers have introduced Graph Contrastive Learning (GCL) techniques into CF to alleviate the sparse supervision issue, which first constructs contrastive views by data augmentations and then provides self-supervised signals by maximizing the mutual information between contrastive views. Despite the effectiveness, we argue that current GCL-based recommendation models are still limited as current data augmentation techniques, either structure augmentation or feature augmentation. First, structure augmentation randomly dropout nodes or edges, which is easy to destroy the intrinsic nature of the user-item graph. Second, feature augmentation imposes the same scale noise augmentation on each node, which neglects the unique characteristics of nodes on the graph. To tackle the above limitations, we propose a novel Variational Graph Generative-Contrastive Learning (VGCL) framework for recommendation. Specifically, we leverage variational graph reconstruction to estimate a Gaussian distribution of each node, then generate multiple contrastive views through multiple samplings from the estimated distributions, which builds a bridge between generative and contrastive learning. The generated contrastive views can well reconstruct the input graph without information distortion. Besides, the estimated variances are tailored to each node, which regulates the scale of contrastive loss for each node on optimization. Considering the similarity of the estimated distributions, we propose a cluster-aware twofold contrastive learning, a node-level to encourage consistency of a node’s contrastive views and a cluster-level to encourage consistency of nodes in a cluster. Finally, extensive experimental results on three public datasets clearly demonstrate the effectiveness of the proposed model. Copyright © 2023, The Authors.

关键词： Collaborative filtering