检索结果-内蒙古大学图书馆

TFGDA: exploring topology and feature alignment in semi-supervised graph domain adaptation through robust clustering 24

学校读者我要写书评

暂无评论

TFGDA: exploring topology and feature alignment in semi-supe...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jun Dan Weiming Liu Chunfeng xie Hua Yu Shunjie Dong Yanchao Tan Zhejiang University Queen Mary University of London Dalian University of Technology Shanghai Jiao Tong University Fuzhou University and Engineering Research Center of Big Data Intelligence Ministry of Education and Fujian Key Laboratory of Network Computing and Intelligent Information Processing

ISBN: (纸本)9798331314385

Semi-supervised graph domain adaptation, as a branch of graph transfer learning, aims to annotate unlabeled target graph nodes by utilizing transferable knowledge learned from a label-scarce source graph. However, most existing studies primarily concentrate on aligning feature distributions directly to extract domain-invariant features, while ignoring the utilization of the intrinsic structure information in graphs. Inspired by the significance of data structure information in enhancing models' generalization performance, this paper aims to investigate how to leverage the structure information to assist graph transfer learning. To this end, we propose an innovative framework called TFGDA. Specially, TFGDA employs a structure alignment strategy named STSA to encode graphs' topological structure information into the latent space, greatly facilitating the learning of transferable features. To achieve a stable alignment of feature distributions, we also introduce a SDA strategy to mitigate domain discrepancy on the sphere. Moreover, to address the overfitting issue caused by label scarcity, a simple but effective RNC strategy is devised to guide the discriminative clustering of unlabeled nodes. Experiments on various benchmarks demonstrate the superiority of TFGDA over SOTA methods.

关键词：

Graph Convolutional Neural Network with Inter-layer Cascade Based on Attention Mechanism 7

学校读者我要写书评

暂无评论

Graph Convolutional Neural Network with Inter-layer Cascade ...

7th IEEE International Conference on Cloud computing and Intelligence Systems, CCIS 2021

作者： Wei, Lu Liu, Yiting Feng, Kaiyuan Li, Jianzhao Sheng, Kai Wu, Yue Xidian University Key Laboratory of Big Data and Intelligent Vision School of Computer Science and Technology Xi'an710071 China Xidian University Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education School of Electronic Engineering Xi'an710071 China Academy of Advanced Interdisciplinary Research Xidian University Xi'an710071 China

ISBN: (纸本)9781665441490

In recent years, graph data in the non-Euclidean space has been widely used, and the methods and techniques for learning graph data in many deep learning fields have been continuously developed, such as the Graph neural network (GNN). The structural characteristics of graph data, the aggregation mode and representation mode of node information, and the node neighbor information are the core issues of GNN. However, most of the existing graph convolutional neural networks have an excessive smoothing problem, which limits the learning ability of the model. Aiming at the over-smoothing problem of the current algorithm, this paper enhances the learning of graph data by improving the expression ability of local information and global features. This paper constructs a cascade structure between graph convolutional layers. This kind of network structure realizes the dense connection of convolutional layers, makes the local feature information is effectively used, and further enhances the graph representation ability. Introduce self-attention and TopK into the Readout module, selectively aggregate and express feature information, and use graph-level information more efficiently. Graph classification is a downstream task to verify the performance of the proposed model. Experimental results prove that this densely structured graph convolutional network can effectively aggregate local node information and global graph-level information. © 2021 IEEE.

关键词： Graph neural networks

AUCSeg: AUC-oriented pixel-level long-tail semantic segmentation 24

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented pixel-level long-tail semantic segmenta...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Boyu Han Qianqian Xu Zhiyong Yang Shilong Bao Peisong Wen Yangbangyan Jiang Qingming Huang Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory School of Computer Science and Tech. University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg.

关键词：

Factual Serialization Enhancement: A key Innovation for Chest X-ray Report Generation

学校读者我要写书评

暂无评论

arxiv 2024年

作者： Liu, Kang Ma, Zhuoqi Liu, Mengmeng Jiao, Zhicheng Kang, xiaolu Miao, Qiguang xie, Kun The School of Computer Science and Technology Xidian University Shaanxi Xi’an710071 China The Xi'an Key Laboratory of Big Data and Intelligent Vision Shaanxi Xi’an710071 China The Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi’an710071 China The School of Artificial Intelligence Xidian University Xi’an710071 China The Department of Diagnostic Imaging Brown University ProvidenceRI02903-4923 United States

A radiology report comprises presentation-style vocabulary, which ensures clarity and organization, and factual vocabulary, which provides accurate and objective descriptions based on observable findings. While manually writing these reports is time-consuming and labor-intensive, automatic report generation offers a promising alternative. A critical step in this process is to align radiographs with their corresponding reports. However, existing methods often rely on complete reports for alignment, overlooking the impact of presentation-style vocabulary. To address this issue, we propose FSE, a two-stage Factual Serialization Enhancement method. In Stage 1, we introduce factuality-guided contrastive learning for visual representation by maximizing the semantic correspondence between radiographs and corresponding factual descriptions. In Stage 2, we present evidence-driven report generation that enhances diagnostic accuracy by integrating insights from similar historical cases structured as factual serialization. Experiments on MIMIC-CXR and IU X-ray datasets across specific and general scenarios demonstrate that FSE outperforms state-of-the-art approaches in both natural language generation and clinical efficacy metrics. Ablation studies further emphasize the positive effects of factual serialization in Stage 1 and Stage 2. The code is available at https://***/mk-runner/FSE. Copyright © 2024, The Authors. All rights reserved.

关键词： Report generators

Rethink Video Retrieval Representation for Video Captioning

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Tian, Mingkai Li, Guorong Qi, Yuankai Wang, Shuhui Sheng, Quan Z. Huang, Qingming School of Computer Science and Technology Key Lab of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences China School of Computing Macquarie University Australia Key Laboratory of Intelligent Information Processing Institute of Computer Technology Chinese Academy of Sciences China

Video captioning, a challenging task targeting the automatic generation of accurate and comprehensive descriptions based on video content, has witnessed substantial success recently driven by bridging video representations and textual semantics. Inspired by the nature of the video retrieval task, which learns visual features strongly related to text queries, we propose to take advantage of visual representation learning from the video retrieval framework to tackle video captioning tasks. However, a simple direct application of video retrieval models performs poorly due to the weak ability to capture sufficient video details and temporal information required for video captioning. To increase the attention on details, we propose a learnable token shift module, which flexibly captures subtle movements in local regions across the temporal sequence. Furthermore, we devise a Refineformer, which learns to integrate local video tokens strongly related to desired captions via a cross-attention mechanism. Extensive experiments on MSVD, MSR-VTT and VATEX demonstrate the favorable performance of our method. © 2024, The Authors. All rights reserved.

关键词： Semantics

A BCS-GDE Multi-objective Optimization Algorithm for Combined Cooling, Heating and Power Model with Decision Strategies

学校读者我要写书评

暂无评论

arxiv 2022年

作者： Sun, Jiaze Deng, Jiahui Li, Yang Han, Nan School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an710121 China Xi 'an Key Laboratory of Big Data and Intelligent Computing Xi’an710127 China School of Information Science and Technology Northwest University Xi’an710127 China School of Electrical Engineering Northeast Electric Power University Jilin132012 China

District energy systems can not only reduce energy consumption but also set energy supply dispatching schemes according to demand. In addition to economic cost, energy consumption and pollutant are more worthy of attention when evaluating combined cooling, heating and power (CCHP) models. In this paper, the CCHP model is established with the objective of economic cost, primary energy consumption, and pollutant emissions. The mathematical expression of the CCHP system is proposed, and a multi-objective optimization model with constraints is established. According to different usage requirements, two decision-making strategies are designed, which can adapt to different scenarios. Besides, a generalized differential evolution with the best compromise solution processing mechanism (BCS-GDE) algorithm is proposed to optimize the CCHP model for the first time. The algorithm provides the optimal energy scheduling scheme by optimizing the production capacity of different capacity equipment. The simulation is conducted in three application scenarios: hotels, offices, and residential buildings. The simulation results show that the model established in this paper can reduce economic cost by 72%, primary energy consumption by 73%, and pollutant emission by 88%. Concurrently, the Wilcoxon signed-rank test shows that BCS-GDE is significantly better than OMOPSO, NSGA-II, and SPEA2 with greater than 95% confidence. Copyright © 2022, The Authors. All rights reserved.

关键词： Evolutionary algorithms

LEGNN: A Label Ensemble Perspective for Training a Label-Noise-Resistant GNN with Reduced Complexity

学校读者我要写书评

暂无评论

arxiv 2024年

作者： Zhao, Rui Shi, Bin Liang, Zhiming Ruan, Jianfei Dong, Bo Lin, Lu School of Computer Science and Technology Xi'an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering China School of Distance Education Xi'an Jiaotong University China College of Information Sciences and Technology Penn State University United States

Graph Neural Networks (GNNs) have been widely employed for semi-supervised node classification tasks on graphs. However, the performance of GNNs is significantly affected by label noise, that is, a small amount of incorrectly labeled nodes can substantially misguide model training. Mainstream solutions define node classification with label noise (NCLN) as a reliable labeling task, often introducing node similarity with quadratic computational complexity to more accurately assess label reliability. To this end, in this paper, we introduce the Label Ensemble Graph Neural Network (LEGNN), a lower complexity method for robust GNNs training against label noise. LEGNN reframes NCLN as a label ensemble task, gathering informative multiple labels instead of constructing a single reliable label, avoiding high-complexity computations for reliability assessment. Specifically, LEGNN conducts a two-step process: bootstrapping neighboring contexts and robust learning with gathered multiple labels. In the former step, we apply random neighbor masks for each node and gather the predicted labels as a high-probability label set. This mitigates the impact of inaccurately labeled neighbors and diversifies the label set. In the latter step, we utilize a partial label learning based strategy to aggregate the high-probability label information for model training. Additionally, we symmetrically gather a low-probability label set to counteract potential noise from the bootstrapped high-probability label set. Extensive experiments on six datasets demonstrate that LEGNN achieves outstanding performance while ensuring efficiency. Moreover, it exhibits good scalability on dataset with over one hundred thousand nodes and one million edges. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

EvoSampling: A Granular Ball-based Evolutionary Hybrid Sampling with Knowledge Transfer for Imbalanced Learning

学校读者我要写书评

暂无评论

arxiv 2024年

作者： Pei, Wenbin Dai, Ruohao Xue, Bing Zhang, Mengjie Zhang, Qiang Cheung, Yiu-Ming xia, Shuyin The School of Computer Science and Technology Dalian University of Technology Dalian116024 China Ministry of Education Dalian116024 China The School of Engineering and Computer Science Victoria University of Wellington PO Box 600 Wellington6140 New Zealand The Department of Computer Science Hong Kong Baptist University Hong Kong The Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China

Class imbalance would lead to biased classifiers that favor the majority class and disadvantage the minority class. Unfortunately, from a practical perspective, the minority class is of importance in many real-life applications. Hybrid sampling methods address this by oversampling the minority class to increase the number of its instances, followed by undersampling to remove low-quality instances. However, most existing sampling methods face difficulties in generating diverse high-quality instances and often fail to remove noise or low-quality instances on a larger scale effectively. This paper therefore proposes an evolutionary multi-granularity hybrid sampling method, called EvoSampling. During the oversampling process, genetic programming (GP) is used with multi-task learning to effectively and efficiently generate diverse high-quality instances. During the undersampling process, we develop a granular ball-based undersampling method that removes noise in a multi-granular fashion, thereby enhancing data quality. Experiments on 20 imbalanced datasets demonstrate that EvoSampling effectively enhances the performance of various classification algorithms by providing better datasets than existing sampling methods. Besides, ablation studies further indicate that allowing knowledge transfer accelerates the GP's evolutionary learning process. Copyright © 2024, The Authors. All rights reserved.

关键词：

K-ON: Stacking Knowledge On the Head Layer of Large Language Model

学校读者我要写书评

暂无评论

arxiv 2025年

作者： Guo, Lingbing Zhang, Yichi Bo, Zhongpu Chen, Zhuo Sun, Mengshu Zhang, Zhiqiang Zhang, Wen Chen, Huajun College of Computer Science and Technology Zhejiang University China ZJU-Ant Group Joint Lab of Knowledge Graph China Ant Group China School of Software Technology Zhejiang University China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Recent advancements in large language models (LLMs) have significantly improved various natural language processing (NLP) tasks. Typically, LLMs are trained to predict the next token, aligning well with many NLP tasks. However, in knowledge graph (KG) scenarios, entities are the fundamental units and identifying an entity requires at least several tokens. This leads to a granularity mismatch between KGs and natural languages. To address this issue, we propose K-ON, which integrates KG knowledge into the LLM by employing multiple head layers for next k-step prediction. K-ON can not only generate entity-level results in one step, but also enables contrastive loss against entities, which is the most powerful tool in KG representation learning. Experimental results show that K-ON outperforms state-of-the-art methods that incorporate text and even the other modalities. Copyright © 2025, The Authors. All rights reserved.

关键词： Knowledge graph