检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zeng, Jia Huang, Lan Wang, Kangping College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education Jilin University Changchun130012 China

ISBN: (纸本)157735897X

Large-scale pre-trained Vision Transformer (ViT) models have demonstrated remarkable performance on visual tasks but are computationally expensive to transfer to downstream tasks. Parameter-Efficient Fine-Tuning (PEFT) offers a promising transferring approach by updating only a subset of parameters. However, PEFT’s effectiveness is hindered by discrepancies between pre-training and downstream tasks in terms of object scale and granularity. Downstream tasks often focus on finer-grained and more specialized recognition, requiring more detailed features. The diversity of feature scales of existing PEFT methods for ViT is limited. To address this, we propose a novel PEFT method named Wavelet-based multi-Scale Tuning (WST), which learns multi-scale features in a simple and efficient way. WST introduces a parallel finetuning patch embedding branch with a smaller patch size than the pre-trained model to capture finer-grained features. Furthermore, to handle the computational challenge from the resulting longer token sequence, WST designs wavelet finetuning blocks that balance both efficiency and performance. In the block, wavelet transform enables invertible and lossless down-sampling of the longer token sequence, aligning it with that of the backbone, and two lightweight linear mappings are employed to learn task-specific features. This design facilitates efficient multi-scale information exchange between the pre-trained backbone and fine-tuning branch. Extensive experiments on transfer learning demonstrate the promising performance and efficiency of our WST. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Contrastive Auxiliary Learning with Structure Transformation for Heterogeneous Graphs 39

Contrastive Auxiliary Learning with Structure Transformation...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Du, Wei Sun, Hongmin Gao, Hang Li, Gaoyang Li, Ying Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University China School of Life Sciences and Technology Tongji University China

ISBN: (纸本)157735897X

In recent years, methods based on heterogeneous graph neural networks (HGNNs) have been widely used for embedding heterogeneous graphs (HGs) due to their ability to effectively encode the rich information from HGs into low-dimensional node embeddings. Existing HGNNs focus on neighbor aggregation and semantic fusion while neglecting the HG structure and learning paradigms. However, the original data in the HG might lack node features, which may not be effectively accounted for by existing models. Additionally, exclusively relying on a single supervised learning approach may only partially leverage the invariant information in graph data. To address these challenges, we introduce the Contrastive Auxiliary Learning Model for Heterogeneous Graphs (CALHG), which combines edge perturbation and graph diffusion to enhance graph data, allowing it to capture the inherent structural information within heterogeneous graphs fully. Additionally, we employ a category-guided multi-view contrastive learning optimizing strategy, which does not rely on positive and negative samples for model training, enabling us to capture the intrinsic invariances in heterogeneous graph data. Extensive experiments and analyses on five benchmark datasets without node features and three benchmark datasets with node features validate the effectiveness and efficiency of our novel method compared with several state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Medical Image Feature Representation and Fusion for AD Early Diagnosis

Multimodal Medical Image Feature Representation and Fusion f...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Qu, Jing Qu, Ying Bai, Xueliang Xu, Lanxin Wang, Han Liu, Guixia Jilin University College of Computer Science and Technology Changchun China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun China North China University of Science and Technology College of Science Tangshan China Institute of Computational Biology Northeast Normal University School of Information Science and Technology Changchun China

ISBN: (纸本)9798350386226

Alzheimer's disease (AD) is progressive and gets worse with time. Early detection is an effective treatment for the disease, which can timely implement effective interventions. The multi-modal medical image contains more comprehensive and abundant information about the disease, which can reflect the different aspects of AD and reduce the potential bias in single-modal diagnosis. However, an effective and reliable solution is still lacking, which can integrate multimodal neuroimaging effectively for the precision diagnosis and treatment of AD. In this work, we proposed a feature representation and fusion model of MRI and PET scans based on a multiscale convolution network and cross-attention for AD early diagnosis, named camAD. Compared with the existing models, camAD performs better with fewer pre-processing steps. Using the Alzheimer's disease neuroimaging initiative (ADNI) datasets, we demonstrated that integrating multi-modality data outperforms single-modality models in accuracy, specificity, sensitivity, AUC, and F1 scores. Our models exhibited significantly good accuracy and generality in four classification tasks, which provided a promising way to understand the underlying mechanisms of the disorder's progression. © 2024 IEEE.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Utterance-level Emotion Recognition in Conversation with Conversation-level Supervision 39

Utterance-level Emotion Recognition in Conversation with Con...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Ximing Dai, Yuanchao Yang, Zhiyao Chi, Jinjin Gao, Wanfu Wu, Lin Yuanbo College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China Swansea University United Kingdom

ISBN: (纸本)157735897X

Emotion Recognition in Conversations (ERC) involves automatically identifying the emotion of each utterance in conversations. The emotion of an utterance is contingent to the conversation context, and thus, annotating each utterance in ERC entails repetitive screening the whole conversation from annotators. Such a requirement leads to prohibitive cost in fine-grained labeling on utterance. In this paper, we propose an efficient coarse-grained labeling strategy for ERC, which assigns a set of emotions for each conversation. In specific, we reformulate the ERC predictors with conversation-level emotion sets as weakly-supervised learning to optimise a potential candidate for ERC, which is termed as Dataless ERC (DERC). To validate this, we propose a simple-yet-flexible DERC framework with Progressive Learning (DERC-PL). We jointly update pseudo-utterance-level emotions and the ERC predictor in a self-training manner, where we progressively update the ERC predictor from training subsets with lower noise densities to the ones with higher noise densities. We implemented several versions of DERC-PL by incorporating various off-the-shelf ERC methods. Extensive experimental results demonstrate that the proposed DERC-PL can be on par with existing weakly-supervised learning baselines and supervised learning ERC methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Distributed solving Sylvester equations with fractional order dynamics

引用

Control Theory and Technology 2021年第2期19卷 249-259页

作者： Songsong Cheng Shu Liang Yuan Fan Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and AutomationAnhui UniversityHefei230601AnhuiChina Key Laboratory of Knowledge Automation for Industrial Processes of Ministry of Education School of Automation and Electrical EngineeringUniversity of Science and Technology BeijingBeijing100083China

This paper addresses distributed computation Sylvester equations of the form AX+XB=C with fractional order *** partitioning parameter matrices A,B and C,we transfer the problem of distributed solving Sylvester equations as two distributed optimization models and design two fractional order continuous-time algorithms,which have more design freedom and have potential to obtain better convergence performance than that of existing first order ***,rewriting distributed algorithms as corresponding frequency distributed models,we design Lyapunov functions and prove that proposed algorithms asymptotically converge to an exact or least squares ***,we validate the effectiveness of proposed algorithms by providing a numerical example.

关键词： Fractional order calculus Distributed optimization Sylvester equation Frequency distributed model Convergence

来源：评论

学校读者我要写书评

暂无评论

Diffuse tumors: Molecular determinants shared by different cancer types

引用

Computers in Biology and Medicine 2024年 178卷 108703-108703页

作者： Li, Xuan Liu, Dingyun Wu, Zhipeng Xu, Ying Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Changchun130012 China School of Medicine Southern University of Science and Technology Shenzhen China

Most cancer types have both diffuse and non-diffuse subtypes, which have rather distinct morphologies, namely scattered tiny tumors vs. one solid tumor, and different levels of aggressiveness. However, the causes for forming such distinct subtypes remain largely unknown. Using the diffuse and non-diffuse gastric cancers (GCs) as the illustrative example, we present a computational study based on the transcriptomic data from the TCGA and GEO databases, to address the following questions: (i) What are the key molecular determinants that give rise to the distinct morphologies between diffuse and non-diffuse cancers? (ii) What are the main reasons for diffuse cancers to be generally more aggressive than non-diffuse ones of the same cancer type? (iii) What are the reasons for their distinct immunoactivities? And (iv) why do diffuse cancers on average tend to take place in younger patients? The study is conducted using the framework we have previously developed for elucidation of general drivers cancer formation and development. Our main discoveries are: (a) the level of (poly-) sialic acids deployed on the surface of cancer cells is a significant factor contributing to questions (i) and (ii);(b) poly-sialic acids synthesized by ST8SIA4 are the key to question (iii);and (c) the circulating growth factors specifically needed by the diffuse subtype dictate the answer to question (iv). All these predictions are substantiated by published experimental studies. Our further analyses on breast, prostate, lung, liver, and thyroid cancers reveal that these discoveries generally apply to the diffuse subtypes of these cancer types, hence indicating the generality of our discoveries. © 2024

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Medical Image Segmentation using PCNN based on Multi-feature Grey Wolf Optimizer Bionic Algorithm

引用

Journal of Bionic engineering 2021年第3期18卷 711-720页

作者： Xue Wang Zhanshan Li Heng Kang Yongping Huang Di Gai College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchun 130012China ZICT Technology Co. Ltd.Shenzhen 518063China

Medical image segmentation is a challenging task especially in multimodality medical image *** this paper,an improved pulse coupled neural network based on multiple hybrid features grey wolf optimizer(MFGWO-PCNN)is proposed for multimodality medical image ***,a two-stage medical image segmentation method based on bionic algorithm is presented,including image fusion and image *** image fusion stage fuses rich information from different modalities by utilizing a multimodality medical image fusion model based on maximum energy *** the stage of image segmentation,an improved PCNN model based on MFGWO is proposed,which can adaptively set the parameters of PCNN according to the features of the *** modalities of FLAIR and TIC brain MRIs are applied to verify the effectiveness of the proposed MFGWO-PCNN *** experimental results demonstrate that the proposed method outperforms the other seven algorithms in subjective vision and objective evaluation indicators.

关键词： grey wolf optimizer pulse coupled neural network bionic algorithm medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

ResolvingWord Vagueness with Scenario-guided Adapter for Natural Language Inference

arXiv

引用

arXiv 2024年

作者： Liu, Yonghao Li, Mengyu Liang, Di Li, Ximing Giunchiglia, Fausto Huang, Lan Feng, Xiaoyue Guan, Renchu Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University China Fudan University China University of Trento Italy

Natural Language Inference (NLI) is a crucial task in natural language processing that involves determining the relationship between two sentences, typically referred to as the premise and the hypothesis. However, traditional NLI models solely rely on the semantic information inherent in independent sentences and lack relevant situational visual information, which can hinder a complete understanding of the intended meaning of the sentences due to the ambiguity and vagueness of language. To address this challenge, we propose an innovative ScenaFuse adapter that simultaneously integrates large-scale pre-trained linguistic knowledge and relevant visual information for NLI tasks. Specifically, we first design an image-sentence interaction module to incorporate visuals into the attention mechanism of the pre-trained model, allowing the two modalities to interact comprehensively. Furthermore, we introduce an image-sentence fusion module that can adaptively integrate visual information from images and semantic information from sentences. By incorporating relevant visual information and leveraging linguistic knowledge, our approach bridges the gap between language and vision, leading to improved understanding and inference capabilities in NLI tasks. Extensive benchmark experiments demonstrate that our proposed ScenaFuse, a scenario-guided approach, consistently boosts NLI performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Bridge approaches

来源：评论

学校读者我要写书评

暂无评论

Stable Learning via Triplex Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 5267-5276页

作者： Yang, Shuai Jiang, Tingting Dang, Qianlong Gu, Lichuan Wu, Xindong Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China Anhui Provincial Engineering Research Center for Agricultural Information Perception and Intelligent Computing Hefei230036 China Northwest A & F University College of Science Yangling712100 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data The Ministry of Education of China Hefei230601 China Hefei University of Technology School of Computer Science and Information Engineering Hefei230601 China

Stable learning aims to learn a model that generalizes well to arbitrary unseen target domain by leveraging a single source domain. Recent advances in stable learning have focused on balancing the distribution of confounders for each feature to eliminate spurious correlations. However, previous studies treat all features equally without considering the difficulties of confounder balancing associated with different features, and regard irrelevant features as confounders, deteriorating generalization performance. To tackle these issues, this article proposes a novel triplex learning (TriL) based stable learning algorithm, which performs sample reweighting, causal feature selection, and representation learning to remove spurious correlations. Specifically, first, TriL adaptively assigns weights to the confounder balancing term of each feature in accordance with the difficulties of confounder balancing, and aligns the confounder distribution of each feature by learning a group of sample weights. Second, TriL integrates the sample weights into a weighted cross-entropy model to compute causal effects of features for excluding irrelevant features from the confounder set. Finally, TriL relearns a set of sample weights and uses them to guide a new supervised dual-autoencoder containing two classifiers to learn feature representations. TriL forces the results of two classifiers to remain consistent for removing spurious correlations by using a cross-classifier consistency regularization. Extensive experiments on synthetic and two real-world datasets show the superiority of TriL compared with seven methods. © 2024 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling

arXiv

引用

arXiv 2024年

作者： Huang, Sili Hu, Jifeng Yang, Zhejian Yang, Liwei Luo, Tao Chen, Hechang Sun, Lichao Yang, Bo Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China School of Artificial Intelligence Jilin University China Institute of High Performance Computing A*STAR Singapore Lehigh University BethlehemPA United States

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement in online environments by providing task contexts, such as multiple trajectories, called in-context RL. However, due to the quadratic computation complexity of attention in transformers, current in-context RL methods suffer from huge computational costs as the task horizon increases. In contrast, the Mamba model is renowned for its efficient ability to process long-term dependencies, which provides an opportunity for in-context RL to solve tasks that require long-term memory. To this end, we first implement Decision Mamba (DM) by replacing the backbone of Decision Transformer (DT). Then, we propose a Decision Mamba-Hybrid (DM-H) with the merits of transformers and Mamba in high-quality prediction and long-term memory. Specifically, DM-H first generates high-value sub-goals from long-term memory through the Mamba model. Then, we use sub-goals to prompt the transformer, establishing high-quality predictions. Experimental results demonstrate that DM-H achieves state-of-the-art in long and short-term tasks, such as D4RL, Grid World, and Tmaze benchmarks. Regarding efficiency, the online testing of DM-H in the long-term task is 28× times faster than the transformer-based baselines. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：