检索结果-内蒙古大学图书馆

DouGNN: An End-to-End Deep Learning Framework for Predicting Individual Behaviors from fMRI Data

学校读者我要写书评

暂无评论

DouGNN: An End-to-End Deep Learning Framework for Predicting...

Image Processing, Computer Vision and machine Learning (ICICML), International Conference on

作者： Qumei Cao Xuyun Wen College of Computer Science and Technology MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China

Predicting individual behavior from functional connectivity (FC) using machine learning is a critical research topic in neuroscience. While various models have been proposed, they mainly focus on designing behavior prediction methods, overlooking the influence of upstream FC network construction approach on downstream tasks. In this paper, leveraging graph neural networks (GNNs), we introduce an end-to-end deep learning framework named DouGNN, aimed at learning individual behavior from fMRI data. Through joint training of two GNNs, DouGNN innovatively integrates individualized cortical parcellation (for FC network construction) and individual behavior prediction into a unified optimization model. By integrating individualized cortical parcellation, the model gains the ability to dynamically modify the subject’s cortical parcellation and the downstream tasks. This enhancement enables the subsequently constructed FC networks to better represent individual-specific features and task-related characteristics, thereby significantly improving the performance of individual behavior prediction. Moreover, the generated individual-specific, task-aware cortical parcellations from this process can also help us in understanding the relationship between FC and behaviors. We conducted three representative behavior prediction experiments on the publicly available HCP dataset. The results demonstrate that DouGNN outperforms existing methods in all behavior prediction tasks, achieving superior performance and generating more functionally homogeneous individualized cortical parcellations.

关键词：

AADL and Modelica model combination and model conversion based on CPS 4

学校读者我要写书评

暂无评论

AADL and Modelica model combination and model conversion bas...

4th International Conference on Electronic Information Technology and Computer Engineering, EITCE 2020

作者： Zhu, Yifeng Cao, Zining Wang, Fujun Lu, Weiwei College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China College of Computer Science and Technology Collaborative Innovation Center of Novel Software Technology and Industrialization Miit Key Laboratory of Pattern Analysis and Machine Intelligence Luoyang China Science and Technology on Electro-optic Control Laboratory Luoyang China

ISBN: (纸本)9781450387811

Cyber-Physical System (CPS), which realizes the close integration of physical resources and information resources, is a distributed and asynchronous dynamic hybrid system running in different time and space. In this paper, we use AADL to model information system and use Modelica to model physical system. However, they are all semi-formal models such that we cannot do future work about formal verification. To overcome this defect, we convert them to formal models like automaton through conversion algorithms and rules. Due to the fact of probabilistic events and resource consumption in CPS, this paper adopts the weighted probabilistic hybrid automaton as formal model, and adds the properties of probability and weight to the behavior annex of AADL. Then we conduct the rule and algorithm of the model conversion. In order to ensure consistency of further work about model checking, the paper prove the equivalence of the two models by bisimulation. Finally, the capability of modeling of the extended modeling language of AADL and the significance of conversion to automaton is illustrated by the aircraft system. © 2020 ACM.

关键词： Cyber Physical System

View-labels Are Indispensable: A Multifacet Complementarity Study of Multi-view Clustering

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Geng, Chuanxing Han, Aiyang Chen, Songcan The College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

Consistency and complementarity are two key ingredients for boosting multi-view clustering (MVC). Recently with the introduction of popular contrastive learning, the consistency learning of views has been further enhanced in MVC, leading to promising performance. However, by contrast, the complementarity has not received sufficient attention except just in the feature facet, where the Hilbert Schmidt Independence Criterion (HSIC) term or the independent encoder-decoder network is usually adopted to capture view-specific information. This motivates us to reconsider the complementarity learning of views comprehensively from multiple facets including the feature-, view-label- and contrast- facets, while maintaining the view consistency. We empirically find that all the facets contribute to the complementarity learning, especially the view-label facet, which is usually neglected by existing methods. Based on this, we develop a novel Multifacet Complementarity learning framework for Multi-View Clustering (MCMVC), which fuses multifacet complementarity information, especially explicitly embedding the view-label information. To our best knowledge, it is the first time to use view-labels explicitly to guide the complementarity learning of views. Compared with the SOTA baseline, MCMVC achieves remarkable improvements, e.g., by average margins over 5.00% and 7.00% respectively in complete and incomplete MVC settings on Caltech101-20 in terms of three evaluation metrics. © 2022, CC BY.

关键词：

Personalized Federated Semi-Supervised Learning with Black-Box Models

学校读者我要写书评

暂无评论

Personalized Federated Semi-Supervised Learning with Black-B...

IEEE International Conference on Data Mining (ICDM)

作者： Siyin Huang Shao-Yuan Li Songcan Chen College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

Federated Semi-Supervised Learning alleviates the necessity for fully labeled data in Federated Learning. However, it does not sufficiently prioritize model privacy or the personalized requirements of clients. To address these concerns, our key idea is to communicate no longer individual model parameters but their black-box models, implying to provide other clients with only an input-output interface of individual models. The communication mechanism is model-agnostic, thereby facilitating adaption to heterogeneous models for each client through customization. Consequently, we propose a framework called Personalized Federated Semi-Supervised Learning with Black-Box Models (B 2 PFSSL) to enhance the privacy of communication. To prevent negative knowledge transfer due to data heterogeneity, we design a two-stage strategy that filters at both the model and data levels, enabling clients to obtain large training datasets by including more high-quality pseudo-labeled data under conditions of scarce labeled data. The experimental results indicate that B 2 PFSSL achieves competitive performance while reducing the amount of information exposed during communication. Furthermore, it can foster productive collaboration among diverse model architectures in model heterogeneous Federated Learning.

关键词：

Contextual Conservative Q-Learning for Offline Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Jiang, Ke Yao, Jiayu Tan, Xiaoyang College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

Offline reinforcement learning learns an effective policy on offline datasets without online interaction, and it attracts persistent research attention due to its potential of practical application. However, extrapolation error generated by distribution shift will still lead to the overestimation for those actions that transit to out-of-distribution(OOD) states, which degrades the reliability and robustness of the offline policy. In this paper, we propose Contextual Conservative Q-Learning(C-CQL) to learn a robustly reliable policy through the contextual information captured via an inverse dynamics model. With the supervision of the inverse dynamics model, it tends to learn a policy that generates stable transition at perturbed states, for the fact that pertuebed states are a common kind of OOD states. In this manner, we enable the learnt policy more likely to generate transition that destines to the empirical next state distributions of the offline dataset, i.e., robustly reliable transition. Besides, we theoretically reveal that C-CQL is the generalization of the Conservative Q-Learning(CQL) and aggressive State Deviation Correction(SDC). Finally, experimental results demonstrate the proposed C-CQL achieves the state-of-the-art performance in most environments of offline Mujoco suite and a noisy Mujoco setting. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

MuSiCNet: A Gradual Coarse-to-Fine Framework for Irregularly Sampled Multivariate Time Series analysis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Jiexi Cao, Meng Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautic China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

Irregularly sampled multivariate time series (ISMTS) are prevalent in reality. Most existing methods treat ISMTS as synchronized regularly sampled time series with missing values, neglecting that the irregularities are primarily attributed to variations in sampling rates. In this paper, we introduce a novel perspective that irregularity is essentially relative in some senses. With sampling rates artificially determined from low to high, an irregularly sampled time series can be transformed into a hierarchical set of relatively regular time series from coarse to fine. We observe that additional coarse-grained relatively regular series not only mitigate the irregularly sampled challenges to some extent but also incorporate broad-view temporal information, thereby serving as a valuable asset for representation learning. Therefore, following the philosophy of learning that Seeing the big picture first, then delving into the details, we present the Multi-Scale and Multi-Correlation Attention Network (MuSiCNet) combining multiple scales to iteratively refine the ISMTS representation. Specifically, within each scale, we explore time attention and frequency correlation matrices to aggregate intra- and inter-series information, naturally enhancing the representation quality with richer and more intrinsic details. While across adjacent scales, we employ a representation rectification method containing contrastive learning and reconstruction results adjustment to further improve representation consistency. MuSiCNet is an ISMTS analysis framework that competitive with SOTA in three mainstream tasks consistently, including classification, interpolation, and forecasting. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

5W1H Extraction With Large Language Models

学校读者我要写书评

暂无评论

5W1H Extraction With Large Language Models

International Joint Conference on Neural Networks (IJCNN)

作者： Yang Cao Yangsong Lan Feiyan Zhai Piji Li College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The extraction of essential news elements through the 5W1H framework (What, When, Where, Why, Who, and How) is critical for event extraction and text summarization. The advent of Large language models (LLMs) such as Chat-GPT presents an opportunity to address language-related tasks through simple prompts without fine-tuning models with much time. While ChatGPT has encountered challenges in processing longer news texts and analyzing specific attributes in context, especially answering questions about What, Why, and How. The effectiveness of extraction tasks is notably dependent on high-quality human-annotated datasets. However, the absence of such datasets for the 5W1H extraction increases the difficulty of fine-tuning strategies based on open-source LLMs. To address these limitations, first, we annotate a high-quality 5W1H dataset based on four typical news corpora (CNN/DailyMail, XSum, NYT, RA-MDS); second, we design several strategies from zero-shot/few-shot prompting to efficient fine-tuning to conduct 5W1H aspects extraction from the original news documents. The experimental results demonstrate that the performance of the fine-tuned models on our labelled dataset is superior to the performance of ChatGPT. Furthermore, we also explore the domain adaptation capability by testing the source-domain (e.g. NYT) models on the target domain corpus (e.g. CNN/DailyMail) for the task of 5W1H extraction.

关键词： Adaptation models Large language models Neural networks Training data Text summarization Chatbots Data models

A DEEP MODEL FOR PARTIAL MULTI-LABEL IMAGE CLASSIFICATION WITH CURRICULUM BASED DISAMBIGUATION

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Sun, Feng Xie, Ming-Kun Huang, Sheng-Jun College of Computer Science and Technology Nanjing University of Aeronautics Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing211106 China

In this paper, we study the partial multi-label (PML) image classification problem, where each image is annotated with a candidate label set consists of multiple relevant labels and other noisy labels. Existing PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions, which unfortunately is unavailable in many real tasks. Furthermore, because the objective function for disambiguation is usually elaborately designed on the whole training set, it can be hardly optimized in a deep model with SGD on mini-batches. In this paper, for the first time we propose a deep model for PML to enhance the representation and discrimination ability. On one hand, we propose a novel curriculum based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different classes. On the other hand, a consistency regularization is introduced for model retraining to balance fitting identified easy labels and exploiting potential relevant labels. Extensive experimental results on the commonly used benchmark datasets show the proposed method significantly outperforms the SOTA methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

Accelerated stochastic gradient-free and projection-free methods

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Huang, Feihu Tao, Lue Chen, Songcan College of Computer Science & Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China MIIT Key Laboratory of Pattern Analysis & Machine Intelligence

In the paper, we propose a class of accelerated stochastic gradient-free and projection-free (a.k.a., zeroth-order Frank-Wolfe) methods to solve the constrained stochastic and finite-sum nonconvex optimization. Specifically, we propose an accelerated stochastic zeroth-order Frank-Wolfe (Acc-SZOFW) method based on the variance reduced technique of SPIDER/SpiderBoost and a novel momentum accelerated technique. Moreover, under some mild conditions, we prove that the Acc-SZOFW has the function query complexity of O(d√n∊−2) for finding an ∊-stationary point in the finite-sum problem, which improves the exiting best result by a factor of O(√n∊−2), and has the function query complexity of O(d∊−3) in the stochastic problem, which improves the exiting best result by a factor of O(∊−1). To relax the large batches required in the Acc-SZOFW, we further propose a novel accelerated stochastic zeroth-order Frank-Wolfe (Acc-SZOFW*) based on a new variance reduced technique of STORM, which still reaches the function query complexity of O(d∊−3) in the stochastic problem without relying on any large batches. In particular, we present an accelerated framework of the Frank-Wolfe methods based on the proposed momentum accelerated technique. The extensive experimental results on black-box adversarial attack and robust black-box classification demonstrate the efficiency of our algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems