检索结果-内蒙古大学图书馆

All Beings Are Equal in Open Set Recognition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Li, Chaohua Zhang, Enhao Geng, Chuanxing Chen, Songcan College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

In open-set recognition (OSR), a promising strategy is exploiting pseudo-unknown data outside given K known classes as an additional K+1-th class to explicitly model potential open space. However, treating unknown classes without distinction is unequal for them relative to known classes due to the category-agnostic and scale-agnostic of the unknowns. This inevitably not only disrupts the inherent distributions of unknown classes but also incurs both class-wise and instance-wise imbalances between known and unknown classes. Ideally, the OSR problem should model the whole class space as K+∞, but enumerating all unknowns is impractical. Since the core of OSR is to effectively model the boundaries of known classes, this means just focusing on the unknowns nearing the boundaries of targeted known classes seems sufficient. Thus, as a compromise, we convert the open classes from infinite to K, with a novel concept Target-Aware Universum (TAU) and propose a simple yet effective framework Dual Contrastive Learning with Target-Aware Universum (DCTAU). In details, guided by the targeted known classes, TAU automatically expands the unknown classes from the previous 1 to K, effectively alleviating the distribution disruption and the imbalance issues mentioned above. Then, a novel Dual Contrastive (DC) loss is designed, where all instances irrespective of known or TAU are considered as positives to contrast with their respective negatives. Experimental results indicate DCTAU sets a new state-of-the-art. Copyright © 2024, The Authors. All rights reserved.

关键词： machine learning

TimeCHEAT: A Channel Harmony Strategy 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 Astronautics China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China

Irregularly sampled multivariate time series (ISMTS) are prevalent in reality. Due to their non-uniform intervals between successive observations and varying sampling rates among series, the channel-independent (CI) strategy, which has been demonstrated more desirable for complete multivariate time series forecasting in recent studies, has failed. This failure can be further attributed to the sampling sparsity, which provides insufficient information for effective CI learning, thereby reducing its capacity. When we resort to the channel-dependent (CD) strategy, even higher capacity cannot mitigate the potential loss of diversity in learning similar embedding patterns across different channels. We find that existing work considers CI and CD strategies to be mutually exclusive, primarily because they apply these strategies to the global channel. However, we hold the view that channel strategies do not necessarily have to be used globally. Instead, by appropriately applying them locally and globally, we can create an opportunity to take full advantage of both strategies. This leads us to introduce the Channel Harmony ISMTS Transformer (TimeCHEAT), which utilizes the CD strategy locally and the CI strategy globally. Specifically, we segment the ISMTS into sub-series level patches. Locally, the CD strategy aggregates information within each patch for time embedding learning, maximizing the use of relevant observations while reducing long-range irrelevant interference. Here, we enhance generality by transforming embedding learning into an edge weight prediction task using bipartite graphs, eliminating the need for special prior knowledge. Globally, the CI strategy is applied across patches, allowing the Transformer to learn individualized attention patterns for each channel. Experimental results indicate our proposed TimeCHEAT demonstrates competitive state-of-the-art performance across three mainstream tasks including classification, forecasting and interpolation. Copyri

关键词： Time series analysis

Dirichlet-Based Prediction Calibration for Learning with Noisy Labels

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zong, Chen-Chen Wang, Ye-Wen Xie, Ming-Kun Huang, Sheng-Jun College of Computer Science and Technology/Artificial Intelligence Nanjing University of Aeronautics Astronautics MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing China

Learning with noisy labels can significantly hinder the generalization performance of deep neural networks (DNNs). Existing approaches address this issue through loss correction or example selection methods. However, these methods often rely on the model’s predictions obtained from the softmax function, which can be over-confident and unreliable. In this study, we identify the translation invariance of the softmax function as the underlying cause of this problem and propose the Dirichlet-based Prediction Calibration (DPC) method as a solution. Our method introduces a calibrated softmax function that breaks the translation invariance by incorporating a suitable constant in the exponent term, enabling more reliable model predictions. To ensure stable model training, we leverage a Dirichlet distribution to assign probabilities to predicted labels and introduce a novel evidence deep learning (EDL) loss. The proposed loss function encourages positive and sufficiently large logits for the given label, while penalizing negative and small logits for other labels, leading to more distinct logits and facilitating better example selection based on a large-margin criterion. Through extensive experiments on diverse benchmark datasets, we demonstrate that DPC achieves state-of-the-art performance. The code is available at https://***/chenchenzong/DPC. Copyright © 2024, The Authors. All rights reserved.

关键词： Forecasting

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：

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

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