Fine-grained Dependencies Research Articles

Enhancing Lithium-Ion Battery Health Predictions by Hybrid-Grained Graph Modeling.

Predicting the health status of lithium-ion batteries is crucial for ensuring safety. The prediction process typically requires inputting multiple time series, which exhibit temporal dependencies. Existing methods for health status prediction fail to uncover both coarse-grained and fine-grained temporal dependencies between these series. Coarse-grained analysis often overlooks minor fluctuations in the data, while fine-grained analysis can be overly complex and prone to overfitting, negatively impacting the accuracy of battery health predictions. To address these issues, this study developed a Hybrid-grained Evolving Aware Graph (HEAG) model for enhanced prediction of lithium-ion battery health. In this approach, the Fine-grained Dependency Graph (FDG) helps us model the dependencies between different sequences at individual time points, and the Coarse-grained Dependency Graph (CDG) is used for capturing the patterns and magnitudes of changes across time series. The effectiveness of the proposed method was evaluated using two datasets. Experimental results demonstrate that our approach outperforms all baseline methods, and the efficacy of each component within the HEAG model is validated through the ablation study.

Evolving masked low-rank transformer for long text understanding

Long sequence text processing is time-consuming owing to the ultra-large-scale self-attention computing. Recent advances demonstrate the attention in transformer can be accelerated by redundancy removal, and there are various sparse variants for attention in large sequences are proposed, which leads to state-of-the-art performance on language and vision task. Low-rank method achieve outstanding success in the field of efficient transformer. The dynamic token sparsification is efficiently time-saving and cost-saving, which can be easily extended to prune redundant spans and to yield semantic features. Evolutionary algorithm is attractive for selecting hyperparameter which is of significant importance in effectiveness. Motivated by these works, we propose an efficient transformers model, termed EMLT, to alleviate time and cost without sacrificing the accuracy. EMLT effectively combines strengths of Low-rank transformers, dynamic token sparsification and evolutionary algorithm to ulteriorly cut redundant token and meanwhile maintains the original precision, which can achieve a linear memory and time complexity. We compress transformer in three stages. Firstly, sliding window is validated as local attention to capture fine-grained dependency semantics. After that, low-rank approximation of attention matrix is applied as global attention to store long-range dependency semantics, and aggregated with local attention. On this basis, we consistently prune redundant token in accordance with importance score to further sparse the attention operation. Finally, Evolutionary algorithm is utilized to optimize the hyper-parameters of every layer. The results of comprehensive experiments and analysis show that our method can rival others on accuracy, and outperforms others on efficiency by a large margin in terms of the computational complexity.

Multivariate time series anomaly detection by fusion of deep convolution residual autoencoding reconstruction model and ConvLstm forecasting model

Multivariate time-series anomaly detection is very essential to ensure the normal operation of physical equipment. Great achievements have been made in this field in recent years. However, two critical challenges limit the generalization ability of the model. Graph attention networks without prior knowledge are unable to extract the distribution features of dependencies among variables in a fine granularity. This reduces the accuracy of the dependence matrix to represent the correlations between variables. Beyond this challenge, the reconstruction model loses the fine-grained seasonal feature information in the spatial dimension during the reconstruction analysis process of the sample. In order to solve the above challenges, we propose a multivariate time-series anomaly detection model consisting of characterization network and forecasting network. In the characterization network, we first remove non-existent dependencies between variables by using prior knowledge. This approach can accurately capture the fine-grained dependency distribution features between variables and improve the accuracy of the dependence matrix representation of the correlations between variables. We then construct a deep convolutional residual autoencoder to reduce the loss of seasonal feature information in the spatial dimension. In forecasting network, we construct a temporal attention-based ConvLstm forecasting network to make fine-grained anomaly decisions on the output of the characterization network in the time dimension. We perform systematic experiments on six open-source datasets, in social network security scenario,the malicous acount behavior can be detected. Experimental results show that the proposed method outperforms the baseline anomaly detection methods with excellent detection performance and robustness. Specifically, our method achieves an average F1 score improvement of 0.23 over the baseline method at its highest level.

Microservice architecture recovery based on intra-service and inter-service features

Microservice architecture supports independent development and deployment; it facilitates software system design and co-development. However, it also brings new challenges to a variety of software engineering tasks, especially in reverse engineering. An improper design or maintenance routine may cause complex invocation, obscure code logic, and complicate service layers, which may lead to difficulties in understanding, even further testing, or maintenance. To reduce the severity of this problem, we present a novel microservice architecture recovery technique that parses the source code to build a fine-grained dependency graph. This process recovers six key information components of the microservice architecture, which helps developers understand the system. Experimental results based on 12 projects show that the recovered accuracy is 94% on average. The results benefit any engineer unfamiliar with the project, increases their answering accuracy by 23.81% on average, and reduces their training time by 65.43% on average.

Fine-grained bidirectional attentional generation and knowledge-assisted networks for cross-modal retrieval

Generally, most existing cross-modal retrieval methods only consider global or local semantic embeddings, lacking fine-grained dependencies between objects. At the same time, it is usually ignored that the mutual transformation between modalities also facilitates the embedding of modalities. Given these problems, we propose a method called BiKA (Bidirectional Knowledge-assisted embedding and Attention-based generation). The model uses a bidirectional graph convolutional neural network to establish dependencies between objects. In addition, it employs a bidirectional attention-based generative network to achieve the mutual transformation between modalities. Specifically, the knowledge graph is used for local matching to constrain the local expression of the modalities, in which the generative network is used for mutual transformation to constrain the global expression of the modalities. In addition, we also propose a new position relation embedding network to embed position relation information between objects. The experiments on two public datasets show that the performance of our method has been dramatically improved compared to many state-of-the-art models.

MSFF-Net: Multi-scale feature fusing networks with dilated mixed convolution and cascaded parallel framework for sound event detection

Sound Event Detection (SED) needs to identify the sound events in a recording and detect the onset and offset times of them. The former desires features with long short-term dependencies to detect sound events with different durations and the latter needs fine-grained dependency. Although our previous proposed Multi-Scale Fully Convolutional Networks (MS-FCN) uses cascaded dilated convolution to model temporal context information and multi-scale information is considered, there are two shortages to deal with: the ignorance of neighboring information and fine-grained dependencies, and neglecting intermediate-length temporal dependencies. The first shortage is caused by the skipping elements sampling mechanism of dilated convolution, by which the neighboring information and fine-grained dependencies are ignored. To overcome this shortage, the paper proposes the dilated mixed convolution module, which mixes dilated convolution and standard convolutions to capture both the fine-grained and long-term dependencies and give weight to neighboring information. The second shortage is caused by the too fast increase of temporal dependent length in cascaded dilated convolution module, which causes too much intermediate temporal information to be ignored. For this shortage, this paper proposes Dilated Temporal Pyramid Pooling module (DTPP), in which parallel dilated convolutions with multiple dilation factors are used to capture the intermediate temporal information with a proper temporal dependent length. As cascaded module has been demonstrated to be valid and efficient to model the temporal context in MS-FCN and DTPP module can capture the ignored temporal information of cascaded module, taking the advantages of both, this paper proposes the cascaded parallel module to capture richer temporal dependencies. Based on that, Multi-Scale Feature Fusion Networks (MSFF-Net) is proposed, which obtains competitive performance on three open datasets.

Fine-grained attribute weighted inverted specific-class distance measure for nominal attributes

The inverted specific-class distance measure (ISCDM) ranks first in the list of distance metrics that deal solely with nominal attributes, especially when values are missing and noise exists in non-class attributes. However, the attribute independence assumption still inevitably exists, which is almost untenable in many real-world applications with sophisticated attribute dependencies. Many improved versions based on different attribute weighting schemes have been proposed to relax this unrealistic assumption and circumvent its damage to measuring performance. However, existing attribute weighting schemes are limited to assigning a weight corresponding to each attribute; they ignore the more fine-grained dependence relationships between attributes and classes. Thus, in this study, we derive a novel fine-grained attribute weighting scheme, which first calculates the initial fine-grained attribute weights according to different attribute values and class labels and then uses random walk with restart to optimize them. We titled our improved measure fine-grained attribute-weighted ISCDM (FAWISCDM). Extensive experimental results on 66 datasets from a machine learning repository, collected by the University of California at Irvine illustrate that the FAWISCDM is notably superior to the original ISCDM and some other state-of-the-art competing methods, in terms of the negative conditional log likelihood and root relative squared error.

Topic modeling for sequential documents based on hybrid inter-document topic dependency

We propose two new topic modeling methods for sequential documents based on hybrid inter-document topic dependency. Topic modeling for sequential documents is the basis of many attractive applications such as emerging topic clustering and novel topic detection. For these tasks, most of the existing models introduce inter-document dependencies between topic distributions. However, in a real situation, adjacent emerging topics are often intertwined and mixed with outliers. These single-dependency based models have difficulties in handling the topic evolution in such multi-topic and outlier mixed sequential documents. To solve this problem, our first method considers three kinds of topic dependencies for each document to handle its probabilities of belonging to a fading topic, an emerging topic, or an independent topic. Secondly, we extend our first method by considering fine-grained dependencies in a given context for more complex topic evolution sequences. Our experiments conducted on six standard datasets on topic modeling show that our proposals outperform state-of-the-art models in terms of the accuracy of topic modeling, the quality of topic clustering, and the effectiveness of outlier detection.

Syntactic Annotation in the I3rab Dependency Treebank

Arabic dependency parsers have a poor performance compared to parsers of other languages. Recently the impact of annotation at lexical level of dependency treebank on the overall performance of the dependency parses has been extensively investigated. This paper focuses on the impact of coarse-grained and fine-grained dependency relations on the performance of Arabic dependency parsers. Moreover, this paper introduces the annotation rules for I3rab dependency treebank. Experimentally, the obtained results showed that having an appropriate set of dependency relations improves the performance of an Arabic dependency parser up to 27.55%.

Multi-cultural Wikipedia mining of geopolitics interactions leveraging reduced Google matrix analysis

Geopolitics focuses on political power in relation to geographic space. Interactions among world countries have been widely studied at various scales, observing economic exchanges, world history or international politics among others. This work exhibits the potential of Wikipedia mining for such studies. Indeed, Wikipedia stores valuable fine-grained dependencies among countries by linking webpages together for diverse types of interactions (not only related to economical, political or historical facts). We mine herein the Wikipedia networks of several language editions using the recently proposed method of reduced Google matrix analysis. This approach allows to establish direct and hidden links between a subset of nodes that belong to a much larger directed network. Our study concentrates on 40 major countries chosen worldwide. Our aim is to offer a multicultural perspective on their interactions by comparing networks extracted from five different Wikipedia language editions, emphasizing English, Russian and Arabic ones. We demonstrate that this approach allows to recover meaningful direct and hidden links among the 40 countries of interest.

Gentoo Linux for Neuroscience - a replicable, flexible, scalable, rolling-release environment that provides direct access to development software

Gentoo is a GNU/Linux metadistribution designed to maximize and simplify user control of the software environment. All determinants of a Gentoo environment are recorded in a small number of plain-text configuration files, from which the software make-up of the system can be reconstructed entirely. As such, Gentoo constitutes a replicable and transparent software infrastructure - as mandated by research valuing reproducibility. Of equal scientific interest is the flexibility of Gentoo's package management. All software is distributed in a rolling-release fashion, giving the user full control over which versions (including live versions and branches/tags from version control) of which programs to install, and with which compilation options. All of the above is accompanied by automatic, version-aware dependency resolution, which also tracks static library linking and prompts for rebuilds as necessary. We believe Gentoo is excellently suited to address many of the challenges in neuroscience software management; including: system replicability, system documentation, data analysis reproducibility, fine-grained dependency management, easy control over compilation options, and seamless access to cutting-edge software releases. We have made a substantial set of neuroimaging and data analysis packages - including their entire dependency stacks - available for any system using Gentoo's Package Management Standard. Neuroscientific software now usable under Gentoo includes but is not limited to: Dipy (Garyfallidis et al. 2014) FSL (Jenkinson et al. 2012) Nipype (Gorgolewski et al. 2016) Nilearn (Abraham et al. 2014) PsychoPy (Peirce 2008) Herein we describe the implementation and current capabilities of this environment, as well as its ability to accelerate and improve research.

A MATERIALIST VIEW OF HUMAN PERSONS AND BELIEF IN THE AFTERLIFE

Current neuroscience favours a materialist over a dualist view of human personhood, as exemplified by the phenomenon of blindsight. The fine-grained dependence of consciousness on neural activity renders a non-physical soul causally irrelevant. Since Christians believe in the resurrection of the body, not the soul, materialism is compatible with the life of the world to come. The branching of causal paths provides a possible model for bodily resurrection.

A case study in preserving a high energy physics application with Parrot

The reproducibility of scientific results increasingly depends upon the preservation of computational artifacts. Although preserving a computation to be used later sounds easy, it is surprisingly difficult due to the complexity of existing software and systems. Implicit dependencies, networked resources, and shifting compatibility all conspire to break applications that appear to work well. To investigate these issues, we present a case study of a complex high energy physics application. We analyze the application and attempt several methods at extracting its dependencies for the purposes of preservation. We propose one fine-grained dependency management toolkit to preserve the application and demonstrate its correctness in three different environments - the original machine, one virtual machine from the Notre Dame Cloud Platform and one virtual machine from the Amazon EC2 Platform. We report on the completeness, performance, and efficiency of each technique, and offer some guidance for future work in application preservation.

Labeling workflow views with fine-grained dependencies

This paper considers the problem of efficiently answering reachability queries over views of provenance graphs, derived from executions of workflows that may include recursion. Such views include composite modules and model fine-grained dependencies between module inputs and outputs. A novel view-adaptive dynamic labeling scheme is developed for efficient query evaluation, in which view specifications are labeled statically (i.e. as they are created) and data items are labeled dynamically as they are produced during a workflow execution. Although the combination of fine-grained dependencies and recursive workflows entail, in general, long (linear-size) data labels, we show that for a large natural class of workflows and views, labels are compact (logarithmic-size) and reachability queries can be evaluated in constant time. Experimental results demonstrate the benefit of this approach over the state-of-the-art technique when applied for labeling multiple views.

Putting lipstick on pig

Workflow provenance typically assumes that each module is a "black-box", so that each output depends on all inputs ( coarse-grained dependencies). Furthermore, it does not model the internal state of a module, which can change between repeated executions. In practice, however, an output may depend on only a small subset of the inputs ( fine-grained dependencies) as well as on the internal state of the module. We present a novel provenance framework that marries database-style and workflow-style provenance, by using Pig Latin to expose the functionality of modules, thus capturing internal state and fine-grained dependencies. A critical ingredient in our solution is the use of a novel form of provenance graph that models module invocations and yields a compact representation of fine-grained workflow provenance. It also enables a number of novel graph transformation operations, allowing to choose the desired level of granularity in provenance querying (ZoomIn and ZoomOut), and supporting "what-if" workflow analytic queries. We implemented our approach in the Lipstick system and developed a benchmark in support of a systematic performance evaluation. Our results demonstrate the feasibility of tracking and querying fine-grained workflow provenance.