Searcharxiv⌕ Search

arXiv subjects

Jianxun Liu

Publications and source records attributed to Jianxun Liu.

13 recordsLinked to original sources
arXiv2025

Spiking Heterogeneous Graph Attention Networks

Real-world graphs or networks are usually heterogeneous, involving multiple types of nodes and relationships. Heterogeneous graph neural networks (HGNNs) can effectively handle these diverse nodes and edges, capturing heterogeneous information within the graph, thus exhibiting outstanding performance. However, most methods of HGNNs usually involve complex structural designs, leading to problems such as high memory usage, long inference time, and extensive consumption of computing resources. These limitations pose certain challenges for the practical application of HGNNs, especially for resource-constrained devices. To mitigate this issue, we propose the Spiking Heterogeneous Graph Attention Networks (SpikingHAN), which incorporates the brain-inspired and energy-saving properties of Spiking Neural Networks (SNNs) into heterogeneous graph learning to reduce the computing cost without compromising the performance. Specifically, SpikingHAN aggregates metapath-based neighbor information using a single-layer graph convolution with shared parameters. It then employs a semantic-level attention mechanism to capture the importance of different meta-paths and performs semantic aggregation. Finally, it encodes the heterogeneous information into a spike sequence through SNNs, simulating bioinformatic processing to derive a binarized 1-bit representation of the heterogeneous graph. Comprehensive experimental results from three real-world heterogeneous graph datasets show that SpikingHAN delivers competitive node classification performance. It achieves this with fewer parameters, quicker inference, reduced memory usage, and lower energy consumption. Code is available at https://github.com/QianPeng369/SpikingHAN.

cs.NE↗
arXiv2023

Estimation of the User Contribution Rate by Leveraging Time Sequence in Pairwise Matching function-point between Users Feedback and App Updating Log

Mobile applications have become an inseparable part of people's daily life. Nonetheless, the market competition is extremely fierce, and apps lacking recognition among most users are susceptible to market elimination. To this end, developers must swiftly and accurately apprehend the requirements of the wider user base to effectively strategize and promote their apps' orderly and healthy evolution. The rate at which general user requirements are adopted by developers, or user contribution, is a very valuable metric that can be an important tool for app developers or software engineering researchers to measure or gain insight into the evolution of app requirements and predict the evolution of app software. Regrettably, the landscape lacks refined quantitative analysis approaches and tools for this pivotal indicator. To address this problem, this paper exploratively proposes a quantitative analysis approach based on the temporal correlation perception that exists in the app update log and user reviews, which provides a feasible solution for quantitatively obtaining the user contribution. The main idea of this scheme is to consider valid user reviews as user requirements and app update logs as developer responses, and to mine and analyze the pairwise and chronological relationships existing between the two by text computing, thus constructing a feasible approach for quantitatively calculating user contribution. To demonstrate the feasibility of the approach, this paper collects data from four Chinese apps in the App Store in mainland China and one English app in the U.S. region, including 2,178 update logs and 4,236,417 user reviews, and from the results of the experiment, it was found that 16.6%-43.2% of the feature of these apps would be related to the drive from the online popular user requirements.

cs.SE↗
arXiv2022

Nonconvex ${L_ {1/2}} $-Regularized Nonlocal Self-similarity Denoiser for Compressive Sensing based CT Reconstruction

Compressive sensing (CS) based computed tomography (CT) image reconstruction aims at reducing the radiation risk through sparse-view projection data. It is usually challenging to achieve satisfying image quality from incomplete projections. Recently, the nonconvex ${L_ {1/2}} $-norm has achieved promising performance in sparse recovery, while the applications on imaging are unsatisfactory due to its nonconvexity. In this paper, we develop a ${L_ {1/2}} $-regularized nonlocal self-similarity (NSS) denoiser for CT reconstruction problem, which integrates low-rank approximation with group sparse coding (GSC) framework. Concretely, we first split the CT reconstruction problem into two subproblems, and then improve the CT image quality furtherly using our ${L_ {1/2}} $-regularized NSS denoiser. Instead of optimizing the nonconvex problem under the perspective of GSC, we particularly reconstruct CT image via low-rank minimization based on two simple yet essential schemes, which build the equivalent relationship between GSC based denoiser and low-rank minimization. Furtherly, the weighted singular value thresholding (WSVT) operator is utilized to optimize the resulting nonconvex ${L_ {1/2}} $ minimization problem. Following this, our proposed denoiser is integrated with the CT reconstruction problem by alternating direction method of multipliers (ADMM) framework. Extensive experimental results on typical clinical CT images have demonstrated that our approach can further achieve better performance than popular approaches.

eess.IV↗
arXiv2020

Evolutionary Architecture Search for Graph Neural Networks

Automated machine learning (AutoML) has seen a resurgence in interest with the boom of deep learning over the past decade. In particular, Neural Architecture Search (NAS) has seen significant attention throughout the AutoML research community, and has pushed forward the state-of-the-art in a number of neural models to address grid-like data such as texts and images. However, very litter work has been done about Graph Neural Networks (GNN) learning on unstructured network data. Given the huge number of choices and combinations of components such as aggregator and activation function, determining the suitable GNN structure for a specific problem normally necessitates tremendous expert knowledge and laborious trails. In addition, the slight variation of hyper parameters such as learning rate and dropout rate could dramatically hurt the learning capacity of GNN. In this paper, we propose a novel AutoML framework through the evolution of individual models in a large GNN architecture space involving both neural structures and learning parameters. Instead of optimizing only the model structures with fixed parameter settings as existing work, an alternating evolution process is performed between GNN structures and learning parameters to dynamically find the best fit of each other. To the best of our knowledge, this is the first work to introduce and evaluate evolutionary architecture search for GNN models. Experiments and validations demonstrate that evolutionary NAS is capable of matching existing state-of-the-art reinforcement learning approaches for both the semi-supervised transductive and inductive node representation learning and classification.

cs.NE↗
arXiv2019

Feature-Attention Graph Convolutional Networks for Noise Resilient Learning

Noise and inconsistency commonly exist in real-world information networks, due to inherent error-prone nature of human or user privacy concerns. To date, tremendous efforts have been made to advance feature learning from networks, including the most recent Graph Convolutional Networks (GCN) or attention GCN, by integrating node content and topology structures. However, all existing methods consider networks as error-free sources and treat feature content in each node as independent and equally important to model node relations. The erroneous node content, combined with sparse features, provide essential challenges for existing methods to be used on real-world noisy networks. In this paper, we propose FA-GCN, a feature-attention graph convolution learning framework, to handle networks with noisy and sparse node content. To tackle noise and sparse content in each node, FA-GCN first employs a long short-term memory (LSTM) network to learn dense representation for each feature. To model interactions between neighboring nodes, a feature-attention mechanism is introduced to allow neighboring nodes learn and vary feature importance, with respect to their connections. By using spectral-based graph convolution aggregation process, each node is allowed to concentrate more on the most determining neighborhood features aligned with the corresponding learning task. Experiments and validations, w.r.t. different noise levels, demonstrate that FA-GCN achieves better performance than state-of-the-art methods on both noise-free and noisy networks.

cs.LG↗
arXiv2019

Multi-Label Graph Convolutional Network Representation Learning

Knowledge representation of graph-based systems is fundamental across many disciplines. To date, most existing methods for representation learning primarily focus on networks with simplex labels, yet real-world objects (nodes) are inherently complex in nature and often contain rich semantics or labels, e.g., a user may belong to diverse interest groups of a social network, resulting in multi-label networks for many applications. The multi-label network nodes not only have multiple labels for each node, such labels are often highly correlated making existing methods ineffective or fail to handle such correlation for node representation learning. In this paper, we propose a novel multi-label graph convolutional network (ML-GCN) for learning node representation for multi-label networks. To fully explore label-label correlation and network topology structures, we propose to model a multi-label network as two Siamese GCNs: a node-node-label graph and a label-label-node graph. The two GCNs each handle one aspect of representation learning for nodes and labels, respectively, and they are seamlessly integrated under one objective function. The learned label representations can effectively preserve the inner-label interaction and node label properties, and are then aggregated to enhance the node representation learning under a unified training framework. Experiments and comparisons on multi-label node classification validate the effectiveness of our proposed approach.

cs.LG↗
arXiv2019

ClassyTune: A Performance Auto-Tuner for Systems in the Cloud

Performance tuning can improve the system performance and thus enable the reduction of cloud computing resources needed to support an application. Due to the ever increasing number of parameters and complexity of systems, there is a necessity to automate performance tuning for the complicated systems in the cloud. The state-of-the-art tuning methods are adopting either the experience-driven tuning approach or the data-driven one. Data-driven tuning is attracting increasing attentions, as it has wider applicability. But existing data-driven methods cannot fully address the challenges of sample scarcity and high dimensionality simultaneously. We present ClassyTune, a data-driven automatic configuration tuning tool for cloud systems. ClassyTune exploits the machine learning model of classification for auto-tuning. This exploitation enables the induction of more training samples without increasing the input dimension. Experiments on seven popular systems in the cloud show that ClassyTune can effectively tune system performance to seven times higher for high-dimensional configuration space, outperforming expert tuning and the state-of-the-art auto-tuning solutions. We also describe a use case in which performance tuning enables the reduction of 33% computing resources needed to run an online stateless service.

cs.PF↗
arXiv2017

Ultrahigh charge electron beams from laser-irradiated solid surface

Compact acceleration of a tightly collimated relativistic electron beam with high charge from a laser-plasma interaction has many unique applications. However, currently the well-known schemes, including laser wakefield acceleration from gases and vacuum laser acceleration from solids, often produce electron beams either with low charge or with large divergence angles. In this work, we report the generation of highly collimated electron beams with a divergence angle of a few degrees, quasi-monoenergetic spectra peaked at the MeV level, and extremely high charge ($\sim$100 nC) via a powerful sub-ps laser pulse interacting with a solid target in grazing incidence. Particle-in-cell simulations illustrate a new direct laser acceleration scenario, in which the self-filamentation is triggered in a large-scale near-critical-density plasma and electron bunches are accelerated periodically and collimated by the ultra-intense electromagnetic field. The energy density of such electron beams in high-Z materials reaches to $\sim10^{12} \mathrm{J/m^{3}}$, making it a promising tool to drive warm or even hot dense matter states.

physics.plasm-ph↗
arXiv2017

BestConfig: Tapping the Performance Potential of Systems via Automatic Configuration Tuning

An ever increasing number of configuration parameters are provided to system users. But many users have used one configuration setting across different workloads, leaving untapped the performance potential of systems. A good configuration setting can greatly improve the performance of a deployed system under certain workloads. But with tens or hundreds of parameters, it becomes a highly costly task to decide which configuration setting leads to the best performance. While such task requires the strong expertise in both the system and the application, users commonly lack such expertise. To help users tap the performance potential of systems, we present BestConfig, a system for automatically finding a best configuration setting within a resource limit for a deployed system under a given application workload. BestConfig is designed with an extensible architecture to automate the configuration tuning for general systems. To tune system configurations within a resource limit, we propose the divide-and-diverge sampling method and the recursive bound-and-search algorithm. BestConfig can improve the throughput of Tomcat by 75%, that of Cassandra by 63%, that of MySQL by 430%, and reduce the running time of Hive join job by about 50% and that of Spark join job by about 80%, solely by configuration adjustment.

cs.PF↗
arXiv2017

ACTS in Need: Automatic Configuration Tuning with Scalability Guarantees

To support the variety of Big Data use cases, many Big Data related systems expose a large number of user-specifiable configuration parameters. Highlighted in our experiments, a MySQL deployment with well-tuned configuration parameters achieves a peak throughput as 12 times much as one with the default setting. However, finding the best setting for the tens or hundreds of configuration parameters is mission impossible for ordinary users. Worse still, many Big Data applications require the support of multiple systems co-deployed in the same cluster. As these co-deployed systems can interact to affect the overall performance, they must be tuned together. Automatic configuration tuning with scalability guarantees (ACTS) is in need to help system users. Solutions to ACTS must scale to various systems, workloads, deployments, parameters and resource limits. Proposing and implementing an ACTS solution, we demonstrate that ACTS can benefit users not only in improving system performance and resource utilization, but also in saving costs and enabling fairer benchmarking.

cs.DC↗
arXiv2017

ACIA, not ACID: Conditions, Properties and Challenges

Although ACID is the previous golden rule for transaction support, durability is now not a basic requirement for data storage. Rather, high availability is becoming the first-class property required by online applications. We show that high availability of data is almost surely a stronger property than durability. We thus propose ACIA (Atomicity, Consistency, Isolation, Availability) as the new standard for transaction support. Essentially, the shift from ACID to ACIA is due to the change of assumed conditions for data management. Four major condition changes exist. With ACIA transactions, more diverse requirements can be flexibly supported for applications through the specification of consistency levels, isolation levels and fault tolerance levels. Clarifying the ACIA properties enables the exploitation of techniques used for ACID transactions, as well as bringing about new challenges for research.

cs.DC↗
arXiv2017

To Vote Before Decide: A Logless One-Phase Commit Protocol for Highly-Available Datastores

Highly-available datastores are widely deployed for online applications. However, many online applications are not contented with the simple data access interface currently provided by highly-available datastores. Distributed transaction support is demanded by applications such as large-scale online payment used by Alipay or Paypal. Current solutions to distributed transaction can spend more than half of the whole transaction processing time in distributed commit. An efficient atomic commit protocol is highly desirable. This paper presents the HACommit protocol, a logless one-phase commit protocol for highly-available systems. HACommit has transaction participants vote for a commit before the client decides to commit or abort the transaction; in comparison, the state-of-the-art practice for distributed commit is to have the client decide before participants vote. The change enables the removal of both the participant logging and the coordinator logging steps in the distributed commit process; it also makes possible that, after the client initiates the transaction commit, the transaction data is visible to other transactions within one communication roundtrip time (i.e., one phase). In the evaluation with extensive experiments, HACommit outperforms recent atomic commit solutions for highly-available datastores under different workloads. In the best case, HACommit can commit in one fifth of the time 2PC does.

cs.DC↗