arXiv subjects

Lin Meng

Publications and source records attributed to Lin Meng.

12 recordsLinked to original sources

arXiv2025

Pre-emptive parametric kill switch for evaporative atomic sources in vacuum

A robust pre-emptive kill switch for cold atom experiments is introduced to significantly reduce costly system reassembly or replacement. The design incorporates upper (alarm) and lower (evaporation) event detection mechanisms based on predefined thresholds. Meanwhile, a duty cycle timing methodology is used to avert unintentional activation of the dispenser in circumstances where pulse signals occur. The circuit employs generic components, a modular design, and formalized logic, ensuring cost-effectiveness, making the design suitable for school laboratories and other research environments. This design is highly versatile and can be applied to other sensitive devices beyond dispensers, such as heating filaments, titanium sublimation pumps, tungsten lamps, and comparable systems.

physics.atom-ph↗

arXiv2025

DeFT: Mitigating Data Dependencies for Flexible Communication Scheduling in Distributed Training

Communication scheduling aims to reduce communication bottlenecks in data parallel training (DP) by maximizing the overlap between computation and communication. However, existing schemes fall short due to three main issues: (1) hard data dependencies break some overlapping between communication and computation; (2) high coverage rates impair further improvement on performance; (3) imbalanced communication/computation times of tensors caused by partitioning/fusion strategies cause more bubbles. To address these drawbacks, we propose a new communication scheduling scheme DeFT, whose key insight is to mitigate data dependencies and support flexible scheduling in distributed training. DeFT uncovers new overlapping chances in training by transforming the scheduling problem into multiple knapsack problems. Specifically, DeFT eliminates hard dependencies with delayed updates, reducing the coverage rate by adjusting update frequency and utilizing heterogeneous communication links, merging the computation times of backward or forward as the knapsack capacity to avoid the negative impact of unbalanced tensors. Additionally, DeFT preserves training accuracy by adjusting its scheduling strategy via convergence loss quantification. Extensive experiments with 16 A100 GPUs showed that DeFT achieved speedups of 29% to 115% on three representative benchmarks compared to US-Byte and Bytescheduler with no loss of accuracy.

cs.DC↗

arXiv2023

Predicting Continuous Locomotion Modes via Multidimensional Feature Learning from sEMG

Walking-assistive devices require adaptive control methods to ensure smooth transitions between various modes of locomotion. For this purpose, detecting human locomotion modes (e.g., level walking or stair ascent) in advance is crucial for improving the intelligence and transparency of such robotic systems. This study proposes Deep-STF, a unified end-to-end deep learning model designed for integrated feature extraction in spatial, temporal, and frequency dimensions from surface electromyography (sEMG) signals. Our model enables accurate and robust continuous prediction of nine locomotion modes and 15 transitions at varying prediction time intervals, ranging from 100 to 500 ms. In addition, we introduced the concept of 'stable prediction time' as a distinct metric to quantify prediction efficiency. This term refers to the duration during which consistent and accurate predictions of mode transitions are made, measured from the time of the fifth correct prediction to the occurrence of the critical event leading to the task transition. This distinction between stable prediction time and prediction time is vital as it underscores our focus on the precision and reliability of mode transition predictions. Experimental results showcased Deep-STP's cutting-edge prediction performance across diverse locomotion modes and transitions, relying solely on sEMG data. When forecasting 100 ms ahead, Deep-STF surpassed CNN and other machine learning techniques, achieving an outstanding average prediction accuracy of 96.48%. Even with an extended 500 ms prediction horizon, accuracy only marginally decreased to 93.00%. The averaged stable prediction times for detecting next upcoming transitions spanned from 28.15 to 372.21 ms across the 100-500 ms time advances.

cs.RO↗

arXiv2023

Near-Linear Scaling Data Parallel Training with Overlapping-Aware Gradient Compression

Existing Data Parallel (DP) trainings for deep neural networks (DNNs) often experience limited scalability in speedup due to substantial communication overheads. While Overlapping technique can mitigate such problem by paralleling communication and computation in DP, its effectiveness is constrained by the high communication-to-computation ratios (CCR) of DP training tasks. Gradient compression (GC) is a promising technique to obtain lower CCR by reducing communication volume directly. However, it is challenging to obtain real performance improvement by applying GC into Overlapping because of (1) severe performance penalties in traditional GCs caused by high compression overhead and (2) decline of Overlapping benefit owing to the possible data dependency in GC schemes. In this paper, we propose COVAP, a novel GC scheme designing a new coarse-grained filter, makes the compression overhead close to zero. COVAP ensures an almost complete overlap of communication and computation by employing adaptive compression ratios and tensor sharding tailored to specific training tasks. COVAP also adopts an improved error feedback mechanism to maintain training accuracy. Experiments are conducted on Alibaba Cloud ECS instances with different DNNs of real-world applications. The results illustrate that COVAP outperforms existent GC schemes in time-to-solution by 1.92x-15.39x and exhibits near-linear scaling. Furthermore, COVAP achieves best scalability under experiments on four different cluster sizes.

cs.DC↗

arXiv2021

Recognition of Oracle Bone Inscriptions by using Two Deep Learning Models

Oracle bone inscriptions (OBIs) contain some of the oldest characters in the world and were used in China about 3000 years ago. As an ancient form of literature, OBIs store a lot of information that can help us understand the world history, character evaluations, and more. However, as OBIs were found only discovered about 120 years ago, few studies have described them, and the aging process has made the inscriptions less legible. Hence, automatic character detection and recognition has become an important issue. This paper aims to design a online OBI recognition system for helping preservation and organization the cultural heritage. We evaluated two deep learning models for OBI recognition, and have designed an API that can be accessed online for OBI recognition. In the first stage, you only look once (YOLO) is applied for detecting and recognizing OBIs. However, not all of the OBIs can be detected correctly by YOLO, so we next utilize MobileNet to recognize the undetected OBIs by manually cropping the undetected OBI in the image. MobileNet is used for this second stage of recognition as our evaluation of ten state-of-the-art models showed that it is the best network for OBI recognition due to its superior performance in terms of accuracy, loss and time consumption. We installed our system on an application programming interface (API) and opened it for OBI detection and recognition.

cs.CV↗

arXiv2020

Deoscillated Graph Collaborative Filtering

Collaborative Filtering (CF) signals are crucial for a Recommender System~(RS) model to learn user and item embeddings. High-order information can alleviate the cold-start issue of CF-based methods, which is modelled through propagating the information over the user-item bipartite graph. Recent Graph Neural Networks~(GNNs) propose to stack multiple aggregation layers to propagate high-order signals. However, the oscillation problem, varying locality of bipartite graph, and the fix propagation pattern spoil the ability of multi-layer structure to propagate information. The oscillation problem results from the bipartite structure, as the information from users only propagates to items. Besides oscillation problem, varying locality suggests the density of nodes should be considered in the propagation process. Moreover, the layer-fixed propagation pattern introduces redundant information between layers. In order to tackle these problems, we propose a new RS model, named as \textbf{D}eoscillated \textbf{G}raph \textbf{C}ollaborative \textbf{F}iltering~(DGCF). We introduce cross-hop propagation layers in it to break the bipartite propagating structure, thus resolving the oscillation problem. Additionally, we design innovative locality-adaptive layers which adaptively propagate information. Stacking multiple cross-hop propagation layers and locality layers constitutes the DGCF model, which models high-order CF signals adaptively to the locality of nodes and layers. Extensive experiments on real-world datasets show the effectiveness of DGCF. Detailed analyses indicate that DGCF solves oscillation problem, adaptively learns local factor, and has layer-wise propagation pattern. Our code is available online at https://github.com/JimLiu96/DeosciRec.

cs.IR↗

arXiv2020

Value driven Analysis Framework of Service Ecosystem Evolution Mechanism

With the development of cloud computing, service computing, IoT(Internet of Things) and mobile Internet, the diversity and sociality of services are increasingly apparent. To meet the customized user demands, Service Ecosystem is emerging as a complex social-technology system, which is formed with various IT services through cross-border integration. However, how to analyze and promote the evolution mechanism of service ecosystem is still a serious challenge in the field, which is of great significance to achieve the expected system evolution trends. Based on this, this paper proposes a value-driven analysis framework of service ecosystem, including value creation, value operation, value realization and value distribution. In addition, a computational experiment system is established to verify the effectiveness of the analysis framework, which stimulates the effect of different operation strategies on the value network in the service ecosystem. The result shows that our analysis framework can provide new means and ideas for the analysis of service ecosystem evolution, and can also support the design of operation strategies. Index

cs.OH↗

arXiv2019

Scalable Heterogeneous Social Network Alignment through Synergistic Graph Partition

Social network alignment has been an important research problem for social network analysis in recent years. With the identified shared users across networks, it will provide researchers with the opportunity to achieve a more comprehensive understanding of users' social activities both within and across networks. Social network alignment is a very difficult problem. Besides the challenges introduced by the network heterogeneity, the network alignment problem can be reduced to a combinatorial optimization problem with an extremely large search space. The learning effectiveness and efficiency of existing alignment models will be degraded significantly as the network size increases. In this paper, we will focus on studying the scalable heterogeneous social network alignment problem, and propose to address it with a novel two-stage network alignment model, namely \textbf{S}calable \textbf{H}eterogeneous \textbf{N}etwork \textbf{A}lignment (SHNA). Based on a group of intra- and inter-network meta diagrams, SHNA first partitions the social networks into a group of sub-networks synergistically. Via the partially known anchor links, SHNA will extract the partitioned sub-network correspondence relationships. Instead of aligning the complete input network, SHNA proposes to identify the anchor links between the matched sub-network pairs, while those between the unmatched sub-networks will be pruned to effectively shrink the search space. Extensive experiments have been done to compare SHNA with the state-of-the-art baseline methods on a real-world aligned social networks dataset. The experimental results have demonstrated both the effectiveness and efficiency of the {\our} model in addressing the problem.

cs.SI↗

arXiv2019

GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation

The existing graph neural networks (GNNs) based on the spectral graph convolutional operator have been criticized for its performance degradation, which is especially common for the models with deep architectures. In this paper, we further identify the suspended animation problem with the existing GNNs. Such a problem happens when the model depth reaches the suspended animation limit, and the model will not respond to the training data any more and become not learnable. Analysis about the causes of the suspended animation problem with existing GNNs will be provided in this paper, whereas several other peripheral factors that will impact the problem will be reported as well. To resolve the problem, we introduce the GResNet (Graph Residual Network) framework in this paper, which creates extensively connected highways to involve nodes' raw features or intermediate representations throughout the graph for all the model layers. Different from the other learning settings, the extensive connections in the graph data will render the existing simple residual learning methods fail to work. We prove the effectiveness of the introduced new graph residual terms from the norm preservation perspective, which will help avoid dramatic changes to the node's representations between sequential layers. Detailed studies about the GResNet framework for many existing GNNs, including GCN, GAT and LoopyNet, will be reported in the paper with extensive empirical experiments on real-world benchmark datasets.

cs.LG↗

arXiv2019

Graph Neural Lasso for Dynamic Network Regression

The regression of multiple inter-connected sequence data is a problem in various disciplines. Formally, we name the regression problem of multiple inter-connected data entities as the "dynamic network regression" in this paper. Within the problem of stock forecasting or traffic speed prediction, we need to consider both the trends of the entities and the relationships among the entities. A majority of existing approaches can't capture that information together. Some of the approaches are proposed to deal with the sequence data, like LSTM. The others use the prior knowledge in a network to get a fixed graph structure and do prediction on some unknown entities, like GCN. To overcome the limitations in those methods, we propose a novel graph neural network, namely Graph Neural Lasso (GNL), to deal with the dynamic network problem. GNL extends the GDU (gated diffusive unit) as the base neuron to capture the information behind the sequence. Rather than using a fixed graph structure, GNL can learn the dynamic graph structure automatically. By adding the attention mechanism in GNL, we can learn the dynamic relations among entities within each network snapshot. Combining these two parts, GNL is able to model the dynamic network problem well. Experimental results provided on two networked sequence datasets, i.e., Nasdaq-100 and METR-LA, show that GNL can address the network regression problem very well and is also very competitive among the existing approaches.

cs.LG↗

arXiv2019

IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification

Deep learning models have achieved huge success in numerous fields, such as computer vision and natural language processing. However, unlike such fields, it is hard to apply traditional deep learning models on the graph data due to the 'node-orderless' property. Normally, adjacency matrices will cast an artificial and random node-order on the graphs, which renders the performance of deep models on graph classification tasks extremely erratic, and the representations learned by such models lack clear interpretability. To eliminate the unnecessary node-order constraint, we propose a novel model named Isomorphic Neural Network (IsoNN), which learns the graph representation by extracting its isomorphic features via the graph matching between input graph and templates. IsoNN has two main components: graph isomorphic feature extraction component and classification component. The graph isomorphic feature extraction component utilizes a set of subgraph templates as the kernel variables to learn the possible subgraph patterns existing in the input graph and then computes the isomorphic features. A set of permutation matrices is used in the component to break the node-order brought by the matrix representation. Three fully-connected layers are used as the classification component in IsoNN. Extensive experiments are conducted on benchmark datasets, the experimental results can demonstrate the effectiveness of ISONN, especially compared with both classic and state-of-the-art graph classification methods.

cs.LG↗

arXiv2017

LATTE: Application Oriented Social Network Embedding

In recent years, many research works propose to embed the network structured data into a low-dimensional feature space, where each node is represented as a feature vector. However, due to the detachment of embedding process with external tasks, the learned embedding results by most existing embedding models can be ineffective for application tasks with specific objectives, e.g., community detection or information diffusion. In this paper, we propose study the application oriented heterogeneous social network embedding problem. Significantly different from the existing works, besides the network structure preservation, the problem should also incorporate the objectives of external applications in the objective function. To resolve the problem, in this paper, we propose a novel network embedding framework, namely the "appLicAtion orienTed neTwork Embedding" (Latte) model. In Latte, the heterogeneous network structure can be applied to compute the node "diffusive proximity" scores, which capture both local and global network structures. Based on these computed scores, Latte learns the network representation feature vectors by extending the autoencoder model model to the heterogeneous network scenario, which can also effectively unite the objectives of network embedding and external application tasks. Extensive experiments have been done on real-world heterogeneous social network datasets, and the experimental results have demonstrated the outstanding performance of Latte in learning the representation vectors for specific application tasks.

cs.SI↗