arXiv subjects

Jiajie Li

Publications and source records attributed to Jiajie Li.

45 records · Page 3Linked to original sources

arXiv2023

Decentralized Governance for Virtual Community(DeGov4VC): Optimal Policy Design of Human-plant Symbiosis Co-creation

Does the decentralized nature of user behavior in interactive virtual communities help create rules promoting user engagement? Through scenarios like planting, this framework suggests a new paradigm for mutual influence that allows users to impact communities' political decisions. Sixteen participants in the first round of interviews were involved in the framework's creation. Then we developed and implemented our framework in the community with the help of other stakeholders. This proof-of-concept creates user groups using information from users' daily activities as input and grows the green plants in a virtual environment. Finally, we involved AI agents and stakeholders in the framework test and iterations. Our study's user evaluation of a few key stakeholders demonstrates how our strategy enhances user viscosity and experience. Via human-planting ecosystems in a virtual community, this research gives a fresh viewpoint on decentralized governance and an engaging method for co-creating interactive ecological communities.

cs.HC↗

arXiv2023

NPS: A Framework for Accurate Program Sampling Using Graph Neural Network

With the end of Moore's Law, there is a growing demand for rapid architectural innovations in modern processors, such as RISC-V custom extensions, to continue performance scaling. Program sampling is a crucial step in microprocessor design, as it selects representative simulation points for workload simulation. While SimPoint has been the de-facto approach for decades, its limited expressiveness with Basic Block Vector (BBV) requires time-consuming human tuning, often taking months, which impedes fast innovation and agile hardware development. This paper introduces Neural Program Sampling (NPS), a novel framework that learns execution embeddings using dynamic snapshots of a Graph Neural Network. NPS deploys AssemblyNet for embedding generation, leveraging an application's code structures and runtime states. AssemblyNet serves as NPS's graph model and neural architecture, capturing a program's behavior in aspects such as data computation, code path, and data flow. AssemblyNet is trained with a data prefetch task that predicts consecutive memory addresses. In the experiments, NPS outperforms SimPoint by up to 63%, reducing the average error by 38%. Additionally, NPS demonstrates strong robustness with increased accuracy, reducing the expensive accuracy tuning overhead. Furthermore, NPS shows higher accuracy and generality than the state-of-the-art GNN approach in code behavior learning, enabling the generation of high-quality execution embeddings.

cs.AR↗

arXiv2022

Analysis and Optimization of GNN-Based Recommender Systems on Persistent Memory

Graph neural networks (GNNs), which have emerged as an effective method for handling machine learning tasks on graphs, bring a new approach to building recommender systems, where the task of recommendation can be formulated as the link prediction problem on user-item bipartite graphs. Training GNN-based recommender systems (GNNRecSys) on large graphs incurs a large memory footprint, easily exceeding the DRAM capacity on a typical server. Existing solutions resort to distributed subgraph training, which is inefficient due to the high cost of dynamically constructing subgraphs and significant redundancy across subgraphs. The emerging persistent memory technologies provide a significantly larger memory capacity than DRAMs at an affordable cost, making single-machine GNNRecSys training feasible, which eliminates the inefficiencies in distributed training. One major concern of using persistent memory devices for GNNRecSys is their relatively low bandwidth compared with DRAMs. This limitation can be particularly detrimental to achieving high performance for GNNRecSys workloads since their dominant compute kernels are sparse and memory access intensive. To understand whether persistent memory is a good fit for GNNRecSys training, we perform an in-depth characterization of GNNRecSys workloads and a comprehensive analysis of their performance on a persistent memory device, namely, Intel Optane. Based on the analysis, we provide guidance on how to configure Optane for GNNRecSys workloads. Furthermore, we present techniques for large-batch training to fully realize the advantages of single-machine GNNRecSys training. Our experiment results show that with the tuned batch size and optimal system configuration, Optane-based single-machine GNNRecSys training outperforms distributed training by a large margin, especially when handling deep GNN models.

cs.IR↗

arXiv2022

Extensible Proxy for Efficient NAS

Neural Architecture Search (NAS) has become a de facto approach in the recent trend of AutoML to design deep neural networks (DNNs). Efficient or near-zero-cost NAS proxies are further proposed to address the demanding computational issues of NAS, where each candidate architecture network only requires one iteration of backpropagation. The values obtained from the proxies are considered the predictions of architecture performance on downstream tasks. However, two significant drawbacks hinder the extended usage of Efficient NAS proxies. (1) Efficient proxies are not adaptive to various search spaces. (2) Efficient proxies are not extensible to multi-modality downstream tasks. Based on the observations, we design a Extensible proxy (Eproxy) that utilizes self-supervised, few-shot training (i.e., 10 iterations of backpropagation) which yields near-zero costs. The key component that makes Eproxy efficient is an untrainable convolution layer termed barrier layer that add the non-linearities to the optimization spaces so that the Eproxy can discriminate the performance of architectures in the early stage. Furthermore, to make Eproxy adaptive to different downstream tasks/search spaces, we propose a Discrete Proxy Search (DPS) to find the optimized training settings for Eproxy with only handful of benchmarked architectures on the target tasks. Our extensive experiments confirm the effectiveness of both Eproxy and Eproxy+DPS. Code is available at https://github.com/leeyeehoo/GenNAS-Zero.

cs.LG↗

arXiv2018

Greedy and Evolutionary Algorithms for Mining Relationship-Based Access Control Policies

Relationship-based access control (ReBAC) provides a high level of expressiveness and flexibility that promotes security and information sharing. We formulate ReBAC as an object-oriented extension of attribute-based access control (ABAC) in which relationships are expressed using fields that refer to other objects, and path expressions are used to follow chains of relationships between objects. ReBAC policy mining algorithms have potential to significantly reduce the cost of migration from legacy access control systems to ReBAC, by partially automating the development of a ReBAC policy from an existing access control policy and attribute data. This paper presents two algorithms for mining ReBAC policies from access control lists (ACLs) and attribute data represented as an object model: a greedy algorithm guided by heuristics, and a grammar-based evolutionary algorithm. An evaluation of the algorithms on four sample policies and two large case studies demonstrates their effectiveness.

cs.CR↗

arXiv2018

Data Acquisition System for CSNS Neutron Beam Monitor

In Chinese Spallation Neutron Source (CSNS), proton beam is used to hit metal tungsten target, and then high flux neutrons are generated for experiments on instruments. For neutron flux spectrum correction, boron-coated GEM, lithium glass and 3He are used as neutron beam monitor in instruments. To be integrated into neutron instrument control, a new DAQ software for neutron beam monitor is developed, called NEROS (Neutron Event Readout System). NEROS is based on EPICS V4 and a unified data format for CSNS neutron beam monitor is defined. The framework and software design of NEROS is introduced in this paper, including real-time data readout, data processing, data visualization and data storage in Nexus format. The performance is evaluated through offline test, X-ray test and 252Cf test. The deployment of NEROS and its running result in CSNS instrument commissioning are also introduced in this paper.

physics.ins-det↗

arXiv2018

The Proton Beam Real-time Monitor System in CSNS

In Chinese Spallation Neutron Source (CSNS), proton beam is used to hit metal tungsten target, and then high flux neutron are generated for experiments on instruments. For neutron flux spectrum correction, the current of proton beam is for each instrument. A real time monitor system is developed in CSNS, to monitor, broadcast and record each pulse of proton. Each proton pulse charge is measured and marked with high-precision timestamp. Then, the result of measurement will be broadcasted to control room and each neutron instrument. In control room, the proton charge of each pulse is listened and stored in database by agent program for offline use. The high-precision timestamp can be used to proton charge and neutron data alignment in time scale. The architecture of proton beam monitor system is introduced in this paper. And the performance of this system is evaluated in this paper.

physics.ins-det↗

arXiv2018

Backward stochastic differential equations with unbounded generators

In this paper we consider two classes of backward stochastic differential equations. Firstly, under a Lipschitz-type condition on the generator of the equation, which can also be unbounded, we give sufficient conditions for the existence of a unique solution pair. The method of proof is that of Picard iterations and the resulting conditions are new. We also prove a comparison theorem. Secondly, under the linear growth and continuity assumptions on the possibly unbounded generator, we prove the existence of the solution pair. This class of equations is more general than the existing ones.

math.PR↗

arXiv2012

Mean Field Games and Nonlinear Markov Processes

In this paper, we investigate the mean field games with $K$ classes of agents who are weakly coupled via the empirical measure. The underlying dynamics of the representative agents is assumed to be a controlled nonlinear Markov process associated with rather general integro-differential generators of Lévy-Khintchine type (with variable coefficients). We show that nonlinear measure-valued kinetic equations describing the dynamic law of large numbers limit for system with large number N of agents are solvable and that their solutions represent 1/N-Nash equilibria for approximating systems of N agents.

math.PR↗