Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleOctober 2024
Social network group decision-making method based on stochastic multi-criteria acceptability analysis for probabilistic linguistic term sets
Information Sciences: an International Journal (ISCI), Volume 681, Issue Chttps://doi.org/10.1016/j.ins.2024.121269AbstractIn social network group decision-making (SNGDM) problems, decision-makers (DMs) often express their opinions or preferences using probabilistic linguistic term sets (PLTSs). In this paper, a novel SNGDM method for probabilistic linguistic ...
- research-articleOctober 2024
Federating from History in Streaming Federated Learning
MOBIHOC '24: Proceedings of the Twenty-fifth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile ComputingPages 151–160https://doi.org/10.1145/3641512.3686375To address the online learning problem in distributed systems, Streaming Federated learning (SFL) enables immediate model training by clients upon collecting new data, finding wide applications in AI-enabled Internet-of-Things and sensor networks. Given ...
- ArticleAugust 2024
ACD: Attention Driven Cognitive Diagnosis for New Learners Joining ITS
AbstractIn Intelligent Tutor Systems (ITS), Cognitive Diagnosis (CD) is an important and fundamental problem, which aims to discover learners’ proficiency in different knowledge concepts. However, existing CD models (CDMs) that are from the perspective of ...
- research-articleAugust 2024
- research-articleSeptember 2024
Systolic Array Acceleration of Spiking Neural Networks with Application-Independent Split-Time Temporal Coding
ISLPED '24: Proceedings of the 29th ACM/IEEE International Symposium on Low Power Electronics and DesignPages 1–6https://doi.org/10.1145/3665314.3672292Spiking Neural Networks (SNNs) are brain-inspired computing models with event-driven based low-power operations and unique temporal dynamics. However, temporal dynamics in SNNs pose a significant overhead in accelerating neural computations and limit the ...
-
- ArticleAugust 2024
Network Traffic Intrusion Detection Strategy Based on E-GraphSAGE and LSTM
Advanced Intelligent Computing Technology and ApplicationsPages 25–37https://doi.org/10.1007/978-981-97-5606-3_3AbstractThe exponential growth of the internet, alongside rapid advancements in information technology, has ushered in an era where network security is critical. As malicious actors employ increasingly complex attack strategies, traditional intrusion ...
- research-articleAugust 2024
Feature-aware transferable adversarial attacks against image classification
AbstractCompared to white-box adversarial attacks, black-box adversarial attacks are more applicable in practical scenarios and have received significant attention. However, most existing black-box attacks are optimized at the output layer, and the ...
Highlights- An attack framework based on a feature-aware triplet is proposed.
- Achieve a better tradeoff between attack capability and transferability.
- A weighted average method for constructing a feature library is designed.
- Define more ...
- research-articleJuly 2024
M4SFWD: A Multi-Faceted synthetic dataset for remote sensing forest wildfires detection
Expert Systems with Applications: An International Journal (EXWA), Volume 248, Issue Chttps://doi.org/10.1016/j.eswa.2024.123489AbstractForest wildfires are one of the most catastrophic natural disasters, which poses a severe threat to both the ecosystem and human life. Therefore, it is imperative to implement technology to prevent and control forest wildfires. The combination of ...
- research-articleJuly 2024
Autonomous driving policy learning from demonstration using regression loss function
AbstractHow to efficiently train a high-performance autonomous driving agent remains a realistic and challenging issue. Although in the literature, many techniques, especially deep reinforcement learning (DRL) methods, have been developed, they are ...
Highlights- A novel pre-training DRL algorithm simplifies the pre-training phase.
- The algorithm reduces the format requirements on the demonstration data.
- The algorithm simplifies the dominance term.
- A novel priority formula fulfills ...
- research-articleJuly 2024
Load forecasting model considering dynamic coupling relationships using structured dynamic-inner latent variables and broad learning system
Engineering Applications of Artificial Intelligence (EAAI), Volume 133, Issue PBhttps://doi.org/10.1016/j.engappai.2024.108180AbstractIntegrated energy systems (IES) can effectively regulate and optimize dynamic loads by utilizing load forecasting, which intelligently manages energy scheduling. Nevertheless, the insufficient attention given by existing research to loads with ...
- research-articleJuly 2024
Improved well-balanced AWENO schemes with hydrostatic reconstruction for the Euler equations under gravitational fields
Mathematics and Computers in Simulation (MCSC), Volume 221, Issue CPages 260–280https://doi.org/10.1016/j.matcom.2024.03.007AbstractThe Euler equations under gravitational fields allow the hydrostatic equilibrium states, which requires that the numerical scheme of the system should also have this characteristic. In our previous work, a well-balanced finite difference ...
- research-articleJuly 2024
An enhanced structural developmental neural network with information saturation for continual unsupervised learning
AbstractIn this paper, an enhanced structural developmental neural network with information saturation (ESDNNIS) is proposed for continual unsupervised learning. It improves SDNNIS in the following respects: (1) it makes a distinction between the ...
- research-articleMay 2024
Table-GPT: Table Fine-tuned GPT for Diverse Table Tasks
- Peng Li,
- Yeye He,
- Dror Yashar,
- Weiwei Cui,
- Song Ge,
- Haidong Zhang,
- Danielle Rifinski Fainman,
- Dongmei Zhang,
- Surajit Chaudhuri
Proceedings of the ACM on Management of Data (PACMMOD), Volume 2, Issue 3Article No.: 176, Pages 1–28https://doi.org/10.1145/3654979Language models, such as GPT-3 and ChatGPT, demonstrate remarkable abilities to follow diverse human instructions and perform a wide range of tasks, using instruction fine-tuning. However, when we test language models with a range of basic table-...
- research-articleJuly 2024
Semantic Collaboration: A Collaborative Approach for Multi-Agent Systems Based on Semantic Communication
CNIOT '24: Proceedings of the 2024 5th International Conference on Computing, Networks and Internet of ThingsPages 123–132https://doi.org/10.1145/3670105.3670127Abstract. In order to meet the practical needs of different intelligent agents collaborating to execute tasks, this paper has studied the multi-agent collaboration mode based on semantic communication and proposed a multi-agent collaboration method based ...
- articleMay 2024
Auto-Tables: Relationalize Tables without Using Examples
Relational tables, where each row corresponds to an entity and each column corresponds to an attribute, have been the standard for tables in relational databases. However, such a standard cannot be taken for granted when dealing with tables "in the wild"...
- research-articleMay 2024
Differentially private federated learning with non-IID data
AbstractIn Differentially Private Federated Learning (DPFL), gradient clipping and random noise addition disproportionately affect statistically heterogeneous data. As a consequence, DPFL has a disparate impact: the accuracy of models trained with DPFL ...
- research-articleMay 2024
Optimal Flash Loan Fee Function with Respect to Leverage Strategies
AAMAS '24: Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent SystemsPages 1874–1882We investigate two decentralized methods for leveraging assets: Firstly, investors recurrently commit their target assets as collateral to secure loans, subsequently reinvesting the borrowed funds in the same assets. Secondly, investors pledge their ...
- research-articleApril 2024
Two novel models with nuclear norm for robust matrix recovery
AbstractIn this paper, we investigate the low-rank matrix recovery problem from linear observations. Inspired by the matrix Lasso and Dantzig selector, we propose nuclear norm regularized models with two data fitting items: ℓ 2-loss function and Dantzig ...
Highlights- Stable recovery errors for nuclear norm regularized models are established.
- Efficient algorithm based on PSS method for low-rank matrix recovery is proposed.
- Our method achieves good recovery performance in numerical experiments.
- research-articleMay 2024
Broadly Enabling KLEE to Effortlessly Find Unrecoverable Errors in Rust
ICSE-SEIP '24: Proceedings of the 46th International Conference on Software Engineering: Software Engineering in PracticePages 441–451https://doi.org/10.1145/3639477.3639714Rust is a general-purpose programming language designed for performance and safety. Unrecoverable errors (e.g., Divide by Zero) in Rust programs are critical, as they signal bad program states and terminate programs abruptly. Previous work has ...
- research-articleApril 2024