arXiv subjects

Fengyu Wang

Publications and source records attributed to Fengyu Wang.

24 records · Page 2Linked to original sources

arXiv2023

Scalable Multi-task Semantic Communication System with Feature Importance Ranking

Semantic communications are expected to be an innovative solution to the emerging intelligent applications in the era of connected intelligence. In this paper, a novel scalable multitask semantic communication system with feature importance ranking (SMSC-FIR) is explored. Firstly, the multi-task correlations are investigated by a joint semantic encoder to extract relevant features. Then, a new scalable coding method is proposed based on feature importance ranking, which dynamically adjusts the coding rate and guarantees that important features for semantic tasks are transmitted with higher priority. Simulation results show that SMSC-FIR achieves performance gain w.r.t. individual intelligent tasks, especially in the low SNR regime.

eess.SP↗

arXiv2023

Directed Greybox Fuzzing with Stepwise Constraint Focusing

Dynamic data flow analysis has been widely used to guide greybox fuzzing. However, traditional dynamic data flow analysis tends to go astray in the massive path tracking and requires to process a large volume of data, resulting in low efficiency in reaching the target location. In this paper, we propose a directed greybox fuzzer based on dynamic constraint filtering and focusing (CONFF). First, all path constraints are tracked, and those with high priority are filtered as the next solution targets. Next, focusing on a single path constraint to be satisfied, we obtain its data condition and probe the mapping relationship between it and the input bytes through multi-byte mapping and single-byte mapping. Finally, various mutation strategies are utilized to solve the path constraint currently focused on, and the target location of the program is gradually approached through path selection. The CONFF fuzzer can reach a specific location faster in the target program, thus efficiently triggering the crash. We designed and implemented a prototype of the CONFF fuzzer and evaluated it with the LAVA-1 dataset and some real-world vulnerabilities. The results show that the CONFF fuzzer can reproduce crashes on the LAVA-1 dataset and most of the real-world vulnerabilities. For most vulnerabilities, the CONFF fuzzer reproduced the crashes with significantly reduced time compared to state-of-the-art fuzzers. On average, the CONFF fuzzer was 23.7x faster than the state-of-the-art code coverage-based fuzzer Angora and 27.3x faster than the classical directed greybox fuzzer AFLGo.

cs.CR↗

arXiv2022

Semantic Communication for Internet of Vehicles: A Multi-User Cooperative Approach

Internet of Vehicles (IoV) is expected to become the central infrastructure to provide advanced services to connected vehicles and users for higher transportation efficiency and security. A variety of emerging applications/services bring explosively growing demands for mobile data traffic between connected vehicles and roadside units (RSU), imposing the significant challenge of spectrum scarcity to IoV. In this paper, we propose a cooperative semantic-aware architecture to convey essential semantics from collaborated users to servers for lowering the data traffic. In contrast to current solutions that are mainly based on piling up highly complex signal processing techniques and multiple access capabilities in terms of syntactic communications, this paper puts forth the idea of semantic-aware content delivery in IoV. Specifically, the successful transmission of essential semantics of the source data is pursued, rather than the accurate reception of symbols regardless of its meaning as in conventional syntactic communications. To assess the benefits of the proposed architecture, we provide a case study of the image retrieval task for vehicles in intelligent transportation systems. Simulation results demonstrate that the proposed architecture outperforms the existing solutions with fewer radio resources, especially in a low signal-to-noise-ratio (SNR) regime, which can shed light on the potential of the proposed architecture in extending the applications in extreme environments.

eess.SP↗

arXiv2021

bert2BERT: Towards Reusable Pretrained Language Models

In recent years, researchers tend to pre-train ever-larger language models to explore the upper limit of deep models. However, large language model pre-training costs intensive computational resources and most of the models are trained from scratch without reusing the existing pre-trained models, which is wasteful. In this paper, we propose bert2BERT, which can effectively transfer the knowledge of an existing smaller pre-trained model (e.g., BERT_BASE) to a large model (e.g., BERT_LARGE) through parameter initialization and significantly improve the pre-training efficiency of the large model. Specifically, we extend the previous function-preserving on Transformer-based language model, and further improve it by proposing advanced knowledge for large model's initialization. In addition, a two-stage pre-training method is proposed to further accelerate the training process. We did extensive experiments on representative PLMs (e.g., BERT and GPT) and demonstrate that (1) our method can save a significant amount of training cost compared with baselines including learning from scratch, StackBERT and MSLT; (2) our method is generic and applicable to different types of pre-trained models. In particular, bert2BERT saves about 45% and 47% computational cost of pre-training BERT_BASE and GPT_BASE by reusing the models of almost their half sizes. The source code will be publicly available upon publication.

cs.CL↗

arXiv2021

Automatic Construction of Sememe Knowledge Bases via Dictionaries

A sememe is defined as the minimum semantic unit in linguistics. Sememe knowledge bases (SKBs), which comprise words annotated with sememes, enable sememes to be applied to natural language processing. So far a large body of research has showcased the unique advantages and effectiveness of SKBs in various tasks. However, most languages have no SKBs, and manual construction of SKBs is time-consuming and labor-intensive. To tackle this challenge, we propose a simple and fully automatic method of building an SKB via an existing dictionary. We use this method to build an English SKB and a French SKB, and conduct comprehensive evaluations from both intrinsic and extrinsic perspectives. Experimental results demonstrate that the automatically built English SKB is even superior to HowNet, the most widely used SKB that takes decades to build manually. And both the English and French SKBs can bring obvious performance enhancement in multiple downstream tasks. All the code and data of this paper (except the copyrighted dictionaries) can be obtained at https://github.com/thunlp/DictSKB.

cs.CL↗

arXiv2017

A Tight Configuration-Component Based Hybrid Model for Combined-Cycle Units in MISO Day-Ahead Market

This paper proposes a hybrid CCGT model for day-ahead market clearing, in order to enhance operation flexibility of CCGTs in practice. The proposed hybrid model, by taking benefits of combined offers on configurations and individual PTs from MPs, can reflect physical operation features of CCGTs more accurately. A comprehensive review on CCGT models in literature is conducted, and their advantages and shortcomings are analyzed. The mapping relationship between the two most investigated models, i.e., CFBM and CPBM, is then revealed and constructed for deriving the proposed hybrid model. Tightening formulations are further discussed for achieving better computational performance. The proposed hybrid model is tested and compared with CFBM via an IEEE 118-bus system and the MISO system. Results show great benefits in maintaining operation flexibility and enhancing social welfare.

math.OC↗