Hao Su

Dr. Hao Su


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 July 2022 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
JWJi Wan
Ji Wan
KHKai Hu
Kai Hu
JLJie Li
Jie Li
HSHao Su
Hao Su
Blockchain is an innovative application of distributed storage, consensus algorithm, encryption algorithm, and other computer technologies. The consensus algorithm is the key to keep consistent among blockchain nodes. In most existing consensus algorithms, the leader node is responsible for proposing new block and communicating with other nodes. The leader node is easy to be the target of malicious attackers. With the increase of the number of nodes, the throughput and scalability of the blockchain system are also unsatisfactory. To address such issues, we propose the AnonymousFox consensus algorithm, which is suitable for the consortium blockchain and private blockchain. First, we design an anonymous leader node sorting algorithm, which hides the identity of the leader node through a variety of encryption algorithms. It periodically changes the ordered leader list to hide the target of malicious attackers. In addition, we design a consensus algorithm based on the anonymous identity of the leader node. Through one-to-many message communication, the amount of messages is greatly reduced. The complexity of the algorithm is $O(n)$ . It solves the problem of ordered replication of state machines when the leader node is anonymous. We analyze the algorithm, it ensures safety and liveness when the fault nodes are less than one-third of the total. We evaluate the throughput, latency, scalability, resource consumption, exception processing, smart contract, and blockchain network through experiments. The throughput of the proposed algorithm is 49.3% higher than that of the practical Byzantine fault tolerance (PBFT) algorithm. The experimental results show that the proposed algorithm has high performance and scalability.

28 October 2024
Verified
Conference Paper
Open access
XWXinghao Wu
Xinghao Wu
XLXuefeng Liu
Xuefeng Liu
Jianwei NiuJianwei Niu
Jianwei Niu
HWHaolin Wang
Haolin Wang
STShaojie Tang
Shaojie Tang
HSHao Su
Hao Su
To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on collaboration if not removed. Existing PFL methods primarily adopt a parameter partitioning approach, where the parameters of a model are designated as one of two types: parameters shared with other clients to extract general knowledge and parameters retained locally to learn client-specific knowledge. However, as these two types of parameters are put together like a jigsaw puzzle into a single model during the training process, each parameter may simultaneously absorb both general and client-specific knowledge, thus struggling to separate the two types of knowledge effectively. In this paper, we introduce FedDecomp, a simple but effective PFL paradigm that employs parameter additive decomposition to address this issue. Instead of assigning each parameter of a model as either a shared or personalized one, FedDecomp decomposes each parameter into the sum of two parameters: a shared one and a personalized one, thus achieving a more thorough decoupling of shared and personalized knowledge compared to the parameter partitioning method. In addition, as we find that retaining local knowledge of specific clients requires much lower model capacity compared with general knowledge across all clients, we let the matrix containing personalized parameters be low rank during the training process. Moreover, a new alternating training strategy is proposed to further improve the performance. Experimental results across multiple datasets and varying degrees of data heterogeneity demonstrate that FedDecomp outperforms state-of-the-art methods up to 4.9%. The code is available at https://github.com/XinghaoWu/FedDecomp

29 August 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
HSHao Su
Hao Su
XLXuefeng Liu
Xuefeng Liu
Jianwei NiuJianwei Niu
Jianwei Niu
JCJiahe Cui
Jiahe Cui
JWJi Wan
Ji Wan
NWNana Wang
Nana Wang
Manga is a fashionable Japanese-style comic form that is composed of black-and-white strokes and is generally displayed as raster images on digital devices. Typical mangas have simple textures, wide lines, and few color gradients, which are vectorizable natures to enjoy the merits of vector graphics, e.g., adaptive resolutions and small file sizes. In this paper, we propose MARVEL (MAnga’s Raster to VEctor Learning), a primitive-wise approach for vectorizing raster gray-level mangas by Deep Reinforcement Learning (DRL). Unlike previous learning-based methods which predict vector parameters for an entire image, MARVEL introduces a new perspective that regards an entire manga as a collection of basic primitives—stroke lines, and designs a DRL model to decompose the target image into a primitive sequence for achieving accurate vectorization. To improve vectorization accuracies and decrease file sizes, we further propose a stroke accuracy reward to predict accurate stroke lines, and a pruning mechanism to avoid generating erroneous and repeated strokes. Extensive subjective and objective experiments show that our MARVEL can generate impressive results and reaches the state-of-the-art level.

25 April 2024 in Journal of Network and Computer Applications
Verified
Journal Article
Closed access
HSHao Su
Hao Su
Jianwei NiuJianwei Niu
Jianwei Niu
XLXuefeng Liu
Xuefeng Liu
MAMohammed Atiquzzaman
Mohammed Atiquzzaman

6 August 2025 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
HSHao Su
Hao Su
XWXuxi Wang
Xuxi Wang
Jianwei NiuJianwei Niu
Jianwei Niu
XLXuefeng Liu
Xuefeng Liu
XWXinghao Wu
Xinghao Wu
NWNana Wang
Nana Wang
We propose 3DFaceSculptor, a general-purpose framework for interactive 3D face editing. Given a source 3D face mesh with semantic materials, and a user-specified semantic image, 3DFaceSculptor can accurately edit the source mesh following the shape guidance of the semantic image, while preserving the source topology as rigid as possible. Recent studies on generating 3D faces focus on learning neural networks to predict 3D shapes, which requires high-cost 3D training datasets. These learning-based methods are limited in compatibility and can only handle face styles involved in the training datasets. Unlike these methods, our 3DFaceSculptor is a non-training and common framework, which only requires supervision from readily-available semantic images, and is compatible with producing various face styles unlimited by datasets. In 3DFaceSculptor, based on the differentiable renderer technique, we deform the source face mesh according to the correspondences between semantic images and mesh materials. However, guiding complex 3D shapes with a simple 2D image incurs extra challenges, that is, the deformation accuracy, surface smoothness, geometric rigidity, and global synchronization of the edited mesh must be guaranteed. To address these challenges, we propose a hierarchical optimization architecture to balance the global and local shape features, and further propose various strategies and losses to improve properties of accuracy, smoothness, rigidity, and so on. Extensive experiments show that our 3DFaceSculptor is able to produce impressive results and has reached the state-of-the-art level.