Publications

Federated clustering (FC) performs well in independent and identically distributed (IID) scenarios, but it does not perform well in non-IID scenarios. In addition, existing methods lack proof of strict privacy protection. To address the above issues, we propose a new secure federated k-means clustering framework to achieve better clustering results under privacy requirements. Specifically, for the clients, we use cluster centers (representative points) generated by k-means to represent the corresponding clusters. These representative points can effectively preserve the structure of the local data and they are encrypted by differential privacy. For the server, we propose two methods to reprocess the uploaded encrypted representative points to obtain better final cluster centers, one uses k-means, and the other considers the improved density peaks (density cores) as final centers and then sends them back to the clients. Finally, each client assigns local data to their nearest centers. Experimental results show that the proposed methods perform better than several centralized (nonfederated) classical clustering algorithms [k-means, density-based spatial clustering of applications with noise (DBSCAN), and density peak clustering (DPC)] and state-of-the-art (SOTA) centralized clustering algorithms in most cases. In particular, the proposed algorithms perform better than the SOTA FC framework k-FED (ICML2021) and MUFC (ICLR2023).

Thanks to the efficient retrieval speed and low storage consumption, learning to hash has been widely used in visual retrieval tasks. However, existing hashing methods assume that the query and retrieval samples lie in homogeneous feature space within the same domain. As a result, they cannot be directly applied to heterogeneous cross-domain retrieval. In this paper, we propose a Generalized Image Transfer Retrieval (GITR) problem, which encounters two crucial bottlenecks: 1) the query and retrieval samples may come from different domains, leading to an inevitable {domain distribution gap}; 2) the features of the two domains may be heterogeneous or misaligned, bringing up an additional {feature gap}. To address the GITR problem, we propose an Asymmetric Transfer Hashing (ATH) framework with its unsupervised/semi-supervised/supervised realizations. Specifically, ATH characterizes the domain distribution gap by the discrepancy between two asymmetric hash functions, and minimizes the feature gap with the help of a novel adaptive bipartite graph constructed on cross-domain data. By jointly optimizing asymmetric hash functions and the bipartite graph, not only can knowledge transfer be achieved but information loss caused by feature alignment can also be avoided. Meanwhile, to alleviate negative transfer, the intrinsic geometrical structure of single-domain data is preserved by involving a domain affinity graph. Extensive experiments on both single-domain and cross-domain benchmarks under different GITR subtasks indicate the superiority of our ATH method in comparison with the state-of-the-art hashing methods.

This paper presents an unsupervised hierarchical multi-scale segmentation method for multi-phase images based on a single level set, a multi-scale analysis using wavelets, and the semi-implicit additive operator splitting (AOS) scheme which is stable, fast, and easy to implement The method successively segments image subregions found at each step of the hierarchy using a decision criterion based on the variance of intensity across the current subregion. Each step starts with segmenting a down-sized image, and the solution is mapped back to the original size and used as an initial contour for further processing. While there is some overhead related to processing a down-sized image, there is a substantial speedup in processing the full-sized image and selecting the subimage to be segmented.

City governments prioritize mobility in urban planning and policy. Greater mobility in a city leads to happier citizens. Although enhanced urban mobility is helpful, it comes with costs, notably in terms of climate change. Transportation systems that enable urban mobility often emit greenhouse gases. Cities must prioritize digital carbon footprint awareness. Cities may reduce the environmental impact of urban mobility while keeping its benefits by close monitoring and reducing the carbon footprint of digital technologies like transportation applications, ride-sharing platforms, and smart traffic control systems. The aim is to advantage prioritize three alternatives, namely doing nothing, upgrading and optimizing data centers and networks, and using renewable energy sources for data centers and networks to minimize the digital carbon footprint using the proposed decision making tool. This study consists of two stages. In the first stage, fuzzy Aczel-Alsina functions (fuzzy Aczel-Alsina weighted assessment - ALWAS method) based Ordinal Priority Approach (OPA) is proposed to find the weights of criteria. Secondly, fuzzy ALWAS Combined Compromise Solution (CoCoSo) model is improved to evaluate and choose the best alternative among the three alternatives. The improved ALWAS-CoCoSo model enables flexible nonlinear processing of uncertain information and simulation of different risk levels. Besides, we proposed the improved fuzzy OPA algorithm for processing uncertain and incomplete information. The case study is provided to the decision-makers to advantage prioritize the alternatives based on twelve criteria organized into four aspects, including digital carbon footprint, externalities, technical capability, and economics. The ranking results reveal that A3=2.445 is the best among the three alternative, while A1=1.705 is the worst alternative. The results show that the best way to reduce the digital carbon footprint is to use renewable energy sources to power data centers and networks (A3).

Constructing information granules (IGs) has been of significant interest to the discipline of granular computing. The principle of justifiable granularity has been proposed to guide the design of IGs, opening an avenue of pursuits of building IGs carried out on a basis of well-defined and intuitively appealing principles. However, how to improve the efficiency and accuracy of the resulting constructs is an open issue. In this paper, we present a local-density-based optimal granulation model (LoDOG), exhibiting evident advantages: 1) it can detect arbitrarily-shaped IGs and 2) it finds the optimal granulation solutions with O(N) complexity, once the leading tree structure has been constructed. We describe IGs of arbitrary shapes using a small collection of landmark points positioned on the skeleton of the underlying manifold, which contribute to approximate reconstruction capabilities of the original dataset. A dissimilarity metric is developed to evaluate the quality of the obtained reconstruction. The interpretability of LoDOG IGs is discussed. Theoretical analysis and empirical evaluations are covered to demonstrate the effectiveness of LoDOG and the manifold description.