Face clustering is a critical task in computer vision due to the increasing number of applications such as augmented reality or photo album management. The primary challenge in this task arises from the imperfections in image feature representations. Given image features extracted from an existing pre-trained representation model, it remains an unresolved problem that how to leverage the inherent characteristics of similarities among unlabelled images to improve the clustering performance. In order to solve face clustering in an unsupervised manner , we develop an effective and robust framework named as Adapt-Infomap. First, we reformulate face clustering as a process of non-overlapping community detection. Specially, Adapt-Infomap achieves face clustering by minimizing the entropy of information flows (also known as the map equation) on an affinity graph of images. Since the affinity graph of images might contain noisy edges, we develop an outlier detection strategy in Adapt-Infomap to adaptively refine the affinity graph. Experiments with ablation studies demonstrate that Adapt-Infomap significantly outperforms existing methods and achieves new state-of-the-arts on three popular large-scale datasets for face clustering, e.g. , an absolute improvement of more than 10 % and 3 % comparing with prior unsupervised and supervised methods respectively in terms of average of Pairwise F-score.

We consider an increasingly popular demand-response scenario where a home user schedules the flexible electric vehicle (EV) charging load in response to real-time electricity prices. The objective is to minimize the total charging cost with user dissatisfaction taken into account. We focus on the online setting where neither accurate prediction nor distribution of future real-time prices is available to the user when making irrevocable charging decisions in each time slot. The emphasis on considering user dissatisfaction and achieving optimal competitive ratio differentiates our work from existing ones and makes our study uniquely challenging. Our key contribution is two simple online algorithms with the optimal competitive ratio among all deterministic algorithms. The optimal competitive ratio is upper-bounded by$\min \left \{{ \sqrt {\alpha /p_{\min }},p_{\max }/p_{\min }}\right \} $and the bound is asymptotically tight with respect to$\alpha $, where$p_{\max }$and$p_{\min }$are the upper and lower bounds of real-time prices and$\alpha \geq p_{\min }$captures the consideration of user dissatisfaction. The bounds with respect to small and large values of$\alpha $suggest the fundamental difference of the problems with and without considering user dissatisfaction. We also extend the algorithms to take minimum charging requirement and short-term prediction into account. Simulation results based on real-world traces corroborate our theoretical findings and show that the empirical performance of our algorithms can be substantially better than the theoretical worst-case guarantees. Our algorithms also achieve notable performance gains under diverse settings as compared to conceivable alternatives.

We consider an increasingly popular demand-response scenario where a user schedules the flexible electric vehicle (EV) charging load in response to real-time electricity prices. The objective is to minimize the total charging cost with user dissatisfaction taken into account. We focus on the online setting where neither accurate prediction nor distribution of future real-time prices is available to the user when making irrevocable charging decision in each time slot. The emphasis on considering user dissatisfaction and achieving optimal competitive ratio differentiates our work from existing ones and makes our study uniquely challenging. Our key contribution is two simple online algorithms with the best possible competitive ratio among all deterministic algorithms. The optimal competitive ratio is upper-bounded by min {√α/pmin, pmax/pmin} and the bound is asymptotically tight with respect to α, where pmaxand pminare the upper and lower bounds of real-time prices and α ≥ pmincaptures the consideration of user dissatisfaction. The bounds under small and large values of α suggest the fundamental difference of the problems with and without considering user dissatisfaction. Simulation results based on real-world traces corroborate our theoretical findings and show that the empirical performance of our algorithms can be substantially better than its theoretical worst-case guarantee. Moreover, our algorithms achieve large performance gains as compared to conceivable alternatives. The results also suggest that increasing EV charging rate limit decreases overall cost almost linearly.