Active learning alleviates labeling costs by selecting and labeling the most informative examples from an unlabeled pool. However, most existing active learning approaches estimate informativeness with uncalibrated confidence, resulting in unreliable informativeness estimation. These approaches generally ignored two significant issues caused by uncalibrated confidence methods. Firstly, the average uncalibrated confidence generated by modern neural networks is usually higher than the accuracy. Secondly, examples located near the decision boundaries are unstable during prediction when the target model updates parameters in the last several epochs, even throughout the training process. This phenomenon, caused by the forgetting characteristic of neural networks , has a significant impact on some specific models that estimate the informativeness by predicted probability vectors or pseudo labels. To address these issues, in this paper, we propose a novel active learning approach to reliably estimate informativeness with calibrated confidence. Specifically, we integrate the intermediate predictions for each unlabeled example , generated by the target model during the training process, to generate calibrated confidence. The calibrated confidence can capture a tendentious label from an indecisive subset of the class space. We show that the calibrated confidence with tendentiousness can maintain the ability of correct predictions. The empirical results demonstrate that our approach outperforms the state-of-the-art active learning methods on image classification tasks.

Influence maximization, which seeks to find top influential individuals from a social network, has been extensively investigated in recent years. However, previous studies mainly focused on single diffusion or the diffusion of positive and negative messages, in which a competitor dominates the diffusion process. However, in a more realistic scenario, there is a level playing field between similar competitors. To cope with this, we introduce a new Balanced Competitive Influence Maximization (BaCIM) problem which considers the balance in information dissemination. We propose a Balanced Competitive Independent Cascade (BCIC) model to describe how two similar competitive products spread and compete in the same mobile social network. Given the competitor's seeding strategy, BaCIM aims to find a size-k seed set to maximize its own influence spread. We prove that the problem is NP-hard and the objective function is submodular, based on which a greedy algorithm is proposed with (1-1/e-ε) approximation guarantee. To handle large networks, we further propose a Blocked Reverse Influence Sampling algorithm named BRIS, in which we redesign the reverse influence sampling procedure to support the diffusion model. Experimental results on two location-based social networks and several large-scale real datasets validate effectiveness and efficiency of our algorithm.