A transformation from second-price auctions (SPA) to first-price auctions (FPA) has been observed in online advertising. The consequential coexistence of mixed FPA and SPA auction types has further led to the problem of mixed censorship, making bid landscape forecasting, the prerequisite for bid shading, more difficult. Our key insight is that the winning price (WP) under SPA can be effectively transferred to FPA scenarios if they share similar user groups, advertisers, and bidding environments. The full utilization of winning price under mixed censorship can effectively alleviate the FPA censorship problem and improve the performance of winning price prediction (aka. bid landscape forecasting). In this work, we propose a Multi-task Mixed Censorship Predictor (MMCP) that utilizes multi-task learning (MTL) to leverage the WP under SPA as supervised information for FPA. A Double-gate Mixture-of-Experts architecture has been proposed to alleviate the negative transfer problem of multi-task learning in our context. Furthermore, several auxiliary modules including the first-second mapping module and adaptive censorship loss function have been introduced to integrate MTL and winning price prediction. Extensive experiments on two real-world datasets demonstrate the superior performance of the proposed MMCP compared with other state-of-the-art FPA models under various performance metrics. The implementation of the code is available on github (https://github.com/Currycurrycurry/MMCP/).

As a bid optimization algorithm in the first-price auction (FPA), bid shading is used in online advertising to avoid overpaying for advertisers. However, we find the bid shading approach would incur serious local optima. This effect prevents the advertisers from maximizing long-term surplus. In this work, we identify the reasons behind this local optima - it comes from the lack of winning price information, which results in the conflict between short-term surplus and the winning rate prediction model training, and is further propagated through the over-exploitation of the model. To rectify this problem, we propose a cost-effective active learning strategy, namely CeBE, for bid exploration. Specifically, we comprehensively consider the uncertainty and density of samples to calculate exploration utility, and use a 2+ε-approximation greedy algorithm to control exploration costs. Instead of selecting bid prices that maximize the expected surplus for all bid requests, we employ the bid exploration strategy to determine the bid prices. By trading off a portion of surplus, we can train the model using higher-quality data to enhance its performance, enabling the system to achieve a long-term surplus. Our method is straightforward and applicable to real-world industrial environment: it is effective across various categories of winning rate prediction models. We conducted empirical studies to validate the efficacy of our approach. In comparison to the traditional bid shading system, CeBE can yield an average surplus improvement of 8.16% across various models and datasets.

Meta-learning based recommendation systems alleviate the cold-start problem through a bi-level meta-optimization process. Recommendation borrows prior experience from pre-trained static system-level parameters and fine-tunes the model in user-level for new users. However, it is more natural for the system to sample users in a dynamic online sequence in most real-world recommendation systems, which brings further challenges for existing meta-learning based recommendation: system-level updates begins before user-level recommendation models have converged on the whole time series; stable and randomness-resistant bi-level gradient descent approaches are missing in the current meta-learning framework; evaluation on learning abilities across different users are lacked for exploring the diversities of different users.

The exploration/exploitation (E&E) dilemma lies at the core of interactive systems such as online advertising, for which contextual bandit algorithms have been proposed. Bayesian approaches provide guided exploration via uncertainty estimation, but the applicability is often limited due to over-simplified assumptions. Non-Bayesian bootstrap methods, on the other hand, can apply to complex problems by using deep reward models, but lack a clear guidance to the exploration behavior. It still remains largely unsolved to develop a practical method for complex deep contextual bandits.

In recent years, mobile crowdsourcing has emerged as a powerful computation paradigm to harness human power to perform spatial tasks such as collecting real-time traffic information and checking product prices in a specific supermarket. A fundamental problem of mobile crowdsourcing is: When both tasks and crowd workers appear in the platforms dynamically, how to assign an appropriate set of tasks to each worker. Most existing studies focus on efficient assignment algorithms based on bipartite graph matching. However, they overlook an important fact that crowd workers might be unreliable. Thus, their task assignment schemes cannot ensure the overall quality. In this article, we investigate the Quality-aware Online Task Assignment (QAOTA) problem in mobile crowdsourcing. We propose a probabilistic model to measure the quality of tasks and a hitchhiking model to characterize workers’ behavior patterns. We model task assignment as a quality maximization problem and derive a polynomial-time online assignment algorithm. Through rigorous analysis, we prove that the proposed algorithm approximates the offline optimal solution with a competitive ratio of 10/7. Finally, we demonstrate the efficiency and effectiveness of our solution through intensive experiments.

Crowdsourced mobile network access (CMNA), in which mobile users can share their Internet access with others, is a promising paradigm for addressing users' increasing needs for ubiquitous connectivity and alleviating cellular network congestion. In this paper, we study the operator-assisted CMNA model, in which a mobile virtual network operator (MVNO) incentivizes its subscribers to operate as mobile WiFi hotspots (hosts) through reimbursement and gets revenue from the relayed traffic. Despite of the promising performance, practical strategies for MVNO and hosts have not been studied yet. Existing works usually assume both MVNO and hosts can obtain complete information, and ignore the accompanied overhead in backhaul and privacy threats to users. Such assumptions are unrealistic in practice. To address this issue, we first systematically characterize the revenue loss for both MVNO and hosts with incomplete market information. Based on the analysis, we propose a novel partial cooperation strategy (PCS) to enable appropriate information exchange between MVNO and hosts with little overhead. With adaptive reimbursement and subtle information control, our PCS efficiently improves MVNO's revenue at equilibrium, and also satisfies the hosts' rationality. Through extensive evaluation on data from the real world, we demonstrate our PCS can improve MVNO's revenue by 23% at equilibrium, compared with the results without PCS.

Offloading network traffic from cellular to WiFi is widely used to reduce energy consumption since WiFi is assumed to have lower power consumption than cellular. However, we find that WiFi link quality may vary significantly under user mobility. Consequently, the energy efficiency of WiFi varies and sometimes becomes even worse than that of cellular. Therefore, widely used WiFi offloading may not be beneficial or even incurs more energy consumption. To address this issue, we propose Furion, an energy efficient WiFi offloading scheme that exploits beneficial WiFi links on smartphones. Towards such a goal, we investigate the relationship between energy efficiency and link quality. Accordingly, we propose a practical probabilistic model to predict WiFi energy efficiency based on the dynamics of link quality. We further extend the method to different environments by exploiting contextual factors in the prediction model to improve the accuracy. Based on the model, we design an adaptive offloading scheme to optimize the energy efficiency of WiFi offloading, while also guaranteeing user experience. We have implemented Furion on the Android platform and conduct extensive real-world experiments. The results demonstrate that Furion achieves 34.13% improvement in energy efficiency compared with the state-of-the- arts.

Over the past few years we have observed a phenomenal growth of smartphones. Smartphones are equipped with various hardware and software resources such as Bluetooth, camera and gravity sensors. If these resources are not managed appropriately, it may cause severe problems such as battery drains and system crashes. However, the specifications of resource management are usually implicit. In this paper, we investigate the problem of mining resource management specifications from off-the-shelf apps. Our key insight is that if a set of operations to a resource are frequently performed in a specific order, it must contain the specifications of how to manage the resource. We design a tool named Automatic Resource Specification Miner (ARSM), to automatically extract resource management specifications in smartphones. In our experiments, ARSM can mine tens of rules from 100 top rated Android apps within six hours. Our work is orthogonal to existing studies on diagnosing smartphone apps. With the resource management specifications discovered, ARSM can help them pinpoint more bugs in apps.

Driven by the proliferation of mobile applications, the conflict between data communication requirement and limited battery capacity is becoming sharp on modern smartphones. Offloading mobile traffic from cellular to WiFi is widely recognized as a viable solution to improve the energy efficiency. However, through extensive field experiments, we find WiFi offloading is not always energy efficient and even consumes more energy than cellular network due to link quality variation. In addition, we also observe that practical data transmission deadline requirement and link utilization allows scheduling of data traffic to time periods with good link quality. Accordingly, we propose Q-offload, the first attempt towards energy efficient WiFi offloading with link dynamics. In Q-offload, we propose an iterative framework to achieve energy efficient WiFi offloading by exploiting good link quality while not affecting user experience. We evaluate the performance of Q-offload through both trace-driven analysis and real-world experiments. The results show that it can achieve 33.5%~55.7% energy efficiency improvement, compared with state-of-the-arts under different conditions.