Federated domain generalization (FDG) for time-series classification (TSC) poses a critical challenge for modern intelligent web services, which rely on edge-collected time-series signals from diverse mobile applications and web devices (e.g., wearables sensors) to support decision-making. The source heterogeneity and temporal dynamics give rise to out-of-distribution (OOD) patterns, which hinder the model's ability to generalize to previously unseen users and devices. In this work, we propose Federated Generalization via Diversity Generation (FedDiG), a diffusion-based FDG framework that captures intra-client distribution shifts from a frequency-domain perspective and employs cross-frequency sampling to synthesize time-series data with diverse spectral patterns. Specifically, FedDiG first performs frequency-proxy representation learning on clients to serve as diffusion conditions. The server then aggregates client-side frequency proxies to construct a global proxy pool and applies class-wise mixup to create novel frequency features. These features guide a global diffusion model to produce diverse data, enabling the simulation of previously unseen patterns and thereby enhancing model training. Extensive experiments on four cross-domain time-series benchmarks demonstrate that FedDiG significantly outperforms state-of-the-art federated learning and FDG baselines, particularly under small-data regimes and large-scale client scenarios, achieving robust generalization to unseen domains in federated settings. This work bridges distribution-diversity synthesis and FDG for time-series to support robust, scalable web applications fed by edge-collected signals, delivering web-scale generalization across heterogeneous web, mobile, and IoT clients.

As neural network models grow larger and more complex, federated learning (FL) faces challenges in terms of communication and computation efficiency. To address these issues, layer-wise learning has been proposed. Existing approaches did not leverage useful properties of layer-wise learning including update locking and variations in convergence rates, thereby resulting in sub-par model performance. To bridge this gap, we propose theFederatedMeanBlockDifference-based global model aggregation approach withPatience-based local training (FedMBDP). We automatically partition the neural network model into uncoupled blocks and progressively train them. Determining which blocks to train and aggregate becomes a critical task. To improve computation efficiency, we propose a patience-based local training algorithm to adaptively select training blocks, reducing computation latency. To improve communication efficiency, we introduce a mean block difference-based global model aggregation algorithm to dynamically select blocks for aggregation to minimize communication latency. We provide the convergence analysis of FedMBDP. Extensive experiments on three widely adopted benchmark datasets show that FedMBDP achieves superior performance compared to six state-of-the-art approaches. It reduces FL training latency by 26.37% compared to the best baseline, while achieving similar test accuracy.

Auction-based Federated Learning (AFL) has gained significant research interest due to its ability to incentivize data owners (DOs) to participate in FL model training tasks of data consumers (DCs) through economic mechanisms via the auctioneer. One of the critical research issues in AFL is decision support for the auctioneer. Existing approaches are based on the simplified assumption of a single, monopolistic AFL marketplace, which is unrealistic in real-world scenarios where multiple AFL marketplaces can co-exist and compete for the same pool of DOs. In this paper, we relax this assumption and frame the AFL auctioneer decision support problem from the perspective of helping them attract participants in a competitive AFL marketplace environment while safeguarding profit. To achieve this objective, we propose the Auctioneer Revenue Allocation Strategy for AFL (ARAS-AFL). We design the concepts of the attractiveness and competitiveness from the perspective of autioneer reputation. Based on the Lyapunov optimization, ARAS-AFL helps individual AFL auctioneer achieve the dual objective of balancing the reputation management costs and its own profit by designing a dynamic revenue allocation strategy. It takes into account both the auctioneer’s revenue and the changes in the number of participants on the AFL marketplace. Through extensive experiments on widely used benchmark datasets, ARAS-AFL demonstrates superior performance compared to state-of-the-art approaches. It outperforms the best baseline by 49.06%, 98.69%, 10.32%, and 4.77% in terms of total revenue, number of data owners, public reputation and accuracy of federated learning models, respectively.

The increasing sophistication of text-to-image generative models raises challenges in defining and enforcing copyright criteria. Existing methods like watermarking and dataset deduplication fall short due to the lack of standardized metrics and the complexity of addressing copyright issues in diffusion models. To tackle these challenges, we propose RLCP, a Reinforcement Learning-based Copyright Protection method for Text-to-Image Diffusion Models. Our approach introduces a novel copyright metric grounded in legal precedents and employs the Denoising Diffusion Policy Optimization (DDPO) framework to minimize copyright-infringing content while preserving image quality. A reward function based on our metric and KL divergence regularization ensures stable fine-tuning. Experiments on mixed datasets of copyright and non-copyright images show that RLCP effectively reduces copyright infringement risk without compromising output quality.

Auction-based Federated Learning (AFL) has emerged as an important research field in recent years. The prevailing strategies for FL data consumers (DCs) assume that the entire team of the required data owners (DOs) for an FL task must be assembled before training can commence. In practice, a DC can trigger the FL training process multiple times. DOs can thus be gradually recruited over multiple FL model training sessions. Existing bidding strategies for AFL DCs are not designed to handle such scenarios. Therefore, the problem of multi-session AFL remains open. To address this problem, we propose the Multi-session Budget Optimization Strategy for forward Auction-based Federated Learning (MBOS-AFL). Based on hierarchical reinforcement learning, MBOS-AFL jointly optimizes intersession budget pacing and intra-session bidding for AFL DCs, with the objective of maximizing the total utility. Extensive experiments on six benchmark datasets show that it significantly outperforms seven state-of-the-art approaches. On average, MBOS-AFL achieves 12.28% higher utility, 14.52% more data acquired through auctions for a given budget, and 1.23% higher test accuracy achieved by the resulting FL model compared to the best baseline. To the best of our knowledge, it is the first budget optimization decision support method with budget pacing capability designed for DCs in multi-session forward AFL.

Federated Active Learning (FAL) aims to learn an effective global model, while minimizing label queries. Owing to privacy requirements, it is challenging to design effective active data selection schemes due to the lack of cross-client query information. In this paper, we bridge this important gap by proposing the Federated Active data selection by LEverage score sampling (FALE) method. It is designed for regression tasks in the presence of non-i.i.d. client data to enable the server to select data globally in a privacy-preserving manner. Based on FedSVD, FALE aims to estimate the utility of unlabeled data and perform data selection via leverage score sampling. Besides, a secure model learning framework is designed for federated regression tasks to exploit supervision. FALE can operate without requiring an initial labeled set and select the instances in a single pass, significantly reducing communication overhead. Theoretical analyze establishes the query complexity for FALE to achieve constant factor approximation and relative error approximation. Extensive experiments on 11 benchmark datasets demonstrate significant improvements of FALE over existing state-of-the-art methods.

Auction-based Federated Learning (AFL) fosters collaboration among self-interested data consumers (DCs) and data owners (DOs). A major challenge in AFL pertains to how DCs select and bid for DOs. Existing methods are generally static, making them ill-suited for dynamic AFL markets. To address this issue, we propose the R}einforcement Learning-based Bidding Strategy for DCs in Auction-based Federated Learning (RLB-AFL). We incorporate historical states into a Deep Q-Network to capture sequential information critical for bidding decisions. To mitigate state space sparsity, where specific states rarely reoccur for each DC during auctions, we incorporate the Gaussian Mixture Model into RLB-AFL. This facilitates soft clustering on sequential states, reducing the state space dimensionality and easing exploration and action-value function approximation. In addition, we enhance the $\epsilon$-greedy policy to help the RLB-AFL agent balance exploitation and exploration, enabling it to be more adaptable in the AFL decision-making process. Extensive experiments under 6 widely used benchmark datasets demonstrate that RLB-AFL achieves superior performance compared to 8 state-of-the-art approaches. It outperforms the best baseline by 10.56% and 3.15% in terms of average total utility

Auction-based federated learning (AFL) has garnered significant research attention recently. However, existing methods for AFL data consumers (DCs) primarily focus on improving FL model performance by recruiting data owners (DOs) with high reputations and low ask prices, disregarding fair treatment for DOs. The challenge of striking a balance between performance and fairness when recruiting DOs remains unaddressed. To tackle this issue, we propose the Fairness-aware Reverse AFL for DCs (FAR-AFL).FAR-AFLleverages Lyapunov optimization to dynamically adjust selection probabilities for potential DOs, taking into account dynamic changes in participation rates and reputation.FAR-AFLadopts a reverse auction-based DO recruitment mechanism to determine candidate selection and pricing. By combining these components,FAR-AFLimproves FL model accuracy while minimizing overall recruitment costs. Crucially,FAR-AFLensures equitable DO treatment, providing them with fair participation opportunities. Theoretical analysis shows the computational efficiency, individual rationality, and truthfulness ofFAR-AFL. Extensive experimental evaluation against six alternative strategies on four benchmark datasets demonstrates thatFAR-AFLoutperforms the best alternative strategy by 1.99%, 6.60%, 1.97%, and 23.31% in terms of test accuracy, root mean square error, cost reduction, and fairness improvement, respectively.

Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of federated learning. This combination allows the large foundation models and the small local domain models at the remote clients to learn from each other in a teacher-student learning setting. This paper provides a comprehensive summary of the ten challenging problems inherent in FedFMs, encompassing foundational theory, utilization of private data, continual learning, unlearning, Non-IID and graph data, bidirectional knowledge transfer, incentive mechanism design, game mechanism design, model watermarking, and efficiency. The ten challenging problems manifest in five pivotal aspects: “Foundational Theory,” which aims to establish a coherent and unifying theoretical framework for FedFMs. “Data,” addressing the difficulties in leveraging domain-specific knowledge from private data while maintaining privacy; “Heterogeneity,” examining variations in data, model, and computational resources across clients; “Security and Privacy,” focusing on defenses against malicious attacks and model theft; and “Efficiency,” highlighting the need for improvements in training, communication, and parameter efficiency. For each problem, we offer a clear mathematical definition on the objective function, analyze existing methods, and discuss the key challenges and potential solutions. This in-depth exploration aims to advance the theoretical foundations of FedFMs, guide practical implementations, and inspire future research to overcome these obstacles, thereby enabling the robust, efficient, and privacy-preserving FedFMs in various real-world applications.

Auction-based federated learning (AFL) has emerged as an efficient and fair approach to incentivize data owners (DOs) to contribute to federated model training, garnering extensive interest. However, the important problem of helping data consumers (DCs) bid for DOs in competitive AFL settings remains open. Existing work simply treats that the actual cost paid by a winning DC (i.e., the bid cost) is equal to the bid price offered by that DC itself. However, this assumption is inconsistent with the widely adopted generalized second-price (GSP) auction mechanism used in AFL, including in these existing works. Under a GSP auction, the winning DC does not pay its own proposed bid price. Instead, the bid cost for the winner is determined by the second-highest bid price among all participating DCs. To address this limitation, we propose a first-of-its-kind federated cost-aware bidding strategy (FedCA-Bidder) to help DCs maximize their utility under GSP auction-based federated learning (FL). It enables DCs to efficiently bid for DOs in competitive AFL markets, maximizing their utility and improving the resulting FL model accuracy. We first formulate the optimal bidding function under the GSP auction setting, and then demonstrate that it depends on utility estimation and market price modeling, which are interrelated. Based on this analysis, FedCA-Bidder jointly optimizes in a novel end-to-end framework, and then executes the proposed return on investment (ROI)-based method to determine the optimal bid price for each piece of the data resource. Through extensive experiments on six commonly adopted benchmark datasets, we show that FedCA-Bidder outperforms eight state-of-the-art methods, beating the best baseline by 4.39%, 4.56%, 1.33%, and 5.43% on average in terms of the total amount of data obtained, number of data samples per unit cost, total utility, and FL model accuracy, respectively.

Social insurance benefits qualification assessment is an important task to ensure that retirees enjoy their benefits according to the regulations. It also plays a key role in curbing social security frauds. In this paper, we report the deployment of the Intelligent Benefit Certification and Analysis (IBCA) platform, an AI-empowered platform for verifying the status of retirees to ensure proper dispursement of funds in Shandong province, China. Based on an improved Gated Recurrent Unit (GRU) neural network, IBCA aggregates missing value interpolation, temporal information, and global and local feature extraction to perform accurate retiree survival rate prediction. Based on the predicted results, a reliability assessment mechanism based on Variational Auto-Encoder (VAE) and Monte-Carlo Dropout (MC Dropout) is executed to perform reliability assessment. Deployed since November 2019, the IBCA platform has been adopted by 12 cities across the Shandong province, handling over 50 terabytes of data. It has empowered human resources and social services, civil affairs, and health care institutions to collaboratively provide high-quality public services. Under the IBCA platform, the efficiency of resources utilization as well as the accuracy of benefit qualification assessment have been significantly improved. It has helped Dareway Software Co. Ltd earn over RMB 50 million of revenue.

Gas usage estimation plays a critical role in various aspects of the power generation and delivery business, including budgeting, resource planning, and environmental preservation. Federated Learning (FL) has demonstrated its potential in enhancing the accuracy and reliability of gas usage estimation by enabling distributedly owned data to be leveraged, while ensuring privacy and confidentiality. However, to effectively motivate stakeholders to contribute their high-quality local data and computational resources for this purpose, incentive mechanism design is key. In this paper, we report our experience designing and deploying the Hierarchical FL Incentive mechanism for Gas usage estimation (HiFi-Gas) system. It is designed to cater to the unique structure of gas companies and their affiliated heating stations. HiFi-Gas provides effective incentivization in a hierarchical federated learning framework that consists of a horizontal federated learning (HFL) component for effective collaboration among gas companies and multiple vertical federated learning (VFL) components for the gas company and its affiliated heating stations. To motivate active participation and ensure fairness among gas companies and heating stations, we incorporate a multi-dimensional contribution-aware reward distribution function that considers both data quality and model contributions. Since its deployment in the ENN Group in December 2022, HiFi-Gas has successfully provided incentives for gas companies and heating stations to actively participate in FL training, resulting in more than 12% higher average gas usage estimation accuracy and substantial gas procurement cost savings. This implementation marks the first successful deployment of a hierarchical FL incentive approach in the energy industry.

Recent years have witnessed a growing interest in Federated Knowledge Graph Embedding, driven by its potential to leverage knowledge from various data owners to improve link prediction performance without the need for data sharing. Existing works typically assume that the central Federated Learning (FL) server owns a table containing unique entities/relations for all FL clients. In addition, all clients are assumed to use the same knowledge graph embedding method. However, these methods are vulnerable to privacy leakage and do not fully explore the different contributions of local entity embeddings. To bridge this gap, we propose a randomized embedding method selection approach for privacy-preserving federated knowledge graph embedding (FedRMS). It selects a knowledge graph embedding method for each client during the local training process with randomness and employs an attention-based aggregator to derive the global entity embedding on the FL server. Extensive experiments on three real-world public datasets demonstrate that FedRMS achieves significant improvements in terms of both privacy preservation and link prediction against 5 state-of-the-art methods.

Auction-based Federated Learning (AFL) has attracted extensive research interest due to its ability to motivate data owners (DOs) to join FL through economic means. While many existing AFL methods focus on providing decision support to model tusers (MUs) and the AFL auctioneer, decision support for data owners remains open. To bridge this gap, we propose a first-of-its-kind agent-oriented joint Pricing, Acceptance and Sub-delegation decision support approach for data owners in AFL (PAS-AFL). By considering a DO’s current reputation, pending FL tasks, willingness to train FL models, and its trust relationships with other DOs, it provides a systematic approach for a DO to make joint decisions on AFL bid acceptance, task sub-delegation and pricing based on Lyapunov optimization to maximize its utility. It is the first to enable each DO to take on multiple FL tasks simultaneously to earn higher income for DOs and enhance the throughput of FL tasks in the AFL ecosystem. Extensive experiments based on six benchmarking datasets demonstrate significant advantages of PAS-AFL compared to six alternative strategies, beating the best baseline by 28.77% and 2.64% on average in terms of utility and test accuracy of the resulting FL models, respectively.

Federated learning (FL) enables collaborative machine learning across distributed data owners, but data heterogeneity poses a challenge for model calibration. While prior work focused on improving accuracy for non-iid data, calibration remains under-explored. This study reveals existing FL aggregation approaches lead to sub-optimal calibration, and theoretical analysis shows despite constraining variance in clients’ label distributions, global calibration error is still asymptotically lower bounded. To address this, we propose a novel Federated Calibration (FedCal) approach, emphasizing both local and global calibration. It leverages client-specific scalers for local calibration to effectively correct output misalignment without sacrificing prediction accuracy. These scalers are then aggregated via weight averaging to generate a global scaler, minimizing the global calibration error. Extensive experiments demonstrate that FedCal significantly outperforms the best-performing baseline, reducing global calibration error by 47.66% on average.

Knowledge Graph Embedding (KGE) is attracting growing research interest because it offers great flexibility for the manipulation and application of Knowledge Graphs (KGs). However, most existing works focus on static KGE, while temporal KGE is still in its infancy. Recent temporal KGE methods attempt to obtain the long-term dependency of facts in consecutive timestamps by merging historical fact information. However, they ignore the different impacts of historical facts on the current facts due to the time decay effect and heterogeneity of historical facts. To bridge this gap, we formalize the concept of fact formation sequence to describe the evolution of an entity and propose the Modeling Time Decay Effect in Temporal Knowledge Graphs via Multivariate Hawkes Process method (TimeDE). TimeDE uses the Hawkes process to model the time decay effect of historical facts. It also incorporates the attention mechanism based on the score function of static KGE methods to better capture the impacts of heterogeneous historical facts on the current facts. Extensive experiments on the five commonly-used benchmark datasets demonstrate that TimeDE achieves significant improvements in terms of both Mean Reciprocal Rank and Hits@K compared to state-of-the-art methods.

Auction-based Federated Learning (AFL) has become a significant focus in recent years. Existing approaches for model users (MUs) in FL generally operate under the assumption that the entire set of essential data owners (DOs) must be gathered before the training process initiates. However, in practical scenarios, the MU can initiate the FL training process multiple times, gradually recruiting DOs across multiple FL training sessions. Current AFL methods are not equipped to handle such situations. The challenge of optimizing the AFL budget across multiple sessions and objectives remains unresolved. To address this gap, we propose the Efficient and Utility Return-Optimizing budget management strategy for MUs in Auction-based Federated Learning (EURO-AFL). By incorporating the hierarchical reinforcement learning framework, EURO-AFL concurrently optimizes inter-session budget pacing and intra-session budget allocation, with the dual objective of maximizing total utility while minimizing waiting time. Extensive experiments conducted on four real-world datasets illustrate the substantial advantages of EURO-AFL compared to five state-of-the-art baselines. It outperforms the best-performing baseline by 6.26%, 47.9% and 17.6% in terms of model accuracy, number of training sessions sustained, and training efficiency, respectively. To our best knowledge, EURO-AFL is the first multi-session multi-objective budget optimization approach designed for AFL MUs.

Federated learning (FL) is a machine learning paradigm that allows multiple FL participants (FL-PTs) to collaborate on training models without sharing private data. Due to data heterogeneity, negative transfer may occur in the FL training process. This necessitates FL-PT selection based on their data complementarity. In cross-silo FL, organizations that engage in business activities are key sources of FL-PTs. The resulting FL ecosystem has two features: (i) self-interest, and (ii) competition among FL-PTs. This requires the desirable FL-PT selection strategy to simultaneously mitigate the problems of free riders and conflicts of interest among competitors. To this end, we propose an optimal FL collaboration formation strategy -FedEgoists- which ensures that: (1) a FL-PT can benefit from FL if and only if it benefits the FL ecosystem, and (2) a FL-PT will not contribute to its competitors or their supporters. It provides an efficient clustering solution to group FL-PTs into coalitions, ensuring that within each coalition, FL-PTs share the same interest. We theoretically prove that the FL-PT coalitions formed are optimal since no coalitions can collaborate together to improve the utility of any of their members. Extensive experiments on widely adopted benchmark datasets demonstrate the effectiveness of FedEgoists compared to nine state-of-the-art baseline methods, and its ability to establish efficient collaborative networks in cross-silos FL with FL-PTs that engage in business activities.

Auction-based Federated Learning (AFL) enables open collaboration among self-interested model users (MUs) and data owners (DOs). Muti-agent reinforcement learning-based bidding methods have gained traction in AFL due to their ability to deal with complex interactions among MUs and DOs. However, existing methods lack the efficiency required to manage a large number of AFL MUs. To bridge this gap, we propose the Cluster-based Personalizable Multi-Agent Reinforcement Learning bidding strategy for MUs in Auction-based Federated Learning (CPMARL-AFL) approach. It leverages the similarities among MUs to group them into distinct clusters, each being treated as a super MU and equipped with its own bidding agent. The core of our proposed multi-agent reinforcement learning formulation revolves around the interactions between cluster agents and DOs, as well as the interactions among the cluster agents themselves. To achieve personalized bidding for each MU within a cluster, the final bid price is fine-tuned based on the expected utility gain from a given DO and the mean utility of the entire cluster, which is influenced by the bid prices generated by the cluster’s bidding agent. In addition, to prevent the bidding agent from converging to sub-optimal solutions, we design a novel reward method that facilitates efficient convergence towards the optimal solution. Through extensive experimentation conducted on six widely used benchmark datasets, CPMARL-AFL demonstrates superior performance compared to eight state-of-the-art approaches. It outperforms the best baseline by 1.28% in terms of the utility and 1.40% in terms of the test accuracy achieved by the resulting FL model.

Auction-based Federated Learning (AFL) has attracted extensive research interest due to its ability to motivate data owners to join FL through economic means. Existing works assume that only one data consumer and multiple data owners exist in an AFL marketplace (i.e., a monopoly market). Therefore, data owners bid to join the data consumer for FL. However, this assumption is not realistic in practical AFL marketplaces in which multiple data consumers can compete to attract data owners to join their respective FL tasks. In this paper, we bridge this gap by proposing a first-of-its-kind utility-maximizing bidding strategy for data consumers in federated learning (Fed-Bidder). It enables multiple FL data consumers to compete for data owners via AFL effectively and efficiently by providing with utility estimation capabilities which can accommodate diverse forms of winning functions, each reflecting different market dynamics. Extensive experiments based on six commonly adopted benchmark datasets show that FedBidder is significantly more advantageous compared to four state-of-the-art approaches.

Auction-based Federated Learning (AFL) enables open collaboration among self-interested data consumers and data owners. Existing AFL approaches cannot manage the mutual influence among multiple data consumers competing to enlist data owners. Moreover, they cannot support a single data owner to join multiple data consumers simultaneously. To bridge these gaps, we propose the Multi-Agent Reinforcement Learning for AFL (MARL-AFL) approach to steer data consumers to bid strategically towards an equilibrium with desirable overall system characteristics. We design a temperature-based reward reassignment scheme to make tradeoffs between cooperation and competition among AFL data consumers. In this way, it can reach an equilibrium state that ensures individual data consumers can achieve good utility, while preserving system-level social welfare. To circumvent potential collusion behaviors among data consumers, we introduce a bar agent to set a personalized bidding lower bound for each data consumer. Extensive experiments on six commonly adopted benchmark datasets show that MARL-AFL is significantly more advantageous compared to six state-of-the-art approaches, outperforming the best by 12.2%, 1.9% and 3.4% in terms of social welfare, revenue and accuracy, respectively.

As a revolutionary auction mechanism for display advertising, real-time bidding (RTB) allows advertisers to purchase individual ad impressions through real-time auctions. In RTB, the demand-side platform (DSP) acts as advertisers' bidding agent and aims at developing appropriate bidding strategies to maximize their specific key performance indicators (KPIs). Existing bidding strategies perform well for optimizing profits when the ad budget severely limited. However, when there is sufficient budget, their performance deteriorates. This results in added complexity for advertisers when applying these approaches in practice, hindering wider adoption. To address this challenging limitation, we propose the Adaptive ROI-Aware Bidding (ARAB) approach. It intelligently analyzes the budget setting and auction market conditions, and adjusts the bidding function accordingly to optimize profits. Different from previous studies that only bid based on the ad revenue, our proposed ROI-aware bidding function also takes into account the ad cost at impression-level. By doing so, ARAB dynamically allocates the budget on more cost-effective impressions to increase profits. Through extensive offline experiments on two real-world public datasets, we demonstrate that the proposed ARAB has achieved significant improvements in terms of both profit and ROI compared to state-of-the-art approaches.

With the rapid development of real-time bidding (RTB) in online advertising, learning the distribution of market price has attracted wide attention, since it plays a critical role in designing bidding strategies. One important problem is the right-censored issue in which the true market price can only be observed by the winner of the auction. To address this, existing studies often use Kaplan–Meier estimation (KM), which is one of the best options for survival analysis. However, these approaches depend on counting sample segments and cannot provide accurate predictions for each individual bid request. To enhance the prediction ability, we propose an original method to build the KM for each bid request by predicting (1) the probability of winning an auction at a specific market price, and (2) the probability of losing an auction at a certain bid price. To deal with the high-dimensional sample data common in RTB scenarios, we design a Markov network to calculate these two probabilities. Extensive experiments on two public datasets demonstrate that the proposed approach significantly outperforms state-of-the-art baselines in terms of various metrics, including Wasserstein distance, KL-divergence, average negative log probability and mean squared error.

The rapid rise of real-time bidding-based online advertising has brought significant economic benefits and attracted extensive research attention. From the perspective of an advertiser, it is crucial to perform accurate utility estimation and cost estimation for each individual auction in order to achieve cost-effective advertising. These problems are known as the click through rate (CTR) prediction task and the market price modeling task, respectively. However, existing approaches treat CTR prediction and market price modeling as two independent tasks to be optimized without regard to each other, thus resulting in suboptimal performance. Moreover, they do not make full use of unlabeled data from the losing bids during estimations, which makes them suffer from the sample selection bias issue. To address these limitations, we propose Multi-task Advertising Estimator (MTAE), an end-to-end joint optimization framework which performs both CTR prediction and market price modeling simultaneously. Through multi-task learning, both estimation tasks can take advantage of knowledge transfer to achieve improved feature representation and generalization abilities. In addition, we leverage the abundant bid price signals in the full-volume bid request data and introduce an auxiliary task of predicting the winning probability into the framework for unbiased learning. Through extensive experiments on two large-scale real-world public datasets, we demonstrate that our proposed approach has achieved significant improvements over the state-of-the-art models under various performance metrics.