Recent advances in Graph Neural Networks (GNNs) have revolutionized graph-structured data modeling, yet traditional GNNs struggle with complex heterogeneous structures prevalent in real-world scenarios. Despite progress in handling heterogeneous interactions, two fundamental challenges persist: noisy data significantly compromising embedding quality and learning performance, and existing methods' inability to capture intricate semantic transitions among heterogeneous relations, which impacts downstream predictions. To address these fundamental issues, we present the Heterogeneous Graph Diffusion Model (DiffGraph), a pioneering framework that introduces an innovative cross-view denoising strategy. This advanced approach transforms auxiliary heterogeneous data into target semantic spaces, enabling precise distillation of task-relevant information. At its core, DiffGraph features a sophisticated latent heterogeneous graph diffusion mechanism, implementing a novel forward and backward diffusion process for superior noise management. This methodology achieves simultaneous heterogeneous graph denoising and cross-type transition, while significantly simplifying graph generation through its latent-space diffusion capabilities. Through rigorous experimental validation on both public and industrial datasets, we demonstrate that DiffGraph consistently surpasses existing methods in link prediction and node classification tasks, establishing new benchmarks for robustness and efficiency in heterogeneous graph processing. The model implementation is publicly available at: https://github.com/HKUDS/DiffGraph.

In real-time bidding systems, ad exchanges and supply-side platforms (SSP) are switching from the second-price auction (SPA) to the first-price auction (FPA), where the advertisers should pay what they bid if they win the auction. To avoid overpaying, advertisers are motivated to conceal their truthful evaluations of impression opportunities through bid shading methods. However, advertisers are consistently facing a trade-off between the probability and cost-saving of winning, due to the information asymmetry, where advertisers lack knowledge about their competitors' bids in the market. To address this challenge, we propose a Bayes ian Multi-Armed Bandit (BayesMAB) algorithm for bid shading when the winning price is unknown to advertisers who lose the impression opportunity. BayesMAB incorporates the mechanism of FPA to infer each price interval's winning rate by progressively updating the market price hidden by SSP. In this way, BayesMAB better approximates the winning rates of price intervals and thus is able to derive the optimal shaded bid that balances the trade-off between the probability and cost-saving of winning the impression opportunity. We conducted large-scale A/B tests on Tencent's online display advertising platform. The cost-per-mile (CPM) and cost-per-action (CPA) decreased by 13.06% and 11.90%, respectively, whereas the return on investment (ROI) increased by 12.31% with only 2.7% sacrifice of the winning rate. We also validated BayesMAB's superior performance in an offline semi-simulated experiment with SPA data sets. BayesMAB has been deployed online and is impacting billions of traffic every day. Codes are available at https://github.com/BayesMAB/BayesMAB.

Recommender systems are widely applied on web. For example, online advertising systems rely on recommender systems to accurately estimate the value of display opportunities, which is critical to maximize the profits of advertisers. To reduce computational resource consumption, the core tactic of Multi-Scenario Multi-Task Learning (MSMTL) is to devise a single recommder system that is adapted to all contexts instead of implementing multiple scenario-oriented or task-oriented recommender systems. However, MSMTL is challenging because there are complicated task-task, scenario-scenario, and task-scenario interrelations; the characteristic of different tasks in different scenarios also largely varies; and samples of each context are often unevenly distributed. Previous MSMTL solutions focus on applying scenario knowledge to improve the performance of multi-task learning, while neglecting the complicated interrelations among tasks and scenarios. Moreover, samples derived from different scenarios are transferred into the latent embedding with the same dimension. This static embedding strategy impedes the practicality of model expressiveness, since the scenarios with sufficient samples are underrepresented and those with insufficient samples are over-represented.

Customer lifetime value (LTV) prediction is essential for mobile game publishers trying to optimize the advertising investment for each user acquisition based on the estimated worth. In mobile games, deploying microtransactions is a simple yet effective monetization strategy, which attracts a tiny group of game whales who splurge on in-game purchases. The presence of such game whales may impede the practicality of existing LTV prediction models, since game whales' purchase behaviours always exhibit varied distribution from general users. Consequently, identifying game whales can open up new opportunities to improve the accuracy of LTV prediction models. However, little attention has been paid to applying game whale detection in LTV prediction, and existing works are mainly specialized for the long-term LTV prediction with the assumption that the high-quality user features are available, which is not applicable in the UA stage. In this paper, we propose ExpLTV, a novel multi-task framework to perform LTV prediction and game whale detection in a unified way. In ExpLTV, we first innovatively design a deep neural network-based game whale detector that can not only infer the intrinsic order in accordance with monetary value, but also precisely identify high spenders (i.e., game whales) and low spenders. Then, by treating the game whale detector as a gating network to decide the different mixture patterns of LTV experts assembling, we can thoroughly leverage the shared information and scenario-specific information (i.e., game whales modelling and low spenders modelling). Finally, instead of separately designing a purchase rate estimator for two tasks, we design a shared estimator that can preserve the inner task relationships. The superiority of ExpLTV in terms of its LTV prediction and game whale detection effectiveness is further validated via extensive experiments on three industrial datasets.

Nowadays, customer lifetime value (LTV) plays an important role in mobile game advertising, since it can be beneficial to adjust ad bids and ensure that the games are promoted to the most valuable users. Some neural models are utilized for LTV prediction based on the rich user features. However, in the advertising scenario, due to the privacy settings or limited length of log retention, etc, most of existing approaches suffer from the missing feature problem. Moreover, only a small fraction of purchase behaviours can be observed. The label sparsity inevitably limits model expressiveness. To tackle the aforementioned challenges, we propose a feature missing-aware routing-and-fusion network (MarfNet) to reduce the effect of the missing features while training. Specifically, we calculate the missing states of raw features and feature interactions for each sample. Based on the missing states, two missing-aware layers are designed to route samples into different experts, thus each expert can focus on the real features of samples assigned to it. Finally we get the missing-aware representation by the weighted fusion of the experts. To alleviate the label sparsity, we further propose a batch-in dynamic discrimination enhanced (Bidden) loss weight mechanism, which can automatically assign greater loss weights to difficult samples in the training process. Both offline experiments and online A/B tests have validated the superiority of our proposed Bidden-MarfNet.

Data scarcity, e.g., labeled data being either unavailable or too expensive, is a perpetual challenge of recommendation systems. Cross-domain recommendation leverages the label information in the source domain to facilitate the task in the target domain. However, in many real-world cross-domain recommendation systems, the source domain and the target domain are sampled from different data distributions, which obstructs the cross-domain knowledge transfer. In this paper, we propose to specifically align the data distributions between the source domain and the target domain to alleviate imbalanced sample distribution and thus challenge the data scarcity issue in the target domain. Technically, our proposed approach builds an adversarial adaptation (AA) framework to adversarially train the target model together with a pre-trained source model. A domain discriminator plays the two-player minmax game with the target model and guides the target model to learn domain-invariant features that can be transferred across domains. At the same time, the target model is calibrated to learn domain-specific information of the target domain. With such a formulation, the target model not only learns domain-invariant features for knowledge transfer, but also preserves domain-specific information for target recommendation. We apply the proposed method to address the issues of insufficient data and imbalanced sample distribution in real-world Click-Through Rate (CTR)/Conversion Rate (CVR) predictions on a large-scale dataset. Specifically, we formulate our approach as a plug-and-play module to boost existing recommendation systems. Extensive experiments verify that the proposed method is able to significantly improve the prediction performance on the target domain. For instance, our method can boost PLE with a performance improvement of 13.88% in terms of Area Under Curve (AUC) compared with single-domain PLE.

The real-time bidding (RTB) paradigm allows the advertisers to submit a bid for each impression in online display advertising. A usual demand of the advertisers is to maximize the total value of winning impressions under constraints on some key performance indicators. Unfortunately, the existing RTB research in industrial applications can hardly achieve the optimum due to the stochastic decision scenarios and complex consumer behaviors. In this study, we address the application of RTB to mobile gaming where the in-app purchase action is of high uncertainty, making it challenging to evaluate individual impression opportunities. We first formulate the bidding process into a constrained optimization problem and then propose an actor-critic reinforcement learning (ACRL) model for obtaining the optimal policy under a dynamic decision environment. To avoid feeding too many samples with zero labels to the model, we provide a new way to quantify impression opportunities by integrating the in-app actions, such as conversion and purchase, and the characteristics of the candidate ad inventories. Moreover, the proposed ACRL learns a Gaussian distribution to simulate the audience's decision in a more real bidding scenario by taking additional contextual side information about both media and the audience. We also introduce how to deploy the learned model online to help adjust the final bid. At last, we conduct comprehensive offline experiments to demonstrate the effectiveness of ACRL and carefully set an online A/B testing experiment. The online experimental results verify the efficacy of the proposed ACRL in terms of multiple critical commercial indicators. ACRL has been deployed in the Tencent online display advertising platform and impacts billions of traffic every day. We believe proposed modifications for optimal bidding problems in RTB are practically innovative and can inspire the relative works in this field.