In most of advertising and recommendation systems, multi-task learning (MTL) paradigm is widely employed to model diverse user behaviors (e.g., click, view, and purchase). Existing MTL models typically use task-shared networks with shared parameters or a routing mechanism to learn the commonalities between tasks while applying task-specific networks to learn the unique characteristics of each task. However, the potential relevance within task-specific networks is ignored, which is intuitively crucial for overall performance. In light of the fact that relevance is both task-complex and instance-specific, we present a novel learning paradigm to address these issues. In this paper, we propose Personalized Inter-task COntrastive Learning (PICO) framework, which can effectively model the inter-task relationship and is utilized to jointly estimate the click-through rate (CTR) and post-click conversion rate (CVR) in advertising systems. PICO utilizes contrastive learning to integrate inter-task knowledge implicitly from the task representations in task-specific networks. In addition, we introduce an auxiliary network to capture the inter-task relevance at instance-level and transform it into personalized temperature parameters for contrastive learning. With this method, fine-grained knowledge can be transferred to improve MTL performance without incurring additional inference costs. Both offline and online experiments show that PICO outperforms previous multi-task models significantly.
An industrial recommender system generally presents a hybrid list that contains results from multiple subsystems. In practice, each subsystem is optimized with its own feedback data to avoid the disturbance among different subsystems. However, we argue that such data usage may lead to sub-optimal online performance because of the \textit{data sparsity}. To alleviate this issue, we propose to extract knowledge from the \textit{super-domain} that contains web-scale and long-time impression data, and further assist the online recommendation task (downstream task). To this end, we propose a novel industrial \textbf{K}nowl\textbf{E}dge \textbf{E}xtraction and \textbf{P}lugging (\textbf{KEEP}) framework, which is a two-stage framework that consists of 1) a supervised pre-training knowledge extraction module on super-domain, and 2) a plug-in network that incorporates the extracted knowledge into the downstream model. This makes it friendly for incremental training of online recommendation. Moreover, we design an efficient empirical approach for KEEP and introduce our hands-on experience during the implementation of KEEP in a large-scale industrial system. Experiments conducted on two real-world datasets demonstrate that KEEP can achieve promising results. It is notable that KEEP has also been deployed on the display advertising system in Alibaba, bringing a lift of $+5.4\%$ CTR and $+4.7\%$ RPM.
Despite the development of ranking optimization techniques, the pointwise model remains the dominating approach for click-through rate (CTR) prediction. It can be attributed to the calibration ability of the pointwise model since the prediction can be viewed as the click probability. In practice, a CTR prediction model is also commonly assessed with the ranking ability, for which prediction models based on ranking losses (e.g., pairwise or listwise loss) usually achieve better performances than the pointwise loss. Previous studies have experimented with a direct combination of the two losses to obtain the benefit from both losses and observed an improved performance. However, previous studies break the meaning of output logit as the click-through rate, which may lead to sub-optimal solutions. To address this issue, we propose an approach that can Jointly optimize the Ranking and Calibration abilities (JRC for short). JRC improves the ranking ability by contrasting the logit value for the sample with different labels and constrains the predicted probability to be a function of the logit subtraction. We further show that JRC consolidates the interpretation of logits, where the logits model the joint distribution. With such an interpretation, we prove that JRC approximately optimizes the contextualized hybrid discriminative-generative objective. Experiments on public and industrial datasets and online A/B testing show that our approach improves both ranking and calibration abilities. Since May 2022, JRC has been deployed on the display advertising platform of Alibaba and has obtained significant performance improvements.
Click-through rate (CTR) prediction is a fundamental technique in recommendation and advertising systems. Recent studies have proved that learning a unified model to serve multiple domains is effective to improve the overall performance. However, it is still challenging to improve generalization across domains under limited training data, and hard to deploy current solutions due to their computational complexity. In this paper, we propose a simple yet effective framework AdaSparse for multi-domain CTR prediction, which learns adaptively sparse structure for each domain, achieving better generalization across domains with lower computational cost. In AdaSparse, we introduce domain-aware neuron-level weighting factors to measure the importance of neurons, with that for each domain our model can prune redundant neurons to improve generalization. We further add flexible sparsity regularizations to control the sparsity ratio of learned structures. Offline and online experiments show that AdaSparse outperforms previous multi-domain CTR models significantly.
Real-Time Bidding (RTB) is an important mechanism in modern online advertising systems. Advertisers employ bidding strategies in RTB to optimize their advertising effects subject to various financial requirements, especially the return-on-investment (ROI) constraint. ROIs change non-monotonically during the sequential bidding process, and often induce a see-saw effect between constraint satisfaction and objective optimization. While some existing approaches show promising results in static or mildly changing ad markets, they fail to generalize to highly dynamic ad markets with ROI constraints, due to their inability to adaptively balance constraints and objectives amidst non-stationarity and partial observability. In this work, we specialize in ROI-Constrained Bidding in non-stationary markets. Based on a Partially Observable Constrained Markov Decision Process, our method exploits an indicator-augmented reward function free of extra trade-off parameters and develops a Curriculum-Guided Bayesian Reinforcement Learning (CBRL) framework to adaptively control the constraint-objective trade-off in non-stationary ad markets. Extensive experiments on a large-scale industrial dataset with two problem settings reveal that CBRL generalizes well in both in-distribution and out-of-distribution data regimes, and enjoys superior learning efficiency and stability.
Industrial recommender systems usually hold data from multiple business scenarios and are expected to provide recommendation services for these scenarios simultaneously. In the retrieval step, the topK high-quality items selected from a large number of corpus usually need to be various for multiple scenarios. Take Alibaba display advertising system for example, not only because the behavior patterns of Taobao users are diverse, but also differentiated scenarios' bid prices assigned by advertisers vary significantly. Traditional methods either train models for each scenario separately, ignoring the cross-domain overlapping of user groups and items, or simply mix all samples and maintain a shared model which makes it difficult to capture significant diversities between scenarios. In this paper, we present Adaptive Domain Interest network that adaptively handles the commonalities and diversities across scenarios, making full use of multi-scenarios data during training. Then the proposed method is able to improve the performance of each business domain by giving various topK candidates for different scenarios during online inference. Specifically, our proposed ADI models the commonalities and diversities for different domains by shared networks and domain-specific networks, respectively. In addition, we apply the domain-specific batch normalization and design the domain interest adaptation layer for feature-level domain adaptation. A self training strategy is also incorporated to capture label-level connections across domains.ADI has been deployed in the display advertising system of Alibaba, and obtains 1.8% improvement on advertising revenue.
Current bundle generation studies focus on generating a combination of items to improve user experience. In real-world applications, there is also a great need to produce bundle creatives that consist of mixture types of objects (e.g., items, slogans and templates) for achieving better promotion effect. We study a new problem named bundle creative generation: for given users, the goal is to generate personalized bundle creatives that the users will be interested in. To take both quality and efficiency into account, we propose a contrastive non-autoregressive model that captures user preferences with ingenious decoding objective. Experiments on large-scale real-world datasets verify that our proposed model shows significant advantages in terms of creative quality and generation speed.
Learning individual-level treatment effect is a fundamental problem in causal inference and has received increasing attention in many areas, especially in the user growth area which concerns many internet companies. Recently, disentangled representation learning methods that decompose covariates into three latent factors, including instrumental, confounding and adjustment factors, have witnessed great success in treatment effect estimation. However, it remains an open problem how to learn the underlying disentangled factors precisely. Specifically, previous methods fail to obtain independent disentangled factors, which is a necessary condition for identifying treatment effect. In this paper, we propose Disentangled Representations for Counterfactual Regression via Mutual Information Minimization (MIM-DRCFR), which uses a multi-task learning framework to share information when learning the latent factors and incorporates MI minimization learning criteria to ensure the independence of these factors. Extensive experiments including public benchmarks and real-world industrial user growth datasets demonstrate that our method performs much better than state-of-the-art methods.
A contemporary feed application usually provides blended results of organic items and sponsored items~(ads) to users. Conventionally, ads are exposed at fixed positions. Such a static exposure strategy is inefficient due to ignoring users' personalized preferences towards ads. To this end, adaptive ad exposure has become an appealing strategy to boost the overall performance of the feed. However, existing approaches to implementing the adaptive ad exposure still suffer from several limitations: 1) they usually fall into sub-optimal solutions because of only focusing on request-level optimization without consideration of the long-term application-level performance and constraints, 2) they neglect the necessity of keeping the game-theoretical properties of ad auctions, which may lead to anarchy in bidding, and 3) they can hardly be deployed in large-scale applications due to high computational complexity. In this paper, we focus on long-term performance optimization under hierarchical constraints in feeds and formulate the adaptive ad exposure as a Dynamic Knapsack Problem. We propose an effective approach: Hierarchically Constrained Adaptive Ad Exposure~(HCA2E). We present that HCA2E possesses desired game-theoretical properties, computational efficiency, and performance robustness. Comprehensive offline and online experiments on a leading e-commerce application demonstrate the significant performance superiority of HCA2E over representative baselines. HCA2E has also been deployed on this application to serve millions of daily users.