Online platforms such as Amazon and Netflix serve users across multiple countries and regions, underscoring the importance of multi-market recommendation (MMR). Most MMR methods adopt a pre-training and fine-tuning paradigm, in which a unified model is first trained on centralized, global data and subsequently adapted to specific markets. However, this approach ignores the privacy of market data. While traditional federated learning preserves privacy, it typically aims to obtain a global model by aggregating model parameters and does not account for significant market heterogeneity. Additionally, because ID spaces are disjoint across markets, embedding-based aggregation strategies become ineffective. To overcome these challenges, we propose a federated collaborative signal quantization (FedMM) method for multi-market click-through rate (CTR) prediction. Our core idea leverages a discrete codebook mechanism to achieve privacy-preserving transmission and align disjoint ID spaces. We further employ a hierarchical codebook structure to capture cross-market shared patterns and market-specific characteristics. Specifically, we deploy a residual quantized variational autoencoder (RQ-VAE) with a dual-layer codebook mechanism for each market to quantize collaborative embeddings. The first layer utilizes a global federated codebook, updated via aggregation to capture universally shared collaborative patterns, while the second layer maintains a local codebook to learn market-specific semantics. Finally, the learned discrete codes, which integrate both general and specific collaborative signals, are incorporated into downstream CTR models to enhance prediction accuracy across all markets. Extensive experiments on benchmark datasets demonstrate that FedMM significantly improves recommendation performance with privacy guarantees.

Multi-scenario multi-task recommendation (MSMTR) systems must address recommendation demands across diverse scenarios while simultaneously optimizing multiple objectives, such as click-through rate and conversion rate. Existing MSMTR models typically consist of four information units: scenario-shared, scenario-specific, task-shared, and task-specific networks. These units interact to generate four types of relationship information flows, directed from scenario-shared or scenario-specific networks to task-shared or task-specific networks. However, these models face two main limitations: 1) They often rely on complex architectures, such as mixture-of-experts (MoE) networks, which increase the complexity of information fusion, model size, and training cost. 2) They extract all available information flows without filtering out irrelevant or even harmful content, introducing potential noise. Regarding these challenges, we propose a lightweight Automated Information Flow Selection (AutoIFS) framework for MSMTR. To tackle the first issue, AutoIFS incorporates low-rank adaptation (LoRA) to decouple the four information units, enabling more flexible and efficient information fusion with minimal parameter overhead. To address the second issue, AutoIFS introduces an information flow selection network that automatically filters out invalid scenario-task information flows based on model performance feedback. It employs a simple yet effective pruning function to eliminate useless information flows, thereby enhancing the impact of key relationships and improving model performance. Finally, we evaluate AutoIFS and confirm its effectiveness through extensive experiments on two public benchmark datasets and an online A/B test.

Large language models (LLMs) have been incorporated into numerous industrial applications. Meanwhile, a vast array of API assets is scattered across various functions in the financial domain. An online financial question-answering system can leverage both LLMs and private APIs to provide timely financial analysis and information. The key is equipping the LLM model with function calling capability tailored to a financial scenario. However, a generic LLM requires customized financial APIs to call and struggles to adapt to the financial domain. Additionally, online user queries are diverse and contain out-of-distribution parameters compared with the required function input parameters, which makes it more difficult for a generic LLM to serve online users. In this paper, we propose a data-driven pipeline to enhance function calling in LLM for our online, deployed financial QA, comprising dataset construction, data augmentation, and model training. Specifically, we construct a dataset based on a previous study and update it periodically, incorporating queries and an augmentation method named AugFC. The addition of user query-related samples will exploit our financial toolset in a data-driven manner, and AugFC explores the possible parameter values to enhance the diversity of our updated dataset. Then, we train an LLM with a two-step method, which enables the use of our financial functions. Extensive experiments on existing offline datasets, as well as the deployment of an online scenario, illustrate the superiority of our pipeline. The related pipeline has been adopted in the financial QA of YuanBao. https://yuanbao.tencent.com/chat/, one of the largest chat platforms in China.

Lifelong behavior modeling for single-domain has been widely investigated in industry click-through (CTR) prediction. However, some domains do not always have rich historical behaviors in online platforms, so cross-domain lifelong behavior modeling is overlooked. This paper proposes a novel retrieval augmented lifelong cross-domain net (RAL-CDNet) to address the challenges in cross-domain lifelong behavior modeling. There are three components in RAL-CDNet, i.e., cross-domain retrieval unit, cross-domain alignment unit, and cross-net. As the general search unit in the previous study, a cross-domain retrieval unit features a retrieval augmented paradigm that utilizes a pre-trained language model to learn the intrinsic textual information of user behaviors and generates the sequential behaviors from the source domain based on sequential behaviors in the target domain. The retrieval augmented behaviors can achieve consistency and capture accurate hidden interest for target domain CTR prediction. Furthermore, we propose the cross-domain alignment unit to align the embeddings across domains by adding a semantic-guided contrastive loss and auxiliary task loss in the source domain. This allows the embeddings to be consistent across domains and have enough source information to capture the cross-domain relation. Finally, the cross-net utilizes two-level attention techniques to enhance the final prediction in the target domain. We conduct extensive experiments on both a public dataset and an industrial dataset from the WeChat advertising platform to demonstrate the effectiveness of RAL-CDNet in terms of offline and online metrics.

Multi-scenario recommendation (MSR) is a popular training paradigm in industrial platforms for uniformly integrating information from multiple scenarios and serving them simultaneously. A key challenge in MSR research is accurately identifying the commonalities and distinctive information between scenarios. Currently, most existing MSR methods focus on implicitly extracting this information from the architectural level. However, this continues to increase the complexity and training overhead of MSR. Furthermore, the custom components responsible for extracting implicit information in each MSR method are too dependent on the specific MSR architecture and are not easily reused in other methods. Given these challenges, we first show in a motivating experiment that it may be beneficial to explicitly select a reasonable set of shared instances that can affect parameter optimization in all scenarios during the training of MSR, i.e., to explicitly obtain the critical information required for MSR from the data level. Then, this paper proposes SSIM with an adaptive selection network. Specifically, SSIM can be integrated with existing MSR methods in a lightweight way to adaptively select an informative and shareable subset of instances from each scenario to improve recommendations. In particular, the selected multi-scenario shared subset has extraordinary reusability and can be easily saved to benefit model training of various future MSR models. Finally, we evaluate SSIM and demonstrate its effectiveness through experiments on two public multi-scenario benchmarks and an online A/B test.

Improving user engagement and platform revenue is crucial for online marketing platforms. Uplift modeling is proposed to solve this problem, which applies different treatments (e.g., discounts, bonus) to satisfy corresponding users. Despite progress in this field, limitations persist. Firstly, most of them focus on scenarios where only user features exist. However, in real-world scenarios, there are rich contexts available in the online platform (e.g., short videos, news), and the uplift model needs to infer an incentive for each user on the specific item, which is called real-time marketing. Thus, only considering the user features will lead to biased prediction of the responses, which may cause the cumulative error for uplift prediction. Moreover, due to the large-scale contexts, directly concatenating the context features with the user features will cause a severe distribution shift in the treatment and control groups. Secondly, capturing the interaction relationship between the user features and context features can better predict the user response. To solve the above limitations, we propose a novel model-agnostic Robust Uplift Modeling with Large-Scale Contexts (UMLC) framework for Real-time Marketing. Our UMLC includes two customized modules. 1) A response-guided context grouping module for extracting context features information and condensing value space through clusters. 2) A feature interaction module for obtaining better uplift prediction. Specifically, this module contains two parts: a user-context interaction component for better modeling the response; a treatment-feature interaction component for discovering the treatment assignment sensitive feature of each instance to better predict the uplift. Moreover, we conduct extensive experiments on a synthetic dataset and a real-world product dataset to verify the effectiveness and compatibility of our UMLC.

In recent years, the introduction of knowledge graphs (KGs) has significantly advanced recommender systems by facilitating the discovery of potential associations between items. However, existing methods still face several limitations. First, most KGs suffer from missing facts or limited scopes. Second, existing methods convert textual information in KGs into IDs, resulting in the loss of natural semantic connections between different items. Third, existing methods struggle to capture high-order connections in the global KG. To address these limitations, we propose a novel method called CoLaKG, which leverages large language models (LLMs) to improve KG-based recommendations. The extensive knowledge and remarkable reasoning capabilities of LLMs enable our method to supplement missing facts in KGs, and their powerful text understanding abilities allow for better utilization of semantic information. Specifically, CoLaKG extracts useful information from KGs at both local and global levels. By employing the item-centered subgraph extraction and prompt engineering, it can accurately understand the local information. In addition, through the semantic-based retrieval module, each item is enriched by related items from the entire knowledge graph, effectively harnessing global information. Furthermore, the local and global information are effectively integrated into the recommendation model through a representation fusion module and a retrieval-augmented representation learning module, respectively. Extensive experiments on four real-world datasets demonstrate the superiority of our method.

Multi-scenario recommendation (MSR) has become a core component of various online platforms, but its increasing model size has also brought attention to its efficiency optimization. An important effort is to find effective and efficient feature embedding layers for MSR, and existing work focuses on scenario-level feature selection, i.e., all instance embeddings in the same scenario get the same filtering results on the feature set, and the filtering results are different for different scenarios. However, this ignores the information redundancy of the dimension set and the individuality of different instances in the same scenario. To address these limitations, we propose a multi-scenario instance embedding learning (MultiEmb) framework that implements exclusive feature-dimension redundant information removal for different instances within a scenario to obtain the optimal individual embeddings. The core of our MultiEmb is to introduce an instance embedding selection network to effectively complete the above challenging tasks, in which a set of feature selection and dimension selection adaptive components are equipped for each scenario, and their combination completes the optimal embedding selection for each instance. Finally, we evaluate MultiEmb through extensive experiments on two public multi-scenario benchmarks and demonstrate its effectiveness, compatibility, transferability, etc.

The evolution of previous Click-Through Rate (CTR) models has mainly been driven by proposing complex components, whether shallow or deep, that are adept at modeling feature interactions. However, there has been less focus on improving fusion design. Instead, two naive solutions, stacked and parallel fusion, are commonly used. Both solutions rely on pre-determined fusion connections and fixed fusion operations. It has been repetitively observed that changes in fusion design may result in different performances, highlighting the critical role that fusion plays in CTR models. While there have been attempts to refine these basic fusion strategies, these efforts have often been constrained to specific settings or dependent on specific components. Neural architecture search has also been introduced to partially deal with fusion design, but it comes with limitations. The complexity of the search space can lead to inefficient and ineffective results. To bridge this gap, we introduce OptFusion, a method that automates the learning of fusion, encompassing both the connection learning and the operation selection. We have proposed a one-shot learning algorithm tackling these tasks concurrently. Our experiments are conducted over three large-scale datasets. Extensive experiments prove both the effectiveness and efficiency of OptFusion in improving CTR model performance. Our code implementation is available here https://github.com/kexin-kxzhang/OptFusion.

Different from the data sparsity that traditional recommendations suffer from, context-aware recommender systems (CARS) face specific sparsity challenges related to contextual features, i.e., feature sparsity and interaction sparsity. How knowledge graphs address these challenges remains under-discussed. To bridge this gap, in this article, we first propose a novel pairwise intent graph containing nodes of users, items, entities, and enhanced intents to integrate knowledge graphs into CARS efficiently. Enhanced intent nodes are generated through the specific fusion of relational sub-intent and contextual sub-intent, and they are derived from semantic information and contextual information, respectively. We develop a pairwise intent graph embedding learning (PING) framework based on it. Specifically, our PING uses a pairwise intent joint graph convolution module to obtain refined embedding of all the features, where each enhanced intent node acts as a hub to effectively propagate information among different features and between all the features and knowledge graphs. Then, a recommendation module with refined embeddings is used to replace the randomly initialized embeddings of downstream recommendation models to improve model performance. Extensive experiments on three public datasets and some real-world scenarios verify the effectiveness and compatibility of our PING.

Customer Lifetime Value (CLTV) prediction is a critical task in business applications, such as customer relationship management (CRM), online marketing, etc. Accurately predicting CLTV is challenging in real-world business scenarios, as the distribution of CLTV is complex and mutable. Firstly, there is a large number of users without any consumption consisting of a long-tailed part that is too complex to fit. Secondly, the small set of high-value users spent orders of magnitude more than a typical user leading to a wide range of the CLTV distribution which is hard to capture in a single distribution. Existing approaches for CLTV estimation either assume a prior probability distribution and fit a single group of distribution-related parameters for all samples, or directly learn from the posterior distribution with manually predefined buckets in a heuristic manner. However, all these methods fail to handle complex and mutable distributions. In this paper, we propose a novel optimal distribution selection model (OptDist) for CLTV prediction, which utilizes an adaptive optimal sub-distribution selection mechanism to improve the accuracy of complex distribution modeling. Specifically, OptDist trains several candidate sub-distribution networks in the distribution learning module (DLM) for modeling the probability distribution of CLTV. Then, a distribution selection module (DSM) is proposed to select the sub-distribution for each sample, thus making the selection automatically and adaptively. Besides, we design an alignment mechanism that connects both modules, which effectively guides the optimization. We conduct extensive experiments on both two public and one private dataset to verify that OptDist outperforms state-of-the-art baselines. Furthermore, OptDist has been deployed on a large-scale financial platform for customer acquisition marketing campaigns and the online experiments also demonstrate the effectiveness of OptDist.

As user behaviors become complicated on business platforms, online recommendations focus more on how to touch the core conversions, which are highly related to the interests of platforms. These core conversions are usually continuous targets, such as watch time, revenue, and so on, whose predictions can be enhanced by previous discrete conversion actions. Therefore, multi-task learning (MTL) can be adopted as the paradigm to learn these hybrid targets. However, existing works mainly emphasize investigating the sequential dependence among discrete conversion actions, which neglects the complexity of dependence between discrete conversions and the final continuous conversion. Moreover, simultaneously optimizing hybrid tasks with stronger task dependence will suffer from volatile issues where the core regression task might have a larger influence on other tasks. In this paper, we study the MTL problem with hybrid targets for the first time and propose the model named Hybrid Targets Learning Network (HTLNet) to explore task dependence and enhance optimization. Specifically, we introduce label embedding for each task to explicitly transfer the label information among these tasks, which can effectively explore logical task dependence. We also further design the gradient adjustment regime between the final regression task and other classification tasks to enhance the optimization. Extensive experiments on two offline public datasets and one real-world industrial dataset are conducted to validate the effectiveness of HTLNet. Moreover, online A/B tests on the financial recommender system also show that our model has improved significantly. Our implementation is available here1.

In modern online platforms, incentives (e.g., discounts, bonus) are essential factors that enhance user engagement and increase platform revenue. Over recent years, uplift modeling has been introduced as a strategic approach to assign incentives to individual customers. Especially in many real-world applications, online platforms can only incentivize customers with specific budget constraints. This problem can be reformulated as the multi-choice knapsack problem (MCKP). The objective of this optimization is to select the optimal incentive for each customer to maximize the return on investment (ROI). Recent works in this field frequently tackle the budget allocation problem using a two-stage approach. However, this solution is confronted with the following challenges: (1) The causal inference methods often ignore the domain knowledge in online marketing, where the expected response curve of a customer should be monotonic and smooth as the incentive increases. (2) There is an optimality gap between the two stages, resulting in inferior sub-optimal allocation performance due to the loss of the incentive recommendation information for the uplift prediction under the limited budget constraint. To address these challenges, we propose a novel End-to-End Cost-Effective Incentive Recommendation (E3IR) model under the budget constraint. Specifically, our methods consist of two modules, i.e., the uplift prediction module and the differentiable allocation module. In the uplift prediction module, we construct prediction heads to capture the incremental improvement between adjacent treatments with the marketing domain constraints (i.e., monotonic and smooth). We incorporate integer linear programming (ILP) as a differentiable layer input in the differentiable allocation module. Furthermore, we conduct extensive experiments on public and real product datasets, demonstrating that our E3IR improves allocation performance compared to existing two-stage approaches.

Multi-behavior recommender systems (MBRS) have been commonly deployed on real-world industrial platforms for their superior advantages in understanding user preferences and mitigating data sparsity. However, the cascade graph modeling paradigm adopted in mainstream MBRS usually assumes that users will refer to all types of behavioral knowledge they have when making decisions about target behaviors, i.e., use all types of behavioral interactions indiscriminately when modeling and predicting target behaviors for each user. We call this a full decision chain constraint and argue that it may be too strict by ignoring that different types of behavioral knowledge have varying importance for different users. In this paper, we propose a novel automated decision chain selection (AutoDCS) framework to relax this constraint, which can consider each user's unique decision dependencies and select a reasonable set of behavioral knowledge to activate for the prediction of target behavior. Specifically, AutoDCS first integrates some existing MBRS methods in a base cascade module to obtain a set of behavior-aware embeddings. Then, a bilateral matching gating mechanism is used to select an exclusive set of behaviors for the current user-item pair to form a decision chain, and the corresponding behavior-augmented embeddings are selectively activated. Subsequently, AutoDCS combines the behavior-augmented and original behavior-aware embeddings to predict the target behavior. Finally, we evaluate AutoDCS and demonstrate its effectiveness through experiments over four public multi-behavior benchmarks.

Multi-scenario recommender systems (MSRSs) have been increasingly used in real-world industrial platforms for their excellent advantages in mitigating data sparsity and reducing maintenance costs. However, conventional MSRSs usually use all relevant features indiscriminately and ignore that different kinds of features have varying importance under different scenarios, which may cause confusion and performance degradation. In addition, existing feature selection methods for deep recommender systems may lack the exploration of scenario relations. In this paper, we propose a novel automated multi-scenario feature selection (MultiFS) framework to bridge this gap, which is able to consider scenario relations and utilize a hierarchical gating mechanism to select features for each scenario. Specifically, MultiFS first efficiently obtains feature importance across all the scenarios through a scenario-shared gate. Then, some scenario-specific gate aims to identify feature importance to individual scenarios from a subset of the former with lower importance. Subsequently, MultiFS imposes constraints on the two gates to make the learning mechanism more feasible and combines the two to select exclusive features for different scenarios. We evaluate MultiFS and demonstrate its ability to enhance the multi-scenario model performance through experiments over two public multi-scenario benchmarks.

Static analysis tools for capturing bugs and vulnerabilities in software programs are widely employed in practice, as they have the unique advantages of high coverage and independence from the execution environment. However, existing tools for analyzing large codebases often produce a great deal of false warnings over genuine bug reports. As a result, developers are required to manually inspect and confirm each warning, a challenging, time-consuming, and automation-essential task. This article advocates a fast, general, and easily extensible approach called Llm4sa that automatically inspects a sheer volume of static warnings by harnessing (some of) the powers of Large Language Models (LLMs). Our key insight is that LLMs have advanced program understanding capabilities, enabling them to effectively act as human experts in conducting manual inspections on bug warnings with their relevant code snippets. In this spirit, we propose a static analysis to effectively extract the relevant code snippets via program dependence traversal guided by the bug warning reports themselves. Then, by formulating customized questions that are enriched with domain knowledge and representative cases to query LLMs, Llm4sa can remove a great deal of false warnings and facilitate bug discovery significantly. Our experiments demonstrate that Llm4sa is practical in automatically inspecting thousands of static warnings from Juliet benchmark programs and 11 real-world C/C++ projects, showcasing a high precision (81.13%) and a recall rate (94.64%) for a total of 9,547 bug warnings. Our research introduces new opportunities and methodologies for using the LLMs to reduce human labor costs, improve the precision of static analyzers, and ensure software trustworthiness

Uplift modeling has shown very promising results in online marketing. However, most existing works are prone to the robustness challenge in some practical applications. In this paper, we first present a possible explanation for the above phenomenon. We verify that there is a feature sensitivity problem in online marketing using different real-world datasets, where the perturbation of some key features will seriously affect the performance of the uplift model and even cause the opposite trend. To solve the above problem, we propose a novel robustness-enhanced uplift modeling framework with adversarial feature desensitization (RUAD). Specifically, our RUAD can more effectively alleviate the feature sensitivity of the uplift model through two customized modules, including a feature selection module with joint multi-label modeling to identify a key subset from the input features and an adversarial feature desensitization module using adversarial training and soft interpolation operations to enhance the robustness of the model against this selected subset of features. Finally, we conduct extensive experiments on a public dataset and a real product dataset to verify the effectiveness of our RUAD in online marketing. In addition, we also demonstrate the robustness of our RUAD to the feature sensitivity, as well as the compatibility with different uplift models.

As a key component in online marketing, uplift modeling aims to accurately capture the degree to which different treatments motivate different users, such as coupons or discounts, also known as the estimation of individual treatment effect (ITE). In an actual business scenario, the options for treatment may be numerous and complex, and there may be correlations between different treatments. In addition, each marketing instance may also have rich user and contextual features. However, existing methods still fall short in both fully exploiting treatment information and mining features that are sensitive to a particular treatment. In this paper, we propose an explicit feature interaction-aware uplift network (EFIN) to address these two problems. Our EFIN includes four customized modules: 1) a feature encoding module encodes not only the user and contextual features, but also the treatment features; 2) a self-interaction module aims to accurately model the user's natural response with all but the treatment features; 3) a treatment-aware interaction module accurately models the degree to which a particular treatment motivates a user through interactions between the treatment features and other features, i.e., ITE; and 4) an intervention constraint module is used to balance the ITE distribution of users between the control and treatment groups so that the model would still achieve a accurate uplift ranking on data collected from a non-random intervention marketing scenario. We conduct extensive experiments on two public datasets and one product dataset to verify the effectiveness of our EFIN. In addition, our EFIN has been deployed in a credit card bill payment scenario of a large online financial platform with a significant improvement.

Although knowledge graph has shown their effectiveness in mitigating data sparsity in many recommendation tasks, they remain underutilized in context-aware recommender systems (CARS) with the specific sparsity challenges associated with the contextual features, i.e., feature sparsity and interaction sparsity. To bridge this gap, in this paper, we propose a novel pairwise intent graph embedding learning (PING) framework to efficiently integrate knowledge graphs into CARS. Specifically, our PING contains three modules: 1) a graph construction module is used to obtain a pairwise intent graph (PIG) containing nodes for users, items, entities, and enhanced intent, where enhanced intent nodes are generated by applying user intent fusion (UIF) on relational intent and contextual intent, and two sub-intents are derived from the semantic information and contextual information, respectively; 2) a pairwise intent joint graph convolution module is used to obtain the refined embeddings of all the features by executing a customized convolution strategy on PIG, where each enhanced intent node acts as a hub to efficiently propagate information among different features and between all the features and knowledge graph; 3) a recommendation module with the refined embeddings is used to replace the randomly initialized embeddings of downstream recommendation models to improve model performance. Finally, we conduct extensive experiments on three public datasets to verify the effectiveness and compatibility of our PING.

Tabular data is one of the most common data storage formats behind many real-world web applications such as retail, banking, and e-commerce. The success of these web applications largely depends on the ability of the employed machine learning model to accurately distinguish influential features from all the predetermined features in tabular data. Intuitively, in practical business scenarios, different instances should correspond to different sets of influential features, and the set of influential features of the same instance may vary in different scenarios. However, most existing methods focus on global feature selection assuming that all instances have the same set of influential features, and few methods considering instance-wise feature selection ignore the variability of influential features in different scenarios. In this paper, we first introduce a new perspective based on the influence function for instance-wise feature selection, and give some corresponding theoretical insights, the core of which is to use the influence function as an indicator to measure the importance of an instance-wise feature. We then propose a new solution for discovering instance-wise influential features in tabular data (DIWIFT), where a self-attention network is used as a feature selection model and the value of the corresponding influence function is used as an optimization objective to guide the model. Benefiting from the advantage of the influence function, i.e., its computation does not depend on a specific architecture and can also take into account the data distribution in different scenarios, our DIWIFT has better flexibility and robustness. Finally, we conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness of our DIWIFT.

Click-through prediction (CTR) models transform features into latent vectors and enumerate possible feature interactions to improve performance based on the input feature set. Therefore, when selecting an optimal feature set, we should consider the influence of both features and their interaction. However, most previous works focus on either feature field selection or only select feature interaction based on the fixed feature set to produce the feature set. The former restricts search space to the feature field, which is too coarse to determine subtle features. They also do not filter useless feature interactions, leading to higher computation costs and degraded model performance. The latter identifies useful feature interaction from all available features, resulting in many redundant features in the feature set. In this paper, we propose a novel method named OptFS to address these problems. To unify the selection of features and their interaction, we decompose the selection of each feature interaction into the selection of two correlated features. Such a decomposition makes the model end-to-end trainable given various feature interaction operations. By adopting feature-level search space, we set a learnable gate to determine whether each feature should be within the feature set. Because of the large-scale search space, we develop a learning-by-continuation training scheme to learn such gates. Hence, OptFS generates the feature set containing features that improve the final prediction results. Experimentally, we evaluate OptFS on three public datasets, demonstrating OptFS can optimize feature sets which enhance the model performance and further reduce both the storage and computational cost.

The bias problems in recommender systems are an important challenge. In this paper, we focus on solving the bias problems via uniform data. Previous works have shown that simple modeling with a uniform data can alleviate the bias problems and improve the performance. However, the uniform data is usually few and expensive to collect in a real product. In order to use the valuable uniform data more effectively, we propose a novel and general knowledge distillation framework for counterfactual recommendation with four specific methods, including label-based distillation, feature-based distillation, sample-based distillation and model structure-based distillation. Moreover, we discuss the relation between the proposed framework and the previous works. We then conduct extensive experiments on both public and product datasets to verify the effectiveness of the proposed four methods. In addition, we explore and analyze the performance trends of the proposed methods on some key factors, and the changes in the distribution of the recommendation lists. Finally, we emphasize that counterfactual modeling with uniform data is a rich research area, and list some interesting and promising research topics worthy of further exploration. Note that the source codes are available athttps://github.com/dgliu/TKDE_KDCRec.

Debiased recommendation with a randomized dataset has shown very promising results in mitigating system-induced biases. However, it still lacks more theoretical insights or an ideal optimization objective function compared with the other more well-studied routes without a randomized dataset. To bridge this gap, we study the debiasing problem from a new perspective and propose to directly minimize the upper bound of an ideal objective function, which facilitates a better potential solution to system-induced biases. First, we formulate a new ideal optimization objective function with a randomized dataset. Second, according to the prior constraints that an adopted loss function may satisfy, we derive two different upper bounds of the objective function: a generalization error bound with triangle inequality and a generalization error bound with separability. Third, we show that most existing related methods can be regarded as the insufficient optimization of these two upper bounds. Fourth, we propose a novel method called debiasing approximate upper bound ( DUB ) with a randomized dataset, which achieves a more sufficient optimization of these upper bounds. Finally, we conduct extensive experiments on a public dataset and a real product dataset to verify the effectiveness of our DUB.

How to effectively mitigate the bias of feedback in recommender systems is an important research topic. In this article, we first describe the generation process of the biased and unbiased feedback in recommender systems via two respective causal diagrams, where the difference between them can be regarded as the source of system-induced biases. We then define this difference as a confounding bias and propose a new perspective on debiased representation learning to alleviate it. Specifically, for the case with biased feedback alone, we derive the conditions that need to be satisfied to obtain a debiased representation from the causal diagrams. Then, we propose a novel framework called debiased information bottleneck (DIB) to optimize these conditions and then find a tractable solution for it. The proposed framework constrains the model to learn a biased embedding vector with independent biased and unbiased components in the training phase, and uses only the unbiased component in the test phase to deliver more accurate recommendations. We further propose a variant of DIB by relaxing the independence between the biased and unbiased components. Finally, we conduct extensive experiments on a public dataset and a real product dataset to verify the effectiveness of the proposed framework.

Autoencoder-based methods have achieved significant performance on item recommendation. However, they may not perform well on tail items due to the ignorance of the items’ popularity bias. As a response, in this paper, we focus on tail items and propose a novel adversarial learning method for tail recommendation (ALTRec). In our ALTRec, the generator (i.e., AutoRec) not only reconstructs the input well, but also minimizes the (any two-user) similarity difference between the input stage and the output stage to keep users’ interaction relationships unchanged. And the discriminator maps the inputs and outputs of the generator to a same semantic space for scoring the similarity and maximizes the similarity difference as the target, and will identify some unsatisfactory predictions, especially on tail items. In order to preserve the similarity, the generator will pay more attention to the tail items compared with the previous autoencoder-based methods. An ablation study validates the effectiveness of preserving the two-user similarity, as well as the adversarial learning strategy in our ALTRec. Extensive experiments on three real-world datasets show that our ALTRec significantly boosts the performance on tail items compared with several state-of-the-art methods.

Most methods for context-aware recommendation focus on improving the feature interaction layer, but overlook the embedding layer. However, an embedding layer with random initialization often suffers in practice from the sparsity of the contextual features, as well as the interactions between the users (or items) and context. In this paper, we propose a novel user-event graph embedding learning (UEG-EL) framework to address these two sparsity challenges. Specifically, our UEG-EL contains three modules: 1) a graph construction module is used to obtain a user-event graph containing nodes for users, intents and items, where the intent nodes are generated by applying intent node attention (INA) on nodes of the contextual features; 2) a user-event collaborative graph convolution module is designed to obtain the refined embeddings of all features by executing a new convolution strategy on the user-event graph, where each intent node acts as a hub to efficiently propagate the information among different features; 3) a recommendation module is equipped to integrate some existing context-aware recommendation model, where the feature embeddings are directly initialized with the obtained refined embeddings. Moreover, we identify a unique challenge of the basic framework, that is, the contextual features associated with too many instances may suffer from noise when aggregating the information. We thus further propose a simple but effective variant, i.e., UEG-EL-V, in order to prune the information propagation of the contextual features. Finally, we conduct extensive experiments on three public datasets to verify the effectiveness and compatibility of our UEG-EL and its variant.

It is crucial to model missing ratings in recommender systems since user preferences learnt from only observed ratings are biased. One possible explanation for missing ratings is motivated by the spiral of silence theory. When the majority opinion is formed, a spiral process is triggered where users are more and more likely to show their ratings if they perceive that they are supported by the opinion climate. In this paper we first verify the existence of the spiral process in recommender systems by using a variety of different real-life datasets. We then study the characteristics of two key factors in the spiral process: opinion climate and the hardcore users who will give ratings even when they are minority opinion holders. Based on our empirical findings, we develop four variants to model missing ratings. They mimic different components of the spiral of silence based on the spiral process with global opinion climate, local opinion climate, hardcore users, relationships between hardcore users and items, respectively. We experimentally show that, the presented variants all outperform state-of-the-art recommendation models with missing rating components.

In a recommender system, a user’s interaction is often biased by the items’ displaying positions and popularity, as well as the user’s self-selection. Most existing recommendation models are built using such a biased user-system interaction data. In this paper, we first additionally introduce a specially collected unbiased data and then propose a novel transfer learning solution, i.e., transfer via joint reconstruction (TJR), to achieve knowledge transfer and sharing between the biased data and unbiased data. Specifically, in our TJR, we refine the prediction via the latent features containing bias information in order to obtain a more accurate and unbiased prediction. Moreover, we integrate the two data by reconstructing their interaction in a joint learning manner. We then adopt three representative methods as the backbone models of our TJR and conduct extensive empirical studies on two public datasets, showcasing the effectiveness of our transfer learning solution over some very competitive baselines.

How to effectively mitigate the bias of feedback in recommender systems is an important research topic. In this paper, we first describe the generation process of the biased and unbiased feedback in recommender systems via two respective causal diagrams, where the difference between them can be regarded as the source of bias. We then define this difference as a confounding bias, which can be regarded as a collection of some specific biases that have previously been studied. For the case with biased feedback alone, we derive the conditions that need to be satisfied to obtain a debiased representation from the causal diagrams. Based on information theory, we propose a novel method called debiased information bottleneck (DIB) to optimize these conditions and then find a tractable solution for it. In particular, the proposed method constrains the model to learn a biased embedding vector with independent biased and unbiased components in the training phase, and uses only the unbiased component in the test phase to deliver more accurate recommendations. Finally, we conduct extensive experiments on a public dataset and a real product dataset to verify the effectiveness of the proposed method and discuss its properties.

Recommender systems are feedback loop systems, which often face bias problems such as popularity bias, previous model bias and position bias. In this paper, we focus on solving the bias problems in a recommender system via a uniform data. Through empirical studies in online and offline settings, we observe that simple modeling with a uniform data can alleviate the bias problems and improve the performance. However, the uniform data is always few and expensive to collect in a real product. In order to use the valuable uniform data more effectively, we propose a general knowledge distillation framework for counterfactual recommendation that enables uniform data modeling through four approaches: (1) label-based distillation focuses on using the imputed labels as a carrier to provide useful de-biasing guidance; (2) feature-based distillation aims to filter out the representative causal and stable features; (3) sample-based distillation considers mutual learning and alignment of the information of the uniform and non-uniform data; and (4) model structure-based distillation constrains the training of the models from the perspective of embedded representation. We conduct extensive experiments on both public and product datasets, demonstrating that the proposed four methods achieve better performance over the baseline models in terms of AUC and NLL. Moreover, we discuss the relation between the proposed methods and the previous works. We emphasize that counterfactual modeling with uniform data is a rich research area, and list some interesting and promising research topics worthy of further exploration. Note that the source codes are available at \urlhttps://github.com/dgliu/SIGIR20_KDCRec.

It has been established that, ratings are missing not at random in recommender systems. However, little research has been done to reveal how the ratings are missing. In this paper we present one possible explanation of the missing not at random phenomenon. We verify that, using a variety of different real-life datasets, there is a spiral process for a silent minority in recommender systems where (1) people whose opinions fall into the minority are less likely to give ratings than majority opinion holders; (2) as the majority opinion becomes more dominant, the rating possibility of a majority opinion holder is intensifying but the rating possibility of a minority opinion holder is shrinking; (3) only hardcore users remain to rate for minority opinions when the spiral achieves its steady state. Our empirical findings are beneficial for future recommendation models. To demonstrate the impact of our empirical findings, we present a probabilistic model that mimics the generation process of spiral of silence. We experimentally show that, the presented model offers more accurate recommendations, compared with state-of-the-art recommendation models.