Click-Through Rate (CTR) prediction models are integral to a myriad of industrial settings, such as personalized search advertising. Current methods typically involve feature extraction from users' historical behavior sequences combined with product information, feeding into a discriminative model that is trained on user feedback to estimate CTR. With the success of models such as GPT, the potential for generative models to enrich expressive power beyond discriminative models has become apparent. In light of this, we introduce a novel model that leverages generative models to enhance the precision of CTR predictions in discriminative models. To reconcile the disparate data aggregation needs of both model types, we design a two-stage training process: 1) Generative pre-training for next-item prediction with the given item category in user behavior sequences; 2) Fine-tuning the well-trained generative model within a discriminative CTR prediction framework. Our method's efficacy is substantiated through extensive experiments on a new dataset, and its significant utility is further corroborated by online A/B testing results. Currently, the model is deployed on one of the world's largest e-commerce platforms, and we intend to release the associated code and dataset in the future.
Cross-domain Click-Through Rate prediction aims to tackle the data sparsity and the cold start problems in online advertising systems by transferring knowledge from source domains to a target domain. Most existing methods rely on overlapping users to facilitate this transfer, often focusing on joint training or pre-training with fine-tuning approach to connect the source and target domains. However, in real-world industrial settings, joint training struggles to learn optimal representations with different distributions, and pre-training with fine-tuning is not well-suited for continuously integrating new data. To address these issues, we propose GIST, a cross-domain lifelong sequence model that decouples the training processes of the source and target domains. Unlike previous methods that search lifelong sequences in the source domains using only content or behavior signals or their simple combinations, we innovatively introduce a Content-Behavior Joint Training Module (CBJT), which aligns content-behavior distributions and combines them with guided information to facilitate a more stable representation. Furthermore, we develop an Asymmetric Similarity Integration strategy (ASI) to augment knowledge transfer through similarity computation. Extensive experiments demonstrate the effectiveness of GIST, surpassing SOTA methods on offline evaluations and an online A/B test. Deployed on the Xiaohongshu (RedNote) platform, GIST effectively enhances online ads system performance at scale, serving hundreds of millions of daily active users.
Spotify, a large-scale multimedia platform, attracts over 675 million monthly active users who collectively consume millions of hours of music, podcasts, audiobooks, and video content. This diverse content consumption pattern introduces unique challenges for computational advertising, which must effectively integrate a variety of ad modalities, including audio, video, and display, within a single user experience. Traditional ad recommendation models, primarily designed for foregrounded experiences, often struggle to reconcile the platform's inherent audio-centrality with the demands of optimizing ad performance across multiple formats and modalities. To overcome these challenges, we introduce Cross-modal Adaptive Mixture-of-Experts (CAMoE), a novel framework for optimizing click-through rate (CTR) prediction in both audio-centric and multi-modal settings. CAMoE enhances traditional mixture-of-experts models by incorporating modality-aware task grouping, adaptive loss masking, and deep-cross networks (DCN) to capture complex feature interactions within a multi-modal ad ecosystem. Through extensive ablation studies, we demonstrate that this approach achieves near Pareto-optimal performance across audio, video, and display ad formats, significantly improving AUC-PR compared to conventional single-task and content-based multi-task learning baselines. When deployed at scale on Spotify's ad serving platform, CAMoE delivered substantial gains, yielding a 14.5% increase in CTR for audio ads, a 1.3% increase for video ads, and a 4.8% reduction in expected cost-per-click (eCPC) for audio slots.
Personalized recommendation systems must adapt to user interactions across different domains. Traditional approaches like MLoRA apply a single adaptation per domain but lack flexibility in handling diverse user behaviors. To address this, we propose MoE-MLoRA, a mixture-of-experts framework where each expert is first trained independently to specialize in its domain before a gating network is trained to weight their contributions dynamically. We evaluate MoE-MLoRA across eight CTR models on Movielens and Taobao, showing that it improves performance in large-scale, dynamic datasets (+1.45 Weighed-AUC in Taobao-20) but offers limited benefits in structured datasets with low domain diversity and sparsity. Further analysis of the number of experts per domain reveals that larger ensembles do not always improve performance, indicating the need for model-aware tuning. Our findings highlight the potential of expert-based architectures for multi-domain recommendation systems, demonstrating that task-aware specialization and adaptive gating can enhance predictive accuracy in complex environments. The implementation and code are available in our GitHub repository.
Predicting Click-Through Rates is a crucial function within recommendation and advertising platforms, as the output of CTR prediction determines the order of items shown to users. The Embedding \& MLP paradigm has become a standard approach for industrial recommendation systems and has been widely deployed. However, this paradigm suffers from cold-start problems, where there is either no or only limited user action data available, leading to poorly learned ID embeddings. The cold-start problem hampers the performance of new items. To address this problem, we designed a novel diffusion model to generate a warmed-up embedding for new items. Specifically, we define a novel diffusion process between the ID embedding space and the side information space. In addition, we can derive a sub-sequence from the diffusion steps to expedite training, given that our diffusion model is non-Markovian. Our diffusion model is supervised by both the variational inference and binary cross-entropy objectives, enabling it to generate warmed-up embeddings for items in both the cold-start and warm-up phases. Additionally, we have conducted extensive experiments on three recommendation datasets. The results confirmed the effectiveness of our approach.
Hadamard Product (HP) has long been a cornerstone in click-through rate (CTR) prediction tasks due to its simplicity, effectiveness, and ability to capture feature interactions without additional parameters. However, the underlying reasons for its effectiveness remain unclear. In this paper, we revisit HP from the perspective of Quadratic Neural Networks (QNN), which leverage quadratic interaction terms to model complex feature relationships. We further reveal QNN's ability to expand the feature space and provide smooth nonlinear approximations without relying on activation functions. Meanwhile, we find that traditional post-activation does not further improve the performance of the QNN. Instead, mid-activation is a more suitable alternative. Through theoretical analysis and empirical evaluation of 25 QNN neuron formats, we identify a good-performing variant and make further enhancements on it. Specifically, we propose the Multi-Head Khatri-Rao Product as a superior alternative to HP and a Self-Ensemble Loss with dynamic ensemble capability within the same network to enhance computational efficiency and performance. Ultimately, we propose a novel neuron format, QNN-alpha, which is tailored for CTR prediction tasks. Experimental results show that QNN-alpha achieves new state-of-the-art performance on six public datasets while maintaining low inference latency, good scalability, and excellent compatibility. The code, running logs, and detailed hyperparameter configurations are available at: https://github.com/salmon1802/QNN.
Click-through rate (CTR) prediction is a critical task in online advertising and recommender systems, relying on effective modeling of feature interactions. Explicit interactions capture predefined relationships, such as inner products, but often suffer from data sparsity, while implicit interactions excel at learning complex patterns through non-linear transformations but lack inductive biases for efficient low-order modeling. Existing two-stream architectures integrate these paradigms but face challenges such as limited information sharing, gradient imbalance, and difficulty preserving low-order signals in sparse CTR data. We propose a novel framework, Dynamic Low-Order-Aware Fusion (DLF), which addresses these limitations through two key components: a Residual-Aware Low-Order Interaction Network (RLI) and a Network-Aware Attention Fusion Module (NAF). RLI explicitly preserves low-order signals while mitigating redundancy from residual connections, and NAF dynamically integrates explicit and implicit representations at each layer, enhancing information sharing and alleviating gradient imbalance. Together, these innovations balance low-order and high-order interactions, improving model expressiveness. Extensive experiments on public datasets demonstrate that DLF achieves state-of-the-art performance in CTR prediction, addressing key limitations of existing models. The implementation is publicly available at https://github.com/USTC-StarTeam/DLF.
Click-through rate (CTR) prediction is a fundamental task in modern recommender systems. In recent years, the integration of large language models (LLMs) has been shown to effectively enhance the performance of traditional CTR methods. However, existing LLM-enhanced methods often require extensive processing of detailed textual descriptions for large-scale instances or user/item entities, leading to substantial computational overhead. To address this challenge, this work introduces LLaCTR, a novel and lightweight LLM-enhanced CTR method that employs a field-level enhancement paradigm. Specifically, LLaCTR first utilizes LLMs to distill crucial and lightweight semantic knowledge from small-scale feature fields through self-supervised field-feature fine-tuning. Subsequently, it leverages this field-level semantic knowledge to enhance both feature representation and feature interactions. In our experiments, we integrate LLaCTR with six representative CTR models across four datasets, demonstrating its superior performance in terms of both effectiveness and efficiency compared to existing LLM-enhanced methods. Our code is available at https://anonymous.4open.science/r/LLaCTR-EC46.
Click-through Rate (CTR) prediction in real-world recommender systems often deals with billions of user interactions every day. To improve the training efficiency, it is common to update the CTR prediction model incrementally using the new incremental data and a subset of historical data. However, the feature embeddings of a CTR prediction model often get stale when the corresponding features do not appear in current incremental data. In the next period, the model would have a performance degradation on samples containing stale features, which we call the feature staleness problem. To mitigate this problem, we propose a Feature Staleness Aware Incremental Learning method for CTR prediction (FeSAIL) which adaptively replays samples containing stale features. We first introduce a staleness aware sampling algorithm (SAS) to sample a fixed number of stale samples with high sampling efficiency. We then introduce a staleness aware regularization mechanism (SAR) for a fine-grained control of the feature embedding updating. We instantiate FeSAIL with a general deep learning-based CTR prediction model and the experimental results demonstrate FeSAIL outperforms various state-of-the-art methods on four benchmark datasets.
With the rapid advancement of Multimodal Large Language Models (MLLMs), an increasing number of researchers are exploring their application in recommendation systems. However, the high latency associated with large models presents a significant challenge for such use cases. The EReL@MIR workshop provided a valuable opportunity to experiment with various approaches aimed at improving the efficiency of multimodal representation learning for information retrieval tasks. As part of the competition's requirements, participants were mandated to submit a technical report detailing their methodologies and findings. Our team was honored to receive the award for Task 2 - Winner (Multimodal CTR Prediction). In this technical report, we present our methods and key findings. Additionally, we propose several directions for future work, particularly focusing on how to effectively integrate recommendation signals into multimodal representations. The codebase for our implementation is publicly available at: https://github.com/Lattice-zjj/MMCTR_Code, and the trained model weights can be accessed at: https://huggingface.co/FireFlyCourageous/MMCTR_DIN_MicroLens_1M_x1.
Multimodal click-through rate (CTR) prediction is a key technique in industrial recommender systems. It leverages heterogeneous modalities such as text, images, and behavioral logs to capture high-order feature interactions between users and items, thereby enhancing the system's understanding of user interests and its ability to predict click behavior. The primary challenge in this field lies in effectively utilizing the rich semantic information from multiple modalities while satisfying the low-latency requirements of online inference in real-world applications. To foster progress in this area, the Multimodal CTR Prediction Challenge Track of the WWW 2025 EReL@MIR Workshop formulates the problem into two tasks: (1) Task 1 of Multimodal Item Embedding: this task aims to explore multimodal information extraction and item representation learning methods that enhance recommendation tasks; and (2) Task 2 of Multimodal CTR Prediction: this task aims to explore what multimodal recommendation model can effectively leverage multimodal embedding features and achieve better performance. In this paper, we propose a novel model for Task 2, named Quadratic Interest Network (QIN) for Multimodal CTR Prediction. Specifically, QIN employs adaptive sparse target attention to extract multimodal user behavior features, and leverages Quadratic Neural Networks to capture high-order feature interactions. As a result, QIN achieved an AUC of 0.9798 on the leaderboard and ranked second in the competition. The model code, training logs, hyperparameter configurations, and checkpoints are available at https://github.com/salmon1802/QIN.
The WWW 2025 EReL@MIR Workshop Multimodal CTR Prediction Challenge focuses on effectively applying multimodal embedding features to improve click-through rate (CTR) prediction in recommender systems. This technical report presents our 1$^{st}$ place winning solution for Task 2, combining sequential modeling and feature interaction learning to effectively capture user-item interactions. For multimodal information integration, we simply append the frozen multimodal embeddings to each item embedding. Experiments on the challenge dataset demonstrate the effectiveness of our method, achieving superior performance with a 0.9839 AUC on the leaderboard, much higher than the baseline model. Code and configuration are available in our GitHub repository and the checkpoint of our model can be found in HuggingFace.
The predictions of click through rate (CTR) and conversion rate (CVR) play a crucial role in the success of ad-recommendation systems. A Deep Hierarchical Ensemble Network (DHEN) has been proposed to integrate multiple feature crossing modules and has achieved great success in CTR prediction. However, its performance for CVR prediction is unclear in the conversion ads setting, where an ad bids for the probability of a user's off-site actions on a third party website or app, including purchase, add to cart, sign up, etc. A few challenges in DHEN: 1) What feature-crossing modules (MLP, DCN, Transformer, to name a few) should be included in DHEN? 2) How deep and wide should DHEN be to achieve the best trade-off between efficiency and efficacy? 3) What hyper-parameters to choose in each feature-crossing module? Orthogonal to the model architecture, the input personalization features also significantly impact model performance with a high degree of freedom. In this paper, we attack this problem and present our contributions biased to the applied data science side, including: First, we propose a multitask learning framework with DHEN as the single backbone model architecture to predict all CVR tasks, with a detailed study on how to make DHEN work effectively in practice; Second, we build both on-site real-time user behavior sequences and off-site conversion event sequences for CVR prediction purposes, and conduct ablation study on its importance; Last but not least, we propose a self-supervised auxiliary loss to predict future actions in the input sequence, to help resolve the label sparseness issue in CVR prediction. Our method achieves state-of-the-art performance compared to previous single feature crossing modules with pre-trained user personalization features.
In modern social media, recommender systems (RecSys) rely on the click-through rate (CTR) as the standard metric to evaluate user engagement. CTR prediction is traditionally framed as a binary classification task to predict whether a user will interact with a given item. However, this approach overlooks the complexity of real-world social modeling, where the user, item, and their interactive features change dynamically in fast-paced online environments. This dynamic nature often leads to model instability, reflected in overfitting short-term fluctuations rather than higher-level interactive patterns. While overfitting calls for more scaled and refined supervisions, current solutions often rely on binary labels that overly simplify fine-grained user preferences through the thresholding process, which significantly reduces the richness of the supervision. Therefore, we aim to alleviate the overfitting problem by increasing the supervision bandwidth in CTR training. Specifically, (i) theoretically, we formulate the impact of fine-grained preferences on model stability as a Lipschitz constrain; (ii) empirically, we discover that scaling the supervision bandwidth can act as an implicit Lipschitz regularizer, stably optimizing existing CTR models to achieve better generalizability. Extensive experiments show that this scaled supervision significantly and consistently improves the optimization process and the performance of existing CTR models, even without the need for additional hyperparameter tuning.
Accurately predicting click-through rates (CTR) under stringent privacy constraints poses profound challenges, particularly when user-item interactions are sparse and fragmented across domains. Conventional cross-domain CTR (CCTR) methods frequently assume homogeneous feature spaces and rely on centralized data sharing, neglecting complex inter-domain discrepancies and the subtle trade-offs imposed by privacy-preserving protocols. Here, we present Federated Cross-Domain CTR Prediction with Large Language Model Augmentation (FedCCTR-LM), a federated framework engineered to address these limitations by synchronizing data augmentation, representation disentanglement, and adaptive privacy protection. Our approach integrates three core innovations. First, the Privacy-Preserving Augmentation Network (PrivAugNet) employs large language models to enrich user and item representations and expand interaction sequences, mitigating data sparsity and feature incompleteness. Second, the Independent Domain-Specific Transformer with Contrastive Learning (IDST-CL) module disentangles domain-specific and shared user preferences, employing intra-domain representation alignment (IDRA) and crossdomain representation disentanglement (CDRD) to refine the learned embeddings and enhance knowledge transfer across domains. Finally, the Adaptive Local Differential Privacy (AdaLDP) mechanism dynamically calibrates noise injection to achieve an optimal balance between rigorous privacy guarantees and predictive accuracy. Empirical evaluations on four real-world datasets demonstrate that FedCCTR-LM substantially outperforms existing baselines, offering robust, privacy-preserving, and generalizable cross-domain CTR prediction in heterogeneous, federated environments.
The two primary tasks in the search recommendation system are search relevance matching and click-through rate (CTR) prediction -- the former focuses on seeking relevant items for user queries whereas the latter forecasts which item may better match user interest. Prior research typically develops two models to predict the CTR and search relevance separately, then ranking candidate items based on the fusion of the two outputs. However, such a divide-and-conquer paradigm creates the inconsistency between different models. Meanwhile, the search relevance model mainly concentrates on the degree of objective text matching while neglecting personalized differences among different users, leading to restricted model performance. To tackle these issues, we propose a unified Personalized Search RElevance Matching and CTR Prediction Fusion Model(PRECTR). Specifically, based on the conditional probability fusion mechanism, PRECTR integrates the CTR prediction and search relevance matching into one framework to enhance the interaction and consistency of the two modules. However, directly optimizing CTR binary classification loss may bring challenges to the fusion model's convergence and indefinitely promote the exposure of items with high CTR, regardless of their search relevance. Hence, we further introduce two-stage training and semantic consistency regularization to accelerate the model's convergence and restrain the recommendation of irrelevant items. Finally, acknowledging that different users may have varied relevance preferences, we assessed current users' relevance preferences by analyzing past users' preferences for similar queries and tailored incentives for different candidate items accordingly. Extensive experimental results on our production dataset and online A/B testing demonstrate the effectiveness and superiority of our proposed PRECTR method.
The Transformer has proven to be a significant approach in feature interaction for CTR prediction, achieving considerable success in previous works. However, it also presents potential challenges in handling feature interactions. Firstly, Transformers may encounter information loss when capturing feature interactions. By relying on inner products to represent pairwise relationships, they compress raw interaction information, which can result in a degradation of fidelity. Secondly, due to the long-tail features distribution, feature fields with low information-abundance embeddings constrain the information abundance of other fields, leading to collapsed embedding matrices. To tackle these issues, we propose a Dual Attention Framework for Enhanced Feature Interaction, known as Dual Enhanced Attention. This framework integrates two attention mechanisms: the Combo-ID attention mechanism and the collapse-avoiding attention mechanism. The Combo-ID attention mechanism directly retains feature interaction pairs to mitigate information loss, while the collapse-avoiding attention mechanism adaptively filters out low information-abundance interaction pairs to prevent interaction collapse. Extensive experiments conducted on industrial datasets have shown the effectiveness of Dual Enhanced Attention.
In recent years, integrating large language models (LLMs) into recommender systems has created new opportunities for improving recommendation quality. However, a comprehensive benchmark is needed to thoroughly evaluate and compare the recommendation capabilities of LLMs with traditional recommender systems. In this paper, we introduce RecBench, which systematically investigates various item representation forms (including unique identifier, text, semantic embedding, and semantic identifier) and evaluates two primary recommendation tasks, i.e., click-through rate prediction (CTR) and sequential recommendation (SeqRec). Our extensive experiments cover up to 17 large models and are conducted across five diverse datasets from fashion, news, video, books, and music domains. Our findings indicate that LLM-based recommenders outperform conventional recommenders, achieving up to a 5% AUC improvement in the CTR scenario and up to a 170% NDCG@10 improvement in the SeqRec scenario. However, these substantial performance gains come at the expense of significantly reduced inference efficiency, rendering the LLM-as-RS paradigm impractical for real-time recommendation environments. We aim for our findings to inspire future research, including recommendation-specific model acceleration methods. We will release our code, data, configurations, and platform to enable other researchers to reproduce and build upon our experimental results.
With the rapid growth of user historical behavior data, user interest modeling has become a prominent aspect in Click-Through Rate (CTR) prediction, focusing on learning user intent representations. However, this complexity poses computational challenges, requiring a balance between model performance and acceptable response times for online services. Traditional methods often utilize filtering techniques. These techniques can lead to the loss of significant information by prioritizing top K items based on item attributes or employing low-precision attention mechanisms. In this study, we introduce LREA, a novel attention mechanism that overcomes the limitations of existing approaches while ensuring computational efficiency. LREA leverages low-rank matrix decomposition to optimize runtime performance and incorporates a specially designed loss function to maintain attention capabilities while preserving information integrity. During the inference phase, matrix absorption and pre-storage strategies are employed to effectively meet runtime constraints. The results of extensive offline and online experiments demonstrate that our method outperforms state-of-the-art approaches.
Large Language Models (LLMs) have demonstrated tremendous potential as the next-generation ranking-based recommendation system. Many recent works have shown that LLMs can significantly outperform conventional click-through-rate (CTR) prediction approaches. Despite such promising results, the computational inefficiency inherent in the current training paradigm makes it particularly challenging to train LLMs for ranking-based recommendation tasks on large datasets. To train LLMs for CTR prediction, most existing studies adopt the prevalent ''sliding-window'' paradigm. Given a sequence of $m$ user interactions, a unique training prompt is constructed for each interaction by designating it as the prediction target along with its preceding $n$ interactions serving as context. In turn, the sliding-window paradigm results in an overall complexity of $O(mn^2)$ that scales linearly with the length of user interactions. Consequently, a direct adoption to train LLMs with such strategy can result in prohibitively high training costs as the length of interactions grows. To alleviate the computational inefficiency, we propose a novel training paradigm, namely Dynamic Target Isolation (DTI), that structurally parallelizes the training of $k$ (where $k >> 1$) target interactions. Furthermore, we identify two major bottlenecks - hidden-state leakage and positional bias overfitting - that limit DTI to only scale up to a small value of $k$ (e.g., 5) then propose a computationally light solution to effectively tackle each. Through extensive experiments on three widely adopted public CTR datasets, we empirically show that DTI reduces training time by an average of $\textbf{92%}$ (e.g., from $70.5$ hrs to $5.31$ hrs), without compromising CTR prediction performance.