Multi-Domain Multi-Task (MDMT) recommendation aims to provide personalized recommendations by leveraging information across multiple domains and tasks. However, existing methods often suffer from spurious correlations between irrelevant features and the target, leading to negative transfer. To address this, we propose a Stable and Adaptive Fusion (SAF) framework for MDMT recommendation. SAF introduces a weighted Hilbert-Schmidt Independence Criterion (HSIC) loss to decorrelate irrelevant features from the target, learning sample weights that promote stable (i.e., robust to spurious correlations) representations in both bottom and expert layers. We employ Random Fourier Features (RFF) to enable scalable computation of the HSIC loss. We further employ adaptive feature and expert gating to select these stable features, enabling the model to capture intricate cross-domain and cross-task dependencies. The learned sample weights are also used to reweight the MDMT loss during training. Experiments on large-scale datasets show that SAF outperforms state-of-the-art baselines by up to 2% in AUC. To facilitate further research, we release a new industrial dataset with 30 million interactions across 3 domains and 2 tasks, with 300 features.

Cold-start remains a fundamental challenge in recommendation systems due to the scarcity of interaction data. Recent methods address this issue by leveraging semantic ID embeddings and cross-domain transfer techniques, achieving notable progress. However, the common practice of learning semantic ID embeddings and training the recommendation model in separate stages hinders the generalization capability of semantic IDs throughout the training process. In this work, we propose Sharpness-Consistent Cross-Domain Recommendation (SC2 Rec), a novel framework designed to enhance the generalization of semantic ID-based models in cold-start scenarios. SC2 Rec alternately optimizes the sharpness of the loss landscape and enforces landscape consistency between warm and cold domains, leading to unified and flatter minima and improved generalization. Extensive experiments on industrial datasets demonstrate the effectiveness of SC2 Rec. Furthermore, we release a high-quality dataset to facilitate further research in this area.

In recommender systems, accurate post-click conversion rate (CVR) estimation is crucial for a company’s revenue growth. Currently, multi-task causal methods—such as multi-task doubly robust learning—improve CVR estimation by reducing bias and variance during training. However, these methods often overlook the impact of hard-to-classify samples, which deviate significantly from the sample cluster center and substantially increase the bias and variance of multi-task causal approaches. To address this limitation, we propose a novel inverse contrastive representation learning guided causal multi-task framework. Specifically, we first select clicked and unclicked samples that deviate significantly from their respective cluster centers to form negative pairs. We then apply inverse contrastive representation learning (ICRL) to pull these negative pairs closer together, encouraging deviated clicked samples to move closer to the clicked cluster center, and vice versa. This approach yields a more accurate and lower-variance inverse propensity score for the CVR estimator. Additionally, we compute the ICRL loss segmentally to reduce computational resource consumption. We conduct extensive experiments on six large-scale datasets, as well as online A/B tests on our advertising platform. Our method achieves a 2.9% improvement on offline datasets compared to state-of-the-art baselines, and a 0.6% increase over the online production model.

In recommender systems, post-click conversion rate (CVR) estimation is an essential task to model user preferences for items and estimate the value of recommendations. Sample selection bias (SSB) and data sparsity (DS) are two persistent challenges for post-click conversion rate (CVR) estimation. Currently, entire-space approaches that exploit unclicked samples through knowledge distillation are promising to mitigate SSB and DS simultaneously. Existing methods use non-conversion, conversion, or adaptive conversion predictors to generate pseudo labels for unclicked samples. However, they fail to consider the unbiasedness and information limitations of these pseudo labels. Motivated by such analysis, we propose an entire-space variational information exploitation framework (EVI) for CVR prediction. First, EVI uses a conditional entire-space CVR teacher to generate unbiased pseudo labels. Then, it applies variational information exploitation and logit distillation to transfer non-click space information to the target CVR estimator. We conduct extensive offline experiments on six large-scale datasets. EVI demonstrated a 2.25% average improvement compared to the state-of-the-art baselines.