Industrial large-scale recommendation models (LRMs) face the challenge of jointly modeling long-range user behavior sequences and heterogeneous non-sequential features under strict efficiency constraints. However, most existing architectures employ a decoupled pipeline: long sequences are first compressed with a query-token based sequence compressor like LONGER, followed by fusion with dense features through token-mixing modules like RankMixer, which thereby limits both the representation capacity and the interaction flexibility. This paper presents HyFormer, a unified hybrid transformer architecture that tightly integrates long-sequence modeling and feature interaction into a single backbone. From the perspective of sequence modeling, we revisit and redesign query tokens in LRMs, and frame the LRM modeling task as an alternating optimization process that integrates two core components: Query Decoding which expands non-sequential features into Global Tokens and performs long sequence decoding over layer-wise key-value representations of long behavioral sequences; and Query Boosting which enhances cross-query and cross-sequence heterogeneous interactions via efficient token mixing. The two complementary mechanisms are performed iteratively to refine semantic representations across layers. Extensive experiments on billion-scale industrial datasets demonstrate that HyFormer consistently outperforms strong LONGER and RankMixer baselines under comparable parameter and FLOPs budgets, while exhibiting superior scaling behavior with increasing parameters and FLOPs. Large-scale online A/B tests in high-traffic production systems further validate its effectiveness, showing significant gains over deployed state-of-the-art models. These results highlight the practicality and scalability of HyFormer as a unified modeling framework for industrial LRMs.

Fairness has become a crucial aspect in the development of trustworthy machine learning algorithms. Current fairness metrics to measure the violation of demographic parity have the following drawbacks: (i) the average difference of model predictions on two groups cannot reflect their distribution disparity, and (ii) the overall calculation along all possible predictions conceals the extreme local disparity at or around certain predictions. In this work, we propose a novel fairness metric called Maximal Cumulative ratio Disparity along varying Predictions’ neighborhood (MCDP), for measuring the maximal local disparity of the fairness-aware classifiers. To accurately and efficiently calculate the MCDP, we develop a provably exact and an approximate calculation algorithm that greatly reduces the computational complexity with low estimation error. We further propose a bi-level optimization algorithm using a differentiable approximation of the MCDP for improving the algorithmic fairness. Extensive experiments on both tabular and image datasets validate that our fair training algorithm can achieve superior fairness-accuracy trade-offs.

Item-side group fairness (IGF) requires a recommendation model to treat different item groups similarly, and has a crucial impact on information diffusion, consumption activity, and market equilibrium. Previous IGF notions only focus on the direct utility of the item exposures, i.e., the exposure numbers across different item groups. Nevertheless, the item exposures also facilitate utility gained from the neighboring users via social influence, called social utility, such as information sharing on the social media. To fill this gap, this paper introduces two social attribute-aware IGF metrics, which require similar user social attributes on the exposed items across the different item groups. In light of the trade-off between the direct utility and social utility, we formulate a new multi-objective optimization problem for training recommender models with flexible trade-off while ensuring controllable accuracy. To solve this problem, we develop a gradient-based optimization algorithm and theoretically show that the proposed algorithm can find Pareto optimal solutions with varying trade-off and guaranteed accuracy. Extensive experiments on two real-world datasets validate the effectiveness of our approach.

Most recommender systems evaluate model performance offline through either: 1) normal biased test on factual interactions; or 2) debiased test with records from the randomized controlled trial. In fact, both tests only reflect part of the whole picture: factual interactions are collected from the recommendation policy, fitting them better implies benefiting the platform with higher click or conversion rate; in contrast, debiased test eliminates system-induced biases and thus is more reflective of user true preference. Nevertheless, we find that existing models exhibit trade-off on the two tests, and there lacks methods that perform well on both tests.