arXiv subjects

Yulei Huang

Publications and source records attributed to Yulei Huang.

4 recordsLinked to original sources

arXiv2026

RCLRec: Reverse Curriculum Learning for Modeling Sparse Conversions in Generative Recommendation

Conversion objectives in large-scale recommender systems are sparse, making them difficult to optimize. Generative recommendation (GR) partially alleviates data sparsity by organizing multi-type behaviors into a unified token sequence with shared representations, but conversion signals remain insufficiently modeled. While recent behavior-aware GR models encode behavior types and employ behavior-aware attention to highlight decision-related intermediate behaviors, they still rely on standard attention over the full history and provide no additional supervision for conversions, leaving conversion sparsity largely unresolved. To address these challenges, we propose RCLRec, a reverse curriculum learning-based GR framework for sparse conversion supervision. For each conversion target, RCLRec constructs a short curriculum by selecting a subsequence of conversion-related items from the history in reverse. Their semantic tokens are fed to the decoder as a prefix, together with the target conversion tokens, under a joint generation objective. This design provides additional instance-specific intermediate supervision, alleviating conversion sparsity and focusing the model on the user's critical decision process. We further introduce a curriculum quality-aware loss to ensure that the selected curricula are informative for conversion prediction. Experiments on offline datasets and an online A/B test show that RCLRec achieves superior performance, with +2.09% advertising revenue and +1.86% orders in online deployment.

cs.IR↗

arXiv2025

HeterRec: Heterogeneous Information Transformer for Scalable Sequential Recommendation

Transformer-based sequential recommendation (TSR) models have shown superior performance in recommendation systems, where the quality of item representations plays a crucial role. Classical representation methods integrate item features using concatenation or neural networks to generate homogeneous representation sequences. While straightforward, these methods overlook the heterogeneity of item features, limiting the transformer's ability to capture fine-grained patterns and restricting scalability. Recent studies have attempted to integrate user-side heterogeneous features into item representation sequences, but item-side heterogeneous features, which are vital for performance, remain excluded. To address these challenges, we propose a Heterogeneous Information Transformer model for Sequential Recommendation (HeterRec), which incorporates Heterogeneous Token Flatten Layer (HTFL) and Hierarchical Causal Transformer Layer (HCT). Our HTFL is a novel item tokenization method that converts items into a heterogeneous token set and organizes these tokens into heterogeneous sequences, effectively enhancing performance gains when scaling up the model. Moreover, HCT introduces token-level and item-level causal transformers to extract fine-grained patterns from the heterogeneous sequences. Additionally, we design a Listwise Multi-step Prediction (LMP) Loss function to further improve performance. Extensive experiments on both offline and online datasets show that the HeterRec model achieves superior performance.

cs.IR↗

arXiv2022

Measuring Quantum Entanglement from Local Information by Machine Learning

Entanglement is a key property in the development of quantum technologies and in the study of quantum many-body simulations. However, entanglement measurement typically requires quantum full-state tomography (FST). Here we present a neural network-assisted protocol for measuring entanglement in equilibrium and non-equilibrium states of local Hamiltonians. Instead of FST, it can learn comprehensive entanglement quantities from single-qubit or two-qubit Pauli measurements, such as Rényi entropy, partially-transposed (PT) moments, and coherence. It is also exciting that our neural network is able to learn the future entanglement dynamics using only single-qubit traces from the previous time. In addition, we perform experiments using a nuclear spin quantum processor and train an adoptive neural network to study entanglement in the ground and dynamical states of a one-dimensional spin chain. Quantum phase transitions (QPT) are revealed by measuring static entanglement in ground states, and the entanglement dynamics beyond measurement time is accurately estimated in dynamical states. These precise results validate our neural network. Our work will have a wide range of applications in quantum many-body systems, from quantum phase transitions to intriguing non-equilibrium phenomena such as quantum thermalization.

quant-ph↗

arXiv2020

Learning Quantum Hamiltonians from Single-qubit Measurements

It is natural to measure the observables from the Hamiltonian-based quantum dynamics, and its inverse process that Hamiltonians are estimated from the measured data also is a vital topic. In this work, we propose a recurrent neural network to learn the parameters of the target Hamiltonians from the temporal records of single-qubit measurements. The method does not require the assumption of ground states and only measures single-qubit observables. It is applicable on both time-independent and time-dependent Hamiltonians and can simultaneously capture the magnitude and sign of Hamiltonian parameters. Taking quantum Ising Hamiltonians with the nearest-neighbor interactions as examples, we trained our recurrent neural networks to learn the Hamiltonian parameters with high accuracy, including the magnetic fields and coupling values. The numerical study also shows that our method has good robustness against the measurement noise and decoherence effect. Therefore, it has widespread applications in estimating the parameters of quantum devices and characterizing the Hamiltonian-based quantum dynamics.

quant-ph↗