arXiv subjects

Xiaoshuang Chen

Publications and source records attributed to Xiaoshuang Chen.

At least 19 recordsLinked to original sources

arXiv2026

UniRec: Cross-stage Multi-Task Fusion with Preference Alignment for Cascaded Recommender Systems

Industrial recommender systems cascade stages with different objectives, feature spaces, and latency constraints. Optimizing pre-ranking and ranking separately induces cross-stage inconsistency: upstream models may filter out items preferred by downstream rankers, while independently tuned downstream fusion can offset upstream improvements. Most existing multi-task fusion methods target the ranking stage alone, and cross-stage methods often align with a downstream-derived score, leaving joint optimization of fusion modules across cascaded stages largely unexplored. We propose UniRec, a Unified Cross-stage Recommendation Fusion model. First, the two fusion agents partially share input embeddings in a single computation graph, allowing gradients from either stage to propagate through the shared representations. Second, a dual-axis preference alignment objective coordinates the two stages: horizontally, a compact aggregation term reorganizes dozens of pairwise objectives over heterogeneous prior signals into bidirectional preference evidence; vertically, a cross-stage consistency term transfers downstream pairwise preferences to the upstream fusion score. Third, we introduce attribute group-relative regularization, which computes relative advantages and normalizes policy updates within each attribute group, ensuring that uniformly promoting all items in a high-reward group provides no additional optimization gain. Offline experiments demonstrate UniRec consistently outperforms single-stage fusion and cross-stage coordination baselines; online A/B experiments show a 0.616% gain in app usage duration. UniRec has been fully deployed on the Kuaishou platform.

cs.IR↗

arXiv2026

Once Generated, Ranked: End-to-End Generative Slate Recommendation with Unified Semantic-Collaborative IDs

Slate recommendation treats a slate rather than an individual item as the recommendation unit, requiring joint optimization of item interactions and slate utility. Existing approaches typically separate candidate generation from ranking and restrict optimization to retrieved candidates. Generative recommendation with Semantic IDs (SIDs) offers a path to end-to-end recommendation, but existing SID construction often lacks recommendation-aware semantics and effective local collaborative signals, while next-token prediction is misaligned with slate-level objectives. We propose OGR, an end-to-end framework that directly generates ordered slates-"Once Generated, Ranked." OGR first introduces TUSID, which adaptively fuses item-specific semantic and local collaborative information into hierarchical SIDs. It then uses list-wise preference planning and pipelined position-wise SID decoding to model global preferences and inter-item dependencies while generating ordered slates. We further propose SPA, a reward-guided conservative policy optimization method that aligns generated slates with user preferences beyond likelihood imitation. Offline experiments show that OGR outperforms representative baselines, with 48.2% and 27.2% relative NDCG@5 gains on industrial and public datasets, respectively. Online A/B testing on Kuaishou further yields a 1.120% improvement in Effective Views.

cs.IR↗

arXiv2026

Trillion-atom molecular dynamics simulations with ab initio accuracy

Material properties are fundamentally dictated by multiscale phenomena, which often reach mesoscale in size. The μm mesoscale is also the size which can be observed directly under an optical microscope, bridging the atomistic microscopic description with the continuous model macroscopic world. In this work, we report an unprecedented molecular dynamics (MD) simulation comprising 1.62 trillion atoms. Utilizing the neuroevolution potential (NEP) framework, we attained ab initio accuracy on China's New-generation Intelligent Supercomputer. Our implementation achieves a time-to-solution (s/step/atom) 100 times faster than previous state-of-the-art machine learning force field simulations, and 1,000 times faster than the Gordon Bell Prize-winning application from six years ago. Furthermore, we demonstrate an 86.9% weak scaling efficiency from a single GPGPU to 45,000 GPGPUs. These results redefine atomistic simulation boundaries, enabling direct mesoscopic modeling with quantum-level precision.

cond-mat.mtrl-sci↗

arXiv2025

Modular Layout Synthesis (MLS): Front-end Code via Structure Normalization and Constrained Generation

Automated front-end engineering drastically reduces development cycles and minimizes manual coding overhead. While Generative AI has shown promise in translating designs to code, current solutions often produce monolithic scripts, failing to natively support modern ecosystems like React, Vue, or Angular. Furthermore, the generated code frequently suffers from poor modularity, making it difficult to maintain. To bridge this gap, we introduce Modular Layout Synthesis (MLS), a hierarchical framework that merges visual understanding with structural normalization. Initially, a visual-semantic encoder maps the screen capture into a serialized tree topology, capturing the essential layout hierarchy. Instead of simple parsing, we apply heuristic deduplication and pattern recognition to isolate reusable blocks, creating a framework-agnostic schema. Finally, a constraint-based generation protocol guides the LLM to synthesize production-ready code with strict typing and component props. Evaluations show that MLS significantly outperforms existing baselines, ensuring superior code reusability and structural integrity across multiple frameworks

cs.IR↗

arXiv2025

Nonlinear bulk photocurrent probe Z2 topological phase transition

Detecting topological phase transitions in bulk is challenging due to the limitations of surface sensitive probes like ARPES. Here, we demonstrate that nonlinear bulk photocurrents, specifically shift and injection currents, serve as effective probes of Z_2 topological transitions. These photocurrents show a robust polarity reversal across the Z_2 phase transition, offering a direct optical signature that distinguishes strong topological phases from weak or trivial ones. This effect originates from a reorganization of key band geometric quantities, the Berry curvature and shift vector, on time-reversal-invariant momentum planes. Using a low energy Dirac model, we trace this behaviour to a band inversion in the time-reversal-invariant momentum plane that drives the topological transition. We validate these findings through tight-binding model for Bi_2Te_3 and first-principles calculations for ZrTe_5 and BiTeI, where the topological phase can be tuned by pressure or temperature. Our results establish nonlinear photocurrent as a sensitive and broadly applicable probe of Z_2 topological phase transitions.

cond-mat.mtrl-sci↗

arXiv2025

xMTF: A Formula-Free Model for Reinforcement-Learning-Based Multi-Task Fusion in Recommender Systems

Recommender systems need to optimize various types of user feedback, e.g., clicks, likes, and shares. A typical recommender system handling multiple types of feedback has two components: a multi-task learning (MTL) module, predicting feedback such as click-through rate and like rate; and a multi-task fusion (MTF) module, integrating these predictions into a single score for item ranking. MTF is essential for ensuring user satisfaction, as it directly influences recommendation outcomes. Recently, reinforcement learning (RL) has been applied to MTF tasks to improve long-term user satisfaction. However, existing RL-based MTF methods are formula-based methods, which only adjust limited coefficients within pre-defined formulas. The pre-defined formulas restrict the RL search space and become a bottleneck for MTF. To overcome this, we propose a formula-free MTF framework. We demonstrate that any suitable fusion function can be expressed as a composition of single-variable monotonic functions, as per the Sprecher Representation Theorem. Leveraging this, we introduce a novel learnable monotonic fusion cell (MFC) to replace pre-defined formulas. We call this new MFC-based model eXtreme MTF (xMTF). Furthermore, we employ a two-stage hybrid (TSH) learning strategy to train xMTF effectively. By expanding the MTF search space, xMTF outperforms existing methods in extensive offline and online experiments.

cs.IR↗

arXiv2025

Creator-Side Recommender System: Challenges, Designs, and Applications

Users and creators are two crucial components of recommender systems. Typical recommender systems focus on the user side, providing the most suitable items based on each user's request. In such scenarios, a few items receive a majority of exposures, while many items receive very few. This imbalance leads to poorer experiences and decreased activity among the creators receiving less feedback, harming the recommender system in the long term. To this end, we develop a creator-side recommender system, called DualRec, to answer the following question: how to find the most suitable users for each item to enhance the creators' experience? We show that typical user-side recommendation algorithms, such as retrieval and ranking algorithms, can be adapted into the creator-side versions with just a few modifications. This greatly simplifies algorithm design in DualRec. Moreover, we discuss a unique challenge in DualRec: the user availability issue, which is not present in user-side recommender systems. To tackle this issue, we incorporate a user availability calculation (UAC) module to effectively enhance DualRec's performance. DualRec has already been implemented in Kwai, a short video recommendation system with over 100 millions user and over 10 million creators, significantly improving the experience for creators.

cs.IR↗

arXiv2024

RPAF: A Reinforcement Prediction-Allocation Framework for Cache Allocation in Large-Scale Recommender Systems

Modern recommender systems are built upon computation-intensive infrastructure, and it is challenging to perform real-time computation for each request, especially in peak periods, due to the limited computational resources. Recommending by user-wise result caches is widely used when the system cannot afford a real-time recommendation. However, it is challenging to allocate real-time and cached recommendations to maximize the users' overall engagement. This paper shows two key challenges to cache allocation, i.e., the value-strategy dependency and the streaming allocation. Then, we propose a reinforcement prediction-allocation framework (RPAF) to address these issues. RPAF is a reinforcement-learning-based two-stage framework containing prediction and allocation stages. The prediction stage estimates the values of the cache choices considering the value-strategy dependency, and the allocation stage determines the cache choices for each individual request while satisfying the global budget constraint. We show that the challenge of training RPAF includes globality and the strictness of budget constraints, and a relaxed local allocator (RLA) is proposed to address this issue. Moreover, a PoolRank algorithm is used in the allocation stage to deal with the streaming allocation problem. Experiments show that RPAF significantly improves users' engagement under computational budget constraints.

cs.LG↗

arXiv2024

Cache-Aware Reinforcement Learning in Large-Scale Recommender Systems

Modern large-scale recommender systems are built upon computation-intensive infrastructure and usually suffer from a huge difference in traffic between peak and off-peak periods. In peak periods, it is challenging to perform real-time computation for each request due to the limited budget of computational resources. The recommendation with a cache is a solution to this problem, where a user-wise result cache is used to provide recommendations when the recommender system cannot afford a real-time computation. However, the cached recommendations are usually suboptimal compared to real-time computation, and it is challenging to determine the items in the cache for each user. In this paper, we provide a cache-aware reinforcement learning (CARL) method to jointly optimize the recommendation by real-time computation and by the cache. We formulate the problem as a Markov decision process with user states and a cache state, where the cache state represents whether the recommender system performs recommendations by real-time computation or by the cache. The computational load of the recommender system determines the cache state. We perform reinforcement learning based on such a model to improve user engagement over multiple requests. Moreover, we show that the cache will introduce a challenge called critic dependency, which deteriorates the performance of reinforcement learning. To tackle this challenge, we propose an eigenfunction learning (EL) method to learn independent critics for CARL. Experiments show that CARL can significantly improve the users' engagement when considering the result cache. CARL has been fully launched in Kwai app, serving over 100 million users.

cs.LG↗

arXiv2024

CREAD: A Classification-Restoration Framework with Error Adaptive Discretization for Watch Time Prediction in Video Recommender Systems

The watch time is a significant indicator of user satisfaction in video recommender systems. However, the prediction of watch time as a target variable is often hindered by its highly imbalanced distribution with a scarcity of observations for larger target values and over-populated samples for small values. State-of-the-art watch time prediction models discretize the continuous watch time into a set of buckets in order to consider the distribution of watch time. However, it is highly uninvestigated how these discrete buckets should be created from the continuous watch time distribution, and existing discretization approaches suffer from either a large learning error or a large restoration error. To address this challenge, we propose a Classification-Restoration framework with Error-Adaptive-Discretization (CREAD) to accurately predict the watch time. The proposed framework contains a discretization module, a classification module, and a restoration module. It predicts the watch time through multiple classification problems. The discretization process is a key contribution of the CREAD framework. We theoretically analyze the impacts of the discretization on the learning error and the restoration error, and then propose the error-adaptive discretization (EAD) technique to better balance the two errors, which achieves better performance over traditional discretization approaches. We conduct detailed offline evaluations on a public dataset and an industrial dataset, both showing performance gains through the proposed approach. Moreover, We have fully launched our framework to Kwai App, an online video platform, which resulted in a significant increase in users' video watch time by 0.29% through A/B testing. These results highlight the effectiveness of the CREAD framework in watch time prediction in video recommender systems.

cs.IR↗

arXiv2024

UNEX-RL: Reinforcing Long-Term Rewards in Multi-Stage Recommender Systems with UNidirectional EXecution

In recent years, there has been a growing interest in utilizing reinforcement learning (RL) to optimize long-term rewards in recommender systems. Since industrial recommender systems are typically designed as multi-stage systems, RL methods with a single agent face challenges when optimizing multiple stages simultaneously. The reason is that different stages have different observation spaces, and thus cannot be modeled by a single agent. To address this issue, we propose a novel UNidirectional-EXecution-based multi-agent Reinforcement Learning (UNEX-RL) framework to reinforce the long-term rewards in multi-stage recommender systems. We show that the unidirectional execution is a key feature of multi-stage recommender systems, bringing new challenges to the applications of multi-agent reinforcement learning (MARL), namely the observation dependency and the cascading effect. To tackle these challenges, we provide a cascading information chain (CIC) method to separate the independent observations from action-dependent observations and use CIC to train UNEX-RL effectively. We also discuss practical variance reduction techniques for UNEX-RL. Finally, we show the effectiveness of UNEX-RL on both public datasets and an online recommender system with over 100 million users. Specifically, UNEX-RL reveals a 0.558% increase in users' usage time compared with single-agent RL algorithms in online A/B experiments, highlighting the effectiveness of UNEX-RL in industrial recommender systems.

cs.IR↗

arXiv2023

Combining Past, Present and Future: A Self-Supervised Approach for Class Incremental Learning

Class Incremental Learning (CIL) aims to handle the scenario where data of novel classes occur continuously and sequentially. The model should recognize the sequential novel classes while alleviating the catastrophic forgetting. In the self-supervised manner, it becomes more challenging to avoid the conflict between the feature embedding spaces of novel classes and old ones without any class labels. To address the problem, we propose a self-supervised CIL framework CPPF, meaning Combining Past, Present and Future. In detail, CPPF consists of a prototype clustering module (PC), an embedding space reserving module (ESR) and a multi-teacher distillation module (MTD). 1) The PC and the ESR modules reserve embedding space for subsequent phases at the prototype level and the feature level respectively to prepare for knowledge learned in the future. 2) The MTD module maintains the representations of the current phase without the interference of past knowledge. One of the teacher networks retains the representations of the past phases, and the other teacher network distills relation information of the current phase to the student network. Extensive experiments on CIFAR100 and ImageNet100 datasets demonstrate that our proposed method boosts the performance of self-supervised class incremental learning. We will release code in the near future.

cs.CV↗

arXiv2022

Efficiently Answering Quality Constrained Shortest Distance Queries in Large Graphs

The shortest-path distance is a fundamental concept in graph analytics and has been extensively studied in the literature. In many real-world applications, quality constraints are naturally associated with edges in the graphs and finding the shortest distance between two vertices $s$ and $t$ along only valid edges (i.e., edges that satisfy a given quality constraint) is also critical. In this paper, we investigate this novel and important problem of quality constraint shortest distance queries. We propose an efficient index structure based on 2-hop labeling approaches. Supported by a path dominance relationship incorporating both quality and length information, we demonstrate the minimal property of the new index. An efficient query processing algorithm is also developed. Extensive experimental studies over real-life datasets demonstrates efficiency and effectiveness of our techniques.

cs.DB↗

arXiv2022

PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting

Crowd counting aims to learn the crowd density distributions and estimate the number of objects (e.g. persons) in images. The perspective effect, which significantly influences the distribution of data points, plays an important role in crowd counting. In this paper, we propose a novel perspective-aware approach called PANet to address the perspective problem. Based on the observation that the size of the objects varies greatly in one image due to the perspective effect, we propose the dynamic receptive fields (DRF) framework. The framework is able to adjust the receptive field by the dilated convolution parameters according to the input image, which helps the model to extract more discriminative features for each local region. Different from most previous works which use Gaussian kernels to generate the density map as the supervised information, we propose the self-distilling supervision (SDS) training method. The ground-truth density maps are refined from the first training stage and the perspective information is distilled to the model in the second stage. The experimental results on ShanghaiTech Part_A and Part_B, UCF_QNRF, and UCF_CC_50 datasets demonstrate that our proposed PANet outperforms the state-of-the-art methods by a large margin.

cs.CV↗

arXiv2022

Reinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting

Fully-supervised crowd counting is a laborious task due to the large amounts of annotations. Few works focus on weekly-supervised crowd counting, where only the global crowd numbers are available for training. The main challenge of weekly-supervised crowd counting is the lack of local supervision information. To address this problem, we propose a self-adaptive feature similarity learning (SFSL) network and a global-local consistency (GLC) loss to reinforce local feature representation. We introduce a feature vector which represents the unbiased feature estimation of persons. The network updates the feature vector self-adaptively and utilizes the feature similarity for the regression of crowd numbers. Besides, the proposed GLC loss leverages the consistency between the network estimations from global and local areas. The experimental results demonstrate that our proposed method based on different backbones narrows the gap between weakly-supervised and fully-supervised dense crowd counting.

cs.CV↗

arXiv2020

A Framework to Quantify Approximate Simulation on Graph Data

Simulation and its variants (e.g., bisimulation and degree-preserving simulation) are useful in a wide spectrum of applications. However, all simulation variants are coarse "yes-or-no" indicators that simply confirm or refute whether one node simulates another, which limits the scope and power of their utility. Therefore, it is meaningful to develop a fractional $χ$-simulation measure to quantify the degree to which one node simulates another by the simulation variant $χ$. To this end, we first present several properties necessary for a fractional $χ$-simulation measure. Then, we present $FSim_χ$, a general fractional $χ$-simulation computation framework that can be configured to quantify the extent of all $χ$-simulations. Comprehensive experiments and real-world case studies show the measure to be effective and the computation framework to be efficient.

cs.LO↗

arXiv2020

Fast Monte Carlo Simulation of Dynamic Power Systems Under Continuous Random Disturbances

Continuous-time random disturbances from the renewable generation pose a significant impact on power system dynamic behavior. In evaluating this impact, the disturbances must be considered as continuous-time random processes instead of random variables that do not vary with time to ensure accuracy. Monte Carlo simulation (MCs) is a nonintrusive method to evaluate such impact that can be performed on commercial power system simulation software and is easy for power utilities to use, but is computationally cumbersome. Fast samplings methods such as Latin hypercube sampling (LHS) have been introduced to speed up sampling random variables, but yet cannot be applied to sample continuous disturbances. To overcome this limitation, this paper proposes a fast MCs method that enables the LHS to speed up sampling continuous disturbances, which is based on the Itô process model of the disturbances and the approximation of the Itô process by functions of independent normal random variables. A case study of the IEEE 39-Bus System shows that the proposed method is 47.6 and 6.7 times faster to converge compared to the traditional MCs in evaluating the expectation and variance of the system dynamic response.

math.OC↗

arXiv2020

Nonintrusive Uncertainty Quantification of Dynamic Power Systems Subject to Stochastic Excitations

Continuous-time random disturbances (also called stochastic excitations) due to increasing renewable generation have an increasing impact on power system dynamics; However, except from the Monte Carlo simulation, most existing methods for quantifying this impact are intrusive, meaning they are not based on commercial simulation software and hence are difficult to use for power utility companies. To fill this gap, this paper proposes an efficient and nonintrusive method for quantifying uncertainty in dynamic power systems subject to stochastic excitations. First, the Gaussian or non-Gaussian stochastic excitations are modeled with an Itô process as stochastic differential equations. Then, the Itô process is spectrally represented by independent Gaussian random parameters, which enables the polynomial chaos expansion (PCE) of the system dynamic response to be calculated via an adaptive sparse probabilistic collocation method. Finally, the probability distribution and the high-order moments of the system dynamic response and performance index are accurately and efficiently quantified. The proposed nonintrusive method is based on commercial simulation software such as PSS/E with carefully designed input signals, which ensures ease of use for power utility companies. The proposed method is validated via case studies of IEEE 39-bus and 118-bus test systems.

math.OC↗