arXiv subjects

Xiaojun Lin

Publications and source records attributed to Xiaojun Lin.

At least 19 recordsLinked to original sources

arXiv2026

Practical Cross-Band Channel Prediction for AI-RAN via Physics-Guided Deep Unfolding

To make cross-band channel prediction practical for AI-native RAN, algorithms must generalize across diverse environments and support real-time inference. Existing approaches achieve one but not both. To bridge this gap, we introduce GUIDE, a physics-guided deep unfolding framework that embeds wireless channel physics into differentiable layers. Without retraining in unseen environments, GUIDE achieves 2.75x beamforming gain than the deep learning-based baseline FIRE with only a slight increase in inference time, and 1.39x beamforming gain than the strongest model-based baseline R2F2 while running over 1610x faster.

eess.SP↗

arXiv2026

A Scalable Distributed Quantum Optimization Framework via Factor Graph Paradigm

Distributed quantum computing (DQC) connects many small quantum processors into a single logical machine, offering a practical route to scalable quantum computation. However, most existing DQC paradigms are structure-agnostic. Circuit cutting proposed by Peng et al. in [Phys. Rev. Lett., Oct. 2020] reduces per-device qubits at the cost of exponential classical post-processing, while search-space partitioning proposed by Avron et al. in [Phys. Rev. A., Nov. 2021] distributes the workload but weakens Grover's ideal quadratic speedup. In this paper, we introduce a structure-aware framework for distributed quantum optimization that resolves this complexity-resource trade-off. We model the objective function as a factor graph and expose its sparse interaction structure. We cut the graph along its natural ``seams'', i.e., a separator of boundary variables, to obtain loosely coupled subproblems that fit on resource-constrained processors. We coordinate these subproblems with shared entanglement, so the network executes a single globally coherent search rather than independent local searches. We prove that this design preserves Grover-like scaling: for a search space of size $N$, our framework achieves $O(\sqrt{N})$ query complexity up to processors and separator dependent factors, while relaxing the qubit requirement of each processor. We extend the framework with a hierarchical divide-and-conquer strategy that scales to large-scale optimization problems and supports two operating modes: a fully coherent mode for fault-tolerant networks and a hybrid mode that inserts measurements to cap circuit depth on near-term devices. We validate the predicted query-entanglement trade-offs through simulations over diverse network topologies, and we show that structure-aware decomposition delivers a practical path to scalable distributed quantum optimization on quantum networks.

quant-ph↗

arXiv2025

PANDA: Noise-Resilient Antagonist Identification in Production Datacenters

Modern warehouse-scale datacenters commonly collocate multiple jobs on shared machines to improve resource utilization. However, such collocation often leads to performance interference caused by antagonistic jobs that overconsume shared resources. Existing antagonist-detection approaches either rely on offline profiling, which is costly and unscalable, or use a sample-from-production approach, which suffers from noisy measurements and fails under multi-victim scenarios. We present PANDA, a noise-resilient antagonist identification framework for production-scale datacenters. Like prior correlation-based methods, PANDA uses cycles per instruction (CPI) as its performance metric, but it differs by (i) leveraging global historical knowledge across all machines to suppress sampling noise and (ii) introducing a machine-level CPI metric that captures shared-resource contention among multiple co-located tasks. Evaluation on a recent Google production trace shows that PANDA ranks true antagonists far more accurately than prior methods -- improving average suspicion percentile from 50-55% to 82.6% -- and achieves consistent antagonist identification under multi-victim scenarios, all with negligible runtime overhead.

cs.PF↗

arXiv2025

Extended Version: Characterizing Distributed Photovoltaic Panel Investment Equilibria

This study investigates long-term investment decisions in distributed photovoltaic panels by individual investors. We consider a setting where investment decisions are driven by expected revenue from participating in short-term electricity markets over the panel lifespan. These revenues depend on short-term market equilibria, i.e., prices and allocations, which are influenced by aggregate invested panel capacity participating in the markets. We model the interactions among investors by a non-atomic game and develop a framework that links short-term market equilibria to the resulting long-term investment equilibrium. Then, within this framework, we analyze three market mechanisms: (a) a single-product real-time energy market, (b) a product-differentiated real-time energy market that treats solar energy and grid energy as different products, and (c) a contract-based panel market that trades claims/rights to the production of certain panel capacity ex-ante, rather than the realized solar production ex-post. For each, we derive expressions for short-term equilibria and the associated expected revenues, and analytically characterize the corresponding long-term Nash equilibrium aggregate capacity. We compare the solutions of these characterizing equations under different conditions and theoretically establish that the product-differentiated market always supports socially optimal investment, while the single-product market consistently results in under-investment. We also establish that the contract-based market leads to over-investment when the extra valuations of users for solar energy are small. Finally, we validate our theoretical results through numerical experiments.

eess.SY↗

arXiv2025

Quantum Algorithms for Finite-horizon Markov Decision Processes

In this work, we design quantum algorithms that are more efficient than classical algorithms to solve time-dependent and finite-horizon Markov Decision Processes (MDPs) in two distinct settings: (1) In the exact dynamics setting, where the agent has full knowledge of the environment's dynamics (i.e., transition probabilities), we prove that our $\textbf{Quantum Value Iteration (QVI)}$ algorithm $\textbf{QVI-1}$ achieves a quadratic speedup in the size of the action space $(A)$ compared with the classical value iteration algorithm for computing the optimal policy ($\pi^{*}$) and the optimal V-value function ($V_{0}^{*}$). Furthermore, our algorithm $\textbf{QVI-2}$ provides an additional speedup in the size of the state space $(S)$ when obtaining near-optimal policies and V-value functions. Both $\textbf{QVI-1}$ and $\textbf{QVI-2}$ achieve quantum query complexities that provably improve upon classical lower bounds, particularly in their dependences on $S$ and $A$. (2) In the generative model setting, where samples from the environment are accessible in quantum superposition, we prove that our algorithms $\textbf{QVI-3}$ and $\textbf{QVI-4}$ achieve improvements in sample complexity over the state-of-the-art (SOTA) classical algorithm in terms of $A$, estimation error $(\epsilon)$, and time horizon $(H)$. More importantly, we prove quantum lower bounds to show that $\textbf{QVI-3}$ and $\textbf{QVI-4}$ are asymptotically optimal, up to logarithmic factors, assuming a constant time horizon.

quant-ph↗

arXiv2024

A Theoretical Analysis of Soft-Label vs Hard-Label Training in Neural Networks

Knowledge distillation, where a small student model learns from a pre-trained large teacher model, has achieved substantial empirical success since the seminal work of \citep{hinton2015distilling}. Despite prior theoretical studies exploring the benefits of knowledge distillation, an important question remains unanswered: why does soft-label training from the teacher require significantly fewer neurons than directly training a small neural network with hard labels? To address this, we first present motivating experimental results using simple neural network models on a binary classification problem. These results demonstrate that soft-label training consistently outperforms hard-label training in accuracy, with the performance gap becoming more pronounced as the dataset becomes increasingly difficult to classify. We then substantiate these observations with a theoretical contribution based on two-layer neural network models. Specifically, we show that soft-label training using gradient descent requires only $O\left(\frac{1}{\gamma^2 \epsilon}\right)$ neurons to achieve a classification loss averaged over epochs smaller than some $\epsilon > 0$, where $\gamma$ is the separation margin of the limiting kernel. In contrast, hard-label training requires $O\left(\frac{1}{\gamma^4} \cdot \ln\left(\frac{1}{\epsilon}\right)\right)$ neurons, as derived from an adapted version of the gradient descent analysis in \citep{ji2020polylogarithmic}. This implies that when $\gamma \leq \epsilon$, i.e., when the dataset is challenging to classify, the neuron requirement for soft-label training can be significantly lower than that for hard-label training. Finally, we present experimental results on deep neural networks, further validating these theoretical findings.

cs.LG↗

arXiv2024

Lightweight Federated Learning with Differential Privacy and Straggler Resilience

Federated learning (FL) enables collaborative model training through model parameter exchanges instead of raw data. To avoid potential inference attacks from exchanged parameters, differential privacy (DP) offers rigorous guarantee against various attacks. However, conventional methods of ensuring DP by adding local noise alone often result in low training accuracy. Combining secure multi-party computation (SMPC) with DP, while improving the accuracy, incurs high communication and computation overheads as well as straggler vulnerability, in either client-to-server or client-to-client links. In this paper, we propose LightDP-FL, a novel lightweight scheme that ensures provable DP against untrusted peers and server, while maintaining straggler resilience, low overheads and high training accuracy. Our scheme incorporates both individual and pairwise noise into each client's parameter, which can be implemented with minimal overheads. Given the uncertain straggler and colluder sets, we utilize the upper bound on the numbers of stragglers and colluders to prove sufficient noise variance conditions to ensure DP in the worst case. Moreover, we optimize the expected convergence bound to ensure accuracy performance by flexibly controlling the noise variances. Using the CIFAR-10 dataset, our experimental results demonstrate that LightDP-FL achieves faster convergence and stronger straggler resilience compared to baseline methods of the same DP level.

cs.CR↗

arXiv2024

A Comprehensive Survey of 3D Dense Captioning: Localizing and Describing Objects in 3D Scenes

Three-Dimensional (3D) dense captioning is an emerging vision-language bridging task that aims to generate multiple detailed and accurate descriptions for 3D scenes. It presents significant potential and challenges due to its closer representation of the real world compared to 2D visual captioning, as well as complexities in data collection and processing of 3D point cloud sources. Despite the popularity and success of existing methods, there is a lack of comprehensive surveys summarizing the advancements in this field, which hinders its progress. In this paper, we provide a comprehensive review of 3D dense captioning, covering task definition, architecture classification, dataset analysis, evaluation metrics, and in-depth prosperity discussions. Based on a synthesis of previous literature, we refine a standard pipeline that serves as a common paradigm for existing methods. We also introduce a clear taxonomy of existing models, summarize technologies involved in different modules, and conduct detailed experiment analysis. Instead of a chronological order introduction, we categorize the methods into different classes to facilitate exploration and analysis of the differences and connections among existing techniques. We also provide a reading guideline to assist readers with different backgrounds and purposes in reading efficiently. Furthermore, we propose a series of promising future directions for 3D dense captioning by identifying challenges and aligning them with the development of related tasks, offering valuable insights and inspiring future research in this field. Our aim is to provide a comprehensive understanding of 3D dense captioning, foster further investigations, and contribute to the development of novel applications in multimedia and related domains.

cs.CV↗

arXiv2024

SPriFed-OMP: A Differentially Private Federated Learning Algorithm for Sparse Basis Recovery

Sparse basis recovery is a classical and important statistical learning problem when the number of model dimensions $p$ is much larger than the number of samples $n$. However, there has been little work that studies sparse basis recovery in the Federated Learning (FL) setting, where the client data's differential privacy (DP) must also be simultaneously protected. In particular, the performance guarantees of existing DP-FL algorithms (such as DP-SGD) will degrade significantly when $p \gg n$, and thus, they will fail to learn the true underlying sparse model accurately. In this work, we develop a new differentially private sparse basis recovery algorithm for the FL setting, called SPriFed-OMP. SPriFed-OMP converts OMP (Orthogonal Matching Pursuit) to the FL setting. Further, it combines SMPC (secure multi-party computation) and DP to ensure that only a small amount of noise needs to be added in order to achieve differential privacy. As a result, SPriFed-OMP can efficiently recover the true sparse basis for a linear model with only $n = O(\sqrt{p})$ samples. We further present an enhanced version of our approach, SPriFed-OMP-GRAD based on gradient privatization, that improves the performance of SPriFed-OMP. Our theoretical analysis and empirical results demonstrate that both SPriFed-OMP and SPriFed-OMP-GRAD terminate in a small number of steps, and they significantly outperform the previous state-of-the-art DP-FL solutions in terms of the accuracy-privacy trade-off.

cs.LG↗

arXiv2024

Code-Based English Models Surprising Performance on Chinese QA Pair Extraction Task

In previous studies, code-based models have consistently outperformed text-based models in reasoning-intensive scenarios. When generating our knowledge base for Retrieval-Augmented Generation (RAG), we observed that code-based models also perform exceptionally well in Chinese QA Pair Extraction task. Further, our experiments and the metrics we designed discovered that code-based models containing a certain amount of Chinese data achieve even better performance. Additionally, the capabilities of code-based English models in specified Chinese tasks offer a distinct perspective for discussion on the philosophical "Chinese Room" thought experiment.

cs.CL↗

arXiv2024

Principles and Practices of Large-Scale Code Analysis at Ant Group: A Data- and Logic-Oriented Approach

Large-scale software development requires dynamic and multifaceted static code analysis that extends beyond the capabilities of traditional tools. Existing tools like CodeQL lack cross-language analysis capabilities and can be time-consuming and resource-intensive. We present CodeFuse-Query, a data system tailored for large-scale code analysis. First, CodeFuse-Query adopts a Logic-Oriented Computation Design, employing Datalog with a two-tiered schema, COREF, to convert source code into data facts, and Godel to express complex analysis tasks in logical terms. Furthermore, CodeFuse-Query adopts a Domain-Optimized System Design. This approach optimizes resource utilization, prioritizes data reusability, applies incremental code extraction, and introduces task-type characteristics specifically for code changes, underscoring its domain-optimized design. We present empirical results demonstrating CodeFuse-Query's robustness, scalability, and efficiency in large-scale real-world scenarios at Ant Group, where it serves as a core static analysis infrastructure. Deployed in production environments, CodeFuse-Query processes up to 10 billion lines of code daily across more than 300,000 distinct analysis tasks. CodeFuse-Query has been open-sourced.

cs.SE↗

arXiv2022

Characterizing and Modeling Control-Plane Traffic for Mobile Core Network

In this paper, we first carry out to our knowledge the first in-depth characterization of control-plane traffic, using a real-world control-plane trace for 37,325 UEs sampled at a real-world LTE Mobile Core Network (MCN). Our analysis shows that control events exhibit significant diversity in device types and time-of-day among UEs. Second, we study whether traditional probability distributions that have been widely adopted for modeling Internet traffic can model the control-plane traffic originated from individual UEs. Our analysis shows that the inter-arrival time of the control events as well as the sojourn time in the UE states of EMM and ECM for the cellular network cannot be modeled as Poisson processes or other traditional probability distributions. We further show that the reasons that these models fail to capture the control-plane traffic are due to its higher burstiness and longer tails in the cumulative distribution than the traditional models. Third, we propose a two-level hierarchical state-machine-based traffic model for UE clusters derived from our adaptive clustering scheme based on the Semi-Markov Model to capture key characteristics of mobile network control-plane traffic -- in particular, the dependence among events generated by each UE, and the diversity in device types and time-of-day among UEs. Finally, we show how our model can be easily adjusted from LTE to 5G to support modeling 5G control-plane traffic, when the sizable control-plane trace for 5G UEs becomes available to train the adjusted model. The developed control-plane traffic generator for LTE/5G networks is open-sourced to the research community to support high-performance MCN architecture design R&D.

cs.NI↗

arXiv2022

Insurance Contract for High Renewable Energy Integration

The increasing penetration of renewable energy poses significant challenges to power grid reliability. There have been increasing interests in utilizing financial tools, such as insurance, to help end-users hedge the potential risk of lost load due to renewable energy variability. With insurance, a user pays a premium fee to the utility, so that he will get compensated in case his demand is not fully satisfied. A proper insurance design needs to resolve the following two challenges: (i) users' reliability preference is private information; and (ii) the insurance design is tightly coupled with the renewable energy investment decision. To address these challenges, we adopt the contract theory to elicit users' private reliability preferences, and we study how the utility can jointly optimize the insurance contract and the planning of renewable energy. A key analytical challenge is that the joint optimization of the insurance design and the planning of renewables is non-convex. We resolve this difficulty by revealing important structural properties of the optimal solution, using the help of two benchmark problems: the no-insurance benchmark and the social-optimum benchmark. Compared with the no-insurance benchmark, we prove that the social cost and users' total energy cost are always no larger under the optimal contract. Simulation results show that the largest benefit of the insurance contract is achieved at a medium electricity-bill price together with a low type heterogeneity and a high renewable uncertainty.

eess.SY↗

arXiv2022

On the Generalization Power of the Overfitted Three-Layer Neural Tangent Kernel Model

In this paper, we study the generalization performance of overparameterized 3-layer NTK models. We show that, for a specific set of ground-truth functions (which we refer to as the "learnable set"), the test error of the overfitted 3-layer NTK is upper bounded by an expression that decreases with the number of neurons of the two hidden layers. Different from 2-layer NTK where there exists only one hidden-layer, the 3-layer NTK involves interactions between two hidden-layers. Our upper bound reveals that, between the two hidden-layers, the test error descends faster with respect to the number of neurons in the second hidden-layer (the one closer to the output) than with respect to that in the first hidden-layer (the one closer to the input). We also show that the learnable set of 3-layer NTK without bias is no smaller than that of 2-layer NTK models with various choices of bias in the neurons. However, in terms of the actual generalization performance, our results suggest that 3-layer NTK is much less sensitive to the choices of bias than 2-layer NTK, especially when the input dimension is large.

cs.LG↗

arXiv2022

SeedGNN: Graph Neural Networks for Supervised Seeded Graph Matching

There is a growing interest in designing Graph Neural Networks (GNNs) for seeded graph matching, which aims to match two unlabeled graphs using only topological information and a small set of seed nodes. However, most previous GNNs for this task use a semi-supervised approach, which requires a large number of seeds and cannot learn knowledge that is transferable to unseen graphs. In contrast, this paper proposes a new supervised approach that can learn from a training set how to match unseen graphs with only a few seeds. Our SeedGNN architecture incorporates several novel designs, inspired by theoretical studies of seeded graph matching: 1) it can learn to compute and use witness-like information from different hops, in a way that can be generalized to graphs of different sizes; 2) it can use easily-matched node-pairs as new seeds to improve the matching in subsequent layers. We evaluate SeedGNN on synthetic and real-world graphs and demonstrate significant performance improvements over both non-learning and learning algorithms in the existing literature. Furthermore, our experiments confirm that the knowledge learned by SeedGNN from training graphs can be generalized to test graphs of different sizes and categories.

cs.LG↗

arXiv2022

A Case for Sampling Based Learning Techniques in Coflow Scheduling

Coflow scheduling improves data-intensive application performance by improving their networking performance. State-of-the-art online coflow schedulers in essence approximate the classic Shortest-Job-First (SJF) scheduling by learning the coflow size online. In particular, they use multiple priority queues to simultaneously accomplish two goals: to sieve long coflows from short coflows, and to schedule short coflows with high priorities. Such a mechanism pays high overhead in learning the coflow size: moving a large coflow across the queues delays small and other large coflows, and moving similar-sized coflows across the queues results in inadvertent round-robin scheduling. We propose Philae, a new online coflow scheduler that exploits the spatial dimension of coflows, i.e., a coflow has many flows, to drastically reduce the overhead of coflow size learning. Philae pre-schedules sampled flows of each coflow and uses their sizes to estimate the average flow size of the coflow. It then resorts to Shortest Coflow First, where the notion of shortest is determined using the learned coflow sizes and coflow contention. We show that the sampling-based learning is robust to flow size skew and has the added benefit of much improved scalability from reduced coordinator-local agent interactions. Our evaluation using an Azure testbed, a publicly available production cluster trace from Facebook shows that compared to the prior art Aalo, Philae reduces the coflow completion time (CCT) in average (P90) cases by 1.50x (8.00x) on a 150-node testbed and 2.72x (9.78x) on a 900-node testbed. Evaluation using additional traces further demonstrates Philae's robustness to flow size skew.

cs.DC↗

arXiv2021

Time-of-use Pricing for Energy Storage Investment

Time-of-use (ToU) pricing is widely used by the electricity utility to shave peak load. Such a pricing scheme provides users with incentives to invest in behind-the-meter energy storage and to shift peak load towards low-price intervals. However, without considering the implication on energy storage investment, an improperly designed ToU pricing scheme may lead to significant welfare loss, especially when users over-invest the storage, which leads to new energy consumption peaks. In this paper, we will study how to design a social-optimum ToU pricing scheme by explicitly considering its impact on storage investment. We model the interactions between the utility and users as a two-stage optimization problem. To resolve the challenge of asymmetric information due to users' private storage cost, we propose a ToU pricing scheme based on different storage types and the aggregate demand per type. Each user does not need to reveal his private cost information. We can further compute the optimal ToU pricing with only a linear complexity. Simulations based on real-world data show that the suboptimality gap of our proposed ToU pricing, compared with the social optimum achieved under complete information, is less than 5%.

eess.SY↗

arXiv2021

Virtual Energy Storage Sharing and Capacity Allocation

Energy storage can play an important role in energy management of end users. To promote an efficient utilization of energy storage, we develop a novel business model to enable virtual storage sharing among a group of users. Specifically, a storage aggregator invests and operates the central physical storage unit, by virtualizing it into separable virtual capacities and selling to users. Each user purchases the virtual capacity, and utilize it to reduce the energy cost. We formulate the interaction between the aggregator and users as a two-stage optimization problem. In Stage 1, over the investment horizon, the aggregator determines the investment and pricing decisions. In Stage 2, in each operational horizon, each user decides the virtual capacity to purchase together with the operation of the virtual storage. We characterize a stepwise form of the optimal solution of Stage-2 Problem and a piecewise linear structure of the optimal profit of Stage-1 Problem, both with respect to the virtual capacity price. Based on the solution structure, we design an algorithm to attain the optimal solution of the two-stage problem. In our simulation results, the proposed storage virtualization model can reduce the physical energy storage investment of the aggregator by 54.3% and reduce the users' total costs by 34.7%, compared to the case where users acquire their own physical storage.

eess.SY↗