arXiv subjects

Ruijie Du

Publications and source records attributed to Ruijie Du.

9 recordsLinked to original sources

arXiv2026

PHKT:Personalized Dynamic Hypergraph-enhanced KAN-Transformer for Multi-behavior Sequential Recommendation

In multi-behavior recommendation, auxiliary behaviors such as clicks, add-to-cart, and purchases can provide richer supervisory information for predicting target behaviors. Although existing graph and hypergraph methods are capable of modeling high-order relationships among users, items, and behaviors, they still have limitations in heterogeneous semantics, user-specific weighting, and sequence dependency modeling. While standard Transformers excel at sequence modeling, their shared feedforward mapping struggles to accommodate the differentiated requirements of heterogeneous latent patterns in multi-behavior scenarios. To address this, this paper proposes the Personalized Hypergraph-enhanced Kolmogorov-Arnold Network Transformer (PHKT). Specifically, we design a personalized dynamic hypergraph module that performs behavior-aware weighting of item similarities based on users' historical behavior sequences to capture user-specific heterogeneous high-order relationships. Meanwhile, a Transformer is used as the temporal backbone to model the evolution of short- and long-term preferences, and KAN is introduced to replace the traditional MLP in the feedforward network to enhance fine-grained modeling capability for nonlinear responses to different latent patterns. Experiments on three real datasets, Tmall, RetailRocket, and IJCAI, show that PHKT consistently outperforms nine strong baseline models across multiple evaluation metrics, demonstrating its effectiveness in multi-behavior preference modeling and target behavior prediction.

cs.IR↗

arXiv2025

Online Learning and Coverage of Unknown Fields Using Random-Feature Gaussian Processes

This paper proposes a framework for multi-robot systems to perform simultaneous learning and coverage of a domain of interest characterized by an unknown and potentially time-varying density function. To overcome the limitations of Gaussian Process (GP) regression, we employ Random Feature GP (RFGP) and its online variant (O-RFGP) which enables online and incremental inference. By integrating these with Voronoi-based coverage control and Upper Confidence Bound (UCB) sampling strategy, a team of robots can adaptively focus on important regions while refining the learned spatial field for efficient coverage. The incremental update mechanism of O-RFGP naturally supports time-varying environments, allowing efficient adaptation without retaining historical data. Furthermore, to the best of our knowledge, we provide the first theoretical analysis of online learning and coverage through a regret-based formulation, establishing asymptotic no-regret guarantees in the time-invariant setting. The effectiveness of the proposed framework is demonstrated through simulations with both time-invariant and time-varying density functions, along with a physical experiment with a time-varying density function.

cs.RO↗

arXiv2024

Gradient Inversion Attack on Graph Neural Networks

Graph federated learning is of essential importance for training over large graph datasets while protecting data privacy, where each client stores a subset of local graph data, while the server collects the local gradients and broadcasts only the aggregated gradients. Recent studies reveal that a malicious attacker can steal private image data from the gradient exchange of neural networks during federated learning. However, the vulnerability of graph data and graph neural networks under such attacks, i.e., reconstructing both node features and graph structure from gradients, remains largely underexplored. To answer this question, this paper studies the problem of whether private data can be reconstructed from leaked gradients in both node classification and graph classification tasks and proposes a novel attack named Graph Leakage from Gradients (GLG). Two widely used GNN frameworks are analyzed, namely GCN and GraphSAGE. The effects of different model settings on reconstruction are extensively discussed. Theoretical analysis and empirical validation demonstrate that, by leveraging the unique properties of graph data and GNNs, GLG achieves more accurate reconstruction of both nodal features and graph structure from gradients.

cs.LG↗

arXiv2024

FairViT: Fair Vision Transformer via Adaptive Masking

Vision Transformer (ViT) has achieved excellent performance and demonstrated its promising potential in various computer vision tasks. The wide deployment of ViT in real-world tasks requires a thorough understanding of the societal impact of the model. However, most ViT-based works do not take fairness into account and it is unclear whether directly applying CNN-oriented debiased algorithm to ViT is feasible. Moreover, previous works typically sacrifice accuracy for fairness. Therefore, we aim to develop an algorithm that improves accuracy without sacrificing fairness. In this paper, we propose FairViT, a novel accurate and fair ViT framework. To this end, we introduce a novel distance loss and deploy adaptive fairness-aware masks on attention layers updating with model parameters. Experimental results show \sys can achieve accuracy better than other alternatives, even with competitive computational efficiency. Furthermore, \sys achieves appreciable fairness results.

cs.CV↗

arXiv2024

Two Ultracold Atoms in a Quasi-Two-Dimensional Box Confinement

We investigate the scattering and two-body bound states of two ultracold atoms in a quasi-two-dimensional (quasi-2D) confinement, with the confinement potential being an infinite square well (box potential) in the transverse ($z$-) direction, and the motion of the atoms in the $x$-$y$ plane being free. Specifically, we calculate the effective 2D scattering length and 2D effective range of the low-energy scattering, as well as the energy and the transverse-excited-mode probability of the bound states. Comparing these results with those obtained under a harmonic transverse confinement potential, we find that in most of the cases the 2D effective range for the box confinement is approximately 0.28 of the one for the harmonic confinement. Moreover, the transverse-excited-mode probability of the bound states for the box confinement is also much lower than the one for the harmonic confinement. These results suggest that the transverse excitation in the box confinement is notably weaker than the one in a harmonic confinement. Therefore, achieving quasi-2D ultracold gases well-described by pure-2D effective models, particularly those with 2D contact interaction, is more feasible through box confinement. Our results are helpful for the quantum simulation of 2D many-body physics with ultracold atoms, e.g., the suppression of 2D effective range may lead to an enhancement of quantum anomaly in two-dimensional Fermi Gases. Additionally, our calculation method is applicable to the two-body problems of ultracold atoms in other types of quasi-2D confinements.

cond-mat.quant-gas↗

arXiv2024

Analytical solutions of the Schr\"{o}dinger equation for two confined atoms with van der Waals interaction

We derive solutions of the Schr\"{o}dinger equation for the isotropic van der Waals interaction in a symmetric harmonic trap, with the recent approach [arXiv:2207.09377 (2022)] to handle the multi-scale long-range potential. Asymptotic behaviors of these solutions are then obtained for $r\rightarrow 0$ and $r\rightarrow \infty$. We further deduce the energy spectrum of the two-body relative motion and relate the spectrum to scattering lengths for $s$ wave and $p$ wave. These results can be used to research trapped atom-atom collisions and energy spectra.

physics.atom-ph↗

arXiv2024

Long-term Fairness For Real-time Decision Making: A Constrained Online Optimization Approach

Machine learning (ML) has demonstrated remarkable capabilities across many real-world systems, from predictive modeling to intelligent automation. However, the widespread integration of machine learning also makes it necessary to ensure machine learning-driven decision-making systems do not violate ethical principles and values of society in which they operate. As ML-driven decisions proliferate, particularly in cases involving sensitive attributes such as gender, race, and age, to name a few, the need for equity and impartiality has emerged as a fundamental concern. In situations demanding real-time decision-making, fairness objectives become more nuanced and complex: instantaneous fairness to ensure equity in every time slot, and long-term fairness to ensure fairness over a period of time. There is a growing awareness that real-world systems that operate over long periods and require fairness over different timelines. However, existing approaches mainly address dynamic costs with time-invariant fairness constraints, often disregarding the challenges posed by time-varying fairness constraints. To bridge this gap, this work introduces a framework for ensuring long-term fairness within dynamic decision-making systems characterized by time-varying fairness constraints. We formulate the decision problem with fairness constraints over a period as a constrained online optimization problem. A novel online algorithm, named LoTFair, is presented that solves the problem 'on the fly'. We prove that LoTFair can make overall fairness violations negligible while maintaining the performance over the long run.

cs.LG↗

arXiv2023

Change Point Detection Approach for Online Control of Unknown Time Varying Dynamical Systems

We propose a novel change point detection approach for online learning control with full information feedback (state, disturbance, and cost feedback) for unknown time-varying dynamical systems. We show that our algorithm can achieve a sub-linear regret with respect to the class of Disturbance Action Control (DAC) policies, which are a widely studied class of policies for online control of dynamical systems, for any sub-linear number of changes and very general class of systems: (i) matched disturbance system with general convex cost functions, (ii) general system with linear cost functions. Specifically, a (dynamic) regret of $Γ_T^{1/5}T^{4/5}$ can be achieved for these class of systems, where $Γ_T$ is the number of changes of the underlying system and $T$ is the duration of the control episode. That is, the change point detection approach achieves a sub-linear regret for any sub-linear number of changes, which other previous algorithms such as in \cite{minasyan2021online} cannot. Numerically, we demonstrate that the change point detection approach is superior to a standard restart approach \cite{minasyan2021online} and to standard online learning approaches for time-invariant dynamical systems. Our work presents the first regret guarantee for unknown time-varying dynamical systems in terms of a stronger notion of variability like the number of changes in the underlying system. The extension of our work to state and output feedback controllers is a subject of future work.

eess.SY↗

arXiv2022

Solutions of the Schr\"{o}dinger equation for anisotropic dipole-dipole interaction plus isotropic van der Waals interaction

By generalizing Bo Gao's approach [Phys. Rev. A 58, 1728 (1998)] for solving the Schr\"{o}dinger equation for an isotropic van der Waals (vdW) potential to the systems with a multi-scale anisotropic long-range interaction, we derive the solutions for the Schr\"{o}dinger equation for an anisotropic dipole-dipole interaction plus an isotropic attractive vdW potential, i.e., ${C_d(1-3\cos^2\theta)}/{r^3}-{C_6}/{r^6}$, which is projected to the subspace with angular momentum $l\leq l_{\rm cut}$, with $l_{\rm cut}$ being an arbitrary angular-momentum cutoff. Here $\theta$ is the polar angle of the coordinate $\boldsymbol{r}$ and $r=|\boldsymbol{r}|$. The asymptotic behaviors of these solutions for $r\rightarrow 0$ and $r\rightarrow \infty$ are obtained. These results can be used in the research of collisions and chemical reactions between ultra-cold polar molecules in a static electric field. Our approach to derive the solutions can be applied to the systems with a general long-range potential $\sum_{\lambda= 2}^{\lambda_{\rm max}} {V_\lambda(\theta,\varphi)}/{r^\lambda}$, with $\varphi$ being the azimuthal angle of $\boldsymbol{r}$, and thus can be used in various problems on molecule-molecule interaction.

cond-mat.quant-gas↗