arXiv subjects

Yi Zhang

Publications and source records attributed to Yi Zhang.

At least 523 records · Page 29Linked to original sources

arXiv2025

MixRec: Individual and Collective Mixing Empowers Data Augmentation for Recommender Systems

The core of the general recommender systems lies in learning high-quality embedding representations of users and items to investigate their positional relations in the feature space. Unfortunately, data sparsity caused by difficult-to-access interaction data severely limits the effectiveness of recommender systems. Faced with such a dilemma, various types of self-supervised learning methods have been introduced into recommender systems in an attempt to alleviate the data sparsity through distribution modeling or data augmentation. However, most data augmentation relies on elaborate manual design, which is not only not universal, but the bloated and redundant augmentation process may significantly slow down model training progress. To tackle these limitations, we propose a novel Dual Mixing-based Recommendation Framework (MixRec) to empower data augmentation as we wish. Specifically, we propose individual mixing and collective mixing, respectively. The former aims to provide a new positive sample that is unique to the target (user or item) and to make the pair-wise recommendation loss benefit from it, while the latter aims to portray a new sample that contains group properties in a batch. The two mentioned mixing mechanisms allow for data augmentation with only one parameter that does not need to be set multiple times and can be done in linear time complexity. Besides, we propose the dual-mixing contrastive learning to maximize the utilization of these new-constructed samples to enhance the consistency between pairs of positive samples. Experimental results on four real-world datasets demonstrate the advantages of MixRec in terms of effectiveness, simplicity, efficiency, and scalability.

cs.IR↗

arXiv2025

Language Representations Can be What Recommenders Need: Findings and Potentials

Recent studies empirically indicate that language models (LMs) encode rich world knowledge beyond mere semantics, attracting significant attention across various fields. However, in the recommendation domain, it remains uncertain whether LMs implicitly encode user preference information. Contrary to prevailing understanding that LMs and traditional recommenders learn two distinct representation spaces due to the huge gap in language and behavior modeling objectives, this work re-examines such understanding and explores extracting a recommendation space directly from the language representation space. Surprisingly, our findings demonstrate that item representations, when linearly mapped from advanced LM representations, yield superior recommendation performance. This outcome suggests the possible homomorphism between the advanced language representation space and an effective item representation space for recommendation, implying that collaborative signals may be implicitly encoded within LMs. Motivated by these findings, we explore the possibility of designing advanced collaborative filtering (CF) models purely based on language representations without ID-based embeddings. To be specific, we incorporate several crucial components to build a simple yet effective model, with item titles as the input. Empirical results show that such a simple model can outperform leading ID-based CF models, which sheds light on using language representations for better recommendation. Moreover, we systematically analyze this simple model and find several key features for using advanced language representations: a good initialization for item representations, zero-shot recommendation abilities, and being aware of user intention. Our findings highlight the connection between language modeling and behavior modeling, which can inspire both natural language processing and recommender system communities.

cs.IR↗

arXiv2025

Symmetry Topological Field Theory for Flavor Symmetry

In this Letter, we demonstrate that the Symmetry Topological Field Theory (SymTFT) associated to a Quantum Field Theory (QFT) with continuous non-abelian $G$-flavor symmetry is a $BF$-theory with gauge group $G$. We show that gauging $G$-symmetry with a flat connection yields a theory with global symmetry characterized by exchanging the conjugate variables in the quantization of $BF$-theory. We construct the extended operators that generate the $G$-flavor symmetry and the $(d-2)$-form $\text{Rep}(G)$-symmetry of the gauged QFT. We demonstrate that $BF$-theory arises as the theory characterizing $G$-flavor symmetry of a QFT in the AdS/CFT setup. 't Hooft anomalies of the $G$-flavor symmetry are realized as extra terms in the action.

hep-th↗

arXiv2025

Enhanced nonlinear Hall effect by Cooper pairs near superconductor criticality

Unlike the linear Hall effect that requires broken time-reversal symmetry, the nonlinear Hall effect may occur in time-reversal symmetric systems as long as there exists a non-zero Berry curvature dipole in the absence of inversion symmetry. Interestingly, the presence of time-reversal symmetry is consistent with and thus allows a direct transition into a superconducting phase. Indeed, superconductivity has been established in various nonlinear Hall materials, such as WTe$_2$ and MoTe$_2$, at sufficiently low temperatures. We find that the nonlinear Hall response should be significantly enhanced near the superconducting criticality, dominated by the Aslamazov-Larkin (AL) contributions augmented by superconducting fluctuations, which we attribute to the Berry curvature dipole and a divergent lifetime $τ\sim (T-T_c)^{-1}$ of the Cooper pairs, instead of the single electrons. Such a controlled enhancement brings the nonlinear Hall effect into various simple experimental observations and practical applicational potentials.

cond-mat.mes-hall↗

arXiv2025

ADT: Tuning Diffusion Models with Adversarial Supervision

Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict diffusion scores from noised versions of true samples in a single forward pass, while inference requires iterative denoising starting from white noise. This training-inference divergences hinder the alignment between inference and training data distributions, due to potential prediction biases and cumulative error accumulation. To address this problem, we propose an intuitive but effective fine-tuning framework, called Adversarial Diffusion Tuning (ADT), by stimulating the inference process during optimization and aligning the final outputs with training data by adversarial supervision. Specifically, to achieve robust adversarial training, ADT features a siamese-network discriminator with a fixed pre-trained backbone and lightweight trainable parameters, incorporates an image-to-image sampling strategy to smooth discriminative difficulties, and preserves the original diffusion loss to prevent discriminator hacking. In addition, we carefully constrain the backward-flowing path for back-propagating gradients along the inference path without incurring memory overload or gradient explosion. Finally, extensive experiments on Stable Diffusion models (v1.5, XL, and v3), demonstrate that ADT significantly improves both distribution alignment and image quality.

cs.CV↗

arXiv2025

Recurrence method in Non-Hermitian Systems

We propose a novel and systematic recurrence method for the energy spectra of non-Hermitian systems under open boundary conditions based on the recurrence relations of their characteristic polynomials. Our formalism exhibits better accuracy and performance on multi-band non-Hermitian systems than numerical diagonalization or the non-Bloch band theory. It also provides a targeted and efficient formulation for the non-Hermitian edge spectra. As demonstrations, we derive general expressions for both the bulk and edge spectra of multi-band non-Hermitian models with nearest-neighbor hopping and under open boundary conditions, such as the non-Hermitian Su-Schrieffer-Heeger and Rice-Mele models and the non-Hermitian Hofstadter butterfly - 2D lattice models in the presence of non-reciprocity and perpendicular magnetic fields, which is only made possible by the significantly lower complexity of the recurrence method. In addition, we use the recurrence method to study non-Hermitian edge physics, including the size-parity effect and the stability of the topological edge modes against boundary perturbations. Our recurrence method offers a novel and favorable formalism to the intriguing physics of non-Hermitian systems under open boundary conditions.

cond-mat.mes-hall↗

arXiv2025

FedRIR: Rethinking Information Representation in Federated Learning

Mobile and Web-of-Things (WoT) devices at the network edge generate vast amounts of data for machine learning applications, yet privacy concerns hinder centralized model training. Federated Learning (FL) allows clients (devices) to collaboratively train a shared model coordinated by a central server without transfer private data, but inherent statistical heterogeneity among clients presents challenges, often leading to a dilemma between clients' needs for personalized local models and the server's goal of building a generalized global model. Existing FL methods typically prioritize either global generalization or local personalization, resulting in a trade-off between these two objectives and limiting the full potential of diverse client data. To address this challenge, we propose a novel framework that simultaneously enhances global generalization and local personalization by Rethinking Information Representation in the Federated learning process (FedRIR). Specifically, we introduce Masked Client-Specific Learning (MCSL), which isolates and extracts fine-grained client-specific features tailored to each client's unique data characteristics, thereby enhancing personalization. Concurrently, the Information Distillation Module (IDM) refines the global shared features by filtering out redundant client-specific information, resulting in a purer and more robust global representation that enhances generalization. By integrating the refined global features with the isolated client-specific features, we construct enriched representations that effectively capture both global patterns and local nuances, thereby improving the performance of downstream tasks on the client. The code is available at https://github.com/Deep-Imaging-Group/FedRIR.

cs.LG↗

arXiv2025

Unveiling Contrastive Learning's Capability of Neighborhood Aggregation for Collaborative Filtering

Personalized recommendation is widely used in the web applications, and graph contrastive learning (GCL) has gradually become a dominant approach in recommender systems, primarily due to its ability to extract self-supervised signals from raw interaction data, effectively alleviating the problem of data sparsity. A classic GCL-based method typically uses data augmentation during graph convolution to generates more contrastive views, and performs contrast on these new views to obtain rich self-supervised signals. Despite this paradigm is effective, the reasons behind the performance gains remain a mystery. In this paper, we first reveal via theoretical derivation that the gradient descent process of the CL objective is formally equivalent to graph convolution, which implies that CL objective inherently supports neighborhood aggregation on interaction graphs. We further substantiate this capability through experimental validation and identify common misconceptions in the selection of positive samples in previous methods, which limit the potential of CL objective. Based on this discovery, we propose the Light Contrastive Collaborative Filtering (LightCCF) method, which introduces a novel neighborhood aggregation objective to bring users closer to all interacted items while pushing them away from other positive pairs, thus achieving high-quality neighborhood aggregation with very low time complexity. On three highly sparse public datasets, the proposed method effectively aggregate neighborhood information while preventing graph over-smoothing, demonstrating significant improvements over existing GCL-based counterparts in both training efficiency and recommendation accuracy. Our implementations are publicly accessible.

cs.IR↗

arXiv2025

Enhanced Marginal Sensitivity Model and Bounds

Sensitivity analysis is important to assess the impact of unmeasured confounding in causal inference from observational studies. The marginal sensitivity model (MSM) provides a useful approach in quantifying the influence of unmeasured confounders on treatment assignment and leading to tractable sharp bounds of common causal parameters. In this paper, to tighten MSM sharp bounds, we propose the enhanced MSM (eMSM) by incorporating another sensitivity constraint that quantifies the influence of unmeasured confounders on outcomes. We derive sharp population bounds of expected potential outcomes under eMSM, which are always narrower than the MSM sharp bounds in a simple and interpretable way. We further discuss desirable specifications of sensitivity parameters related to the outcome sensitivity constraint, and obtain both doubly robust point estimation and confidence intervals for the eMSM population bounds. The effectiveness of eMSM is also demonstrated numerically through two real-data applications. Our development represents, for the first time, a satisfactory extension of MSM to exploit both treatment and outcome sensitivity constraints on unmeasured confounding.

stat.ME↗

arXiv2025

On the monomorphism category of large modules

Let $R$ be an associative ring with identity. This paper investigates the structure of the monomorphism category of large $R$-modules and establishes connections with the category of contravariant functors defined on finitely presented $R$-modules. Several equivalences and dualities will be presented. Our results highlight the role of pure-injective modules in studying the homological properties of functor categories.

math.RT↗

arXiv2025

Dissipative iFIR filters for data-driven design

We tackle the problem of providing closed-loop stability guarantees with a scalable data-driven design. We combine virtual reference feedback tuning with dissipativity constraints on the controller for closed-loop stability. The constraints are formulated as a set of linear inequalities in the frequency domain. This leads to a convex problem that is scalable with respect to the length of the data and the complexity of the controller. An extension of virtual reference feedback tuning to include disturbance dynamics is also discussed. The proposed data-driven control design is illustrated by a soft gripper impedance control example.

eess.SY↗

arXiv2025

Intent Representation Learning with Large Language Model for Recommendation

Intent-based recommender systems have garnered significant attention for uncovering latent fine-grained preferences. Intents, as underlying factors of interactions, are crucial for improving recommendation interpretability. Most methods define intents as learnable parameters updated alongside interactions. However, existing frameworks often overlook textual information (e.g., user reviews, item descriptions), which is crucial for alleviating the sparsity of interaction intents. Exploring these multimodal intents, especially the inherent differences in representation spaces, poses two key challenges: i) How to align multimodal intents and effectively mitigate noise issues; ii) How to extract and match latent key intents across modalities. To tackle these challenges, we propose a model-agnostic framework, Intent Representation Learning with Large Language Model (IRLLRec), which leverages large language models (LLMs) to construct multimodal intents and enhance recommendations. Specifically, IRLLRec employs a dual-tower architecture to learn multimodal intent representations. Next, we propose pairwise and translation alignment to eliminate inter-modal differences and enhance robustness against noisy input features. Finally, to better match textual and interaction-based intents, we employ momentum distillation to perform teacher-student learning on fused intent representations. Empirical evaluations on three datasets show that our IRLLRec framework outperforms baselines.Code available at https://github.com/wangyu0627/IRLLRec.

cs.IR↗

arXiv2025

InstantSticker: Realistic Decal Blending via Disentangled Object Reconstruction

We present InstantSticker, a disentangled reconstruction pipeline based on Image-Based Lighting (IBL), which focuses on highly realistic decal blending, simulates stickers attached to the reconstructed surface, and allows for instant editing and real-time rendering. To achieve stereoscopic impression of the decal, we introduce shadow factor into IBL, which can be adaptively optimized during training. This allows the shadow brightness of surfaces to be accurately decomposed rather than baked into the diffuse color, ensuring that the edited texture exhibits authentic shading. To address the issues of warping and blurriness in previous methods, we apply As-Rigid-As-Possible (ARAP) parameterization to pre-unfold a specified area of the mesh and use the local UV mapping combined with a neural texture map to enhance the ability to express high-frequency details in that area. For instant editing, we utilize the Disney BRDF model, explicitly defining material colors with 3-channel diffuse albedo. This enables instant replacement of albedo RGB values during the editing process, avoiding the prolonged optimization required in previous approaches. In our experiment, we introduce the Ratio Variance Warping (RVW) metric to evaluate the local geometric warping of the decal area. Extensive experimental results demonstrate that our method surpasses previous decal blending methods in terms of editing quality, editing speed and rendering speed, achieving the state-of-the-art.

cs.CV↗

arXiv2025

Prospects for constraining interacting dark energy cosmology with gravitational-wave bright sirens detected by future SKA-era pulsar timing arrays

We explore the constraints on cosmological parameters in interacting dark energy (IDE) models described by energy transfer rates $Q = βH ρ_{\rm de}$ and $Q = βH ρ_{\rm c}$, using simulated gravitational-wave (GW) bright siren data from pulsar timing arrays (PTAs) and the Planck 2018 cosmic microwave background (CMB) data. In particular, we simulate a future PTA observation in the FAST/SKA era with 20 millisecond pulsars (MSPs), each having 20\,ns white noise over a 10-year observation span, and demonstrate that this mock dataset significantly improves the constraint precision of key cosmological parameters such as the Hubble constant $H_0$, matter density $Ω_m$, and the coupling parameter $β$. For the IDE model $Q = βH ρ_{\rm de}$, PTA data alone provides tighter constraints on these parameters than the CMB data alone, primarily due to the high sensitivity of GW standard sirens in probing the late universe. Combining PTA and CMB data further enhances the constraints by 43.6\% for $H_0$, 43.2\% for $Ω_m$, and 44.7\% for $β$, relative to using CMB data alone. In contrast, for $Q = βH ρ_{\rm c}$, the CMB data alone constrains $β$ more tightly than the PTA data, due to the stronger impact of this interaction in the early universe. Nevertheless, the PTA+\,CMB combination still yields improvements of 13.3\% for $H_0$, 22.7\% for $Ω_m$, and 18.2\% for $β$. Increasing the number of MSPs in the PTA further tightens all parameter constraints in both IDE models. Our results highlight the great potential of future PTA observations for significantly improving cosmological parameter estimation in IDE models, offering critical insights into the nature of dark energy and its interaction with dark matter.

astro-ph.CO↗

arXiv2025

Cross-correlation between soft X-rays and galaxies A new benchmark for galaxy evolution models

This article presents the construction and validation of complete stellar mass-selected, volume-limited galaxy samples using the Legacy Survey (data release 10) galaxy catalogs, covering $\sim16,800$ deg$^2$ of extra-galactic sky, and extending to redshift $z<0.35$. We measure the correlation function of these galaxies with tiny statistical uncertainties at the percent level and systematic uncertainties up to 5\%. A 4-parameter halo occupation distribution (HOD) model is fitted to retrieve the population of host halos, yielding results on the stellar to halo mass relation consistent with the current models of galaxy formation and evolution. Using these complete galaxy samples, we measure and analyze the cross-correlation (X-corr) between galaxies and all soft X-ray photons observed by SRG/eROSITA in the 0.5-2 keV band over $\sim13,000$ deg$^2$. The cross correlation measurements have unprecedented sub-percent statistical uncertainty and ~5-10\% systematic uncertainty. An extension to the halo model is introduced to interpret the X-corr, decomposing contributions from X-ray point sources, hot gas (CGM), satellites, and the 2-halo term. For low stellar mass thresholds ($\log M^*/M_{\odot}>$ 10, 10.25, 10.5), we find that the point source emission dominates the X-corr at small separation ($r<80$kpc). Then, in the range ($80 2$Mpc), the 2-halo term becomes dominant. Interestingly, there is no scale at which the CGM dominates. In the range ($20<r<200$kpc), the CGM contributes to more than 10\% of the signal. Progressively, with the minimum stellar mass increasing, the CGM emission increases. We constrain the $M_{500c}-L_X$ scaling relation slope, $1.629^{+0.091}_{-0.089}$, at the 5\% level using the samples with the lowest mass threshold.

astro-ph.GA↗

arXiv2025

Individualized Policy Evaluation and Learning under Clustered Network Interference

Although there is now a large literature on policy evaluation and learning, much of the prior work assumes that the treatment assignment of one unit does not affect the outcome of another unit. Unfortunately, ignoring interference can lead to biased policy evaluation and ineffective learned policies. For example, treating influential individuals who have many friends can generate positive spillover effects, thereby improving the overall performance of an individualized treatment rule (ITR). We consider the problem of evaluating and learning an optimal ITR under clustered network interference (also known as partial interference), where clusters of units are sampled from a population and units may influence one another within each cluster. Unlike previous methods that impose strong restrictions on spillover effects, such as anonymous interference, the proposed methodology only assumes a semiparametric structural model, where each unit's outcome is an additive function of individual treatments within the cluster. Under this model, we propose an estimator that can be used to evaluate the empirical performance of an ITR. We show that this estimator is substantially more efficient than the standard inverse probability weighting estimator, which does not impose any assumption about spillover effects. We derive the finite-sample regret bound for a learned ITR, showing that the use of our efficient evaluation estimator leads to the improved performance of learned policies. We consider both experimental and observational studies, and for the latter, we develop a doubly robust estimator that is semiparametrically efficient and yields an optimal regret bound. Finally, we conduct simulation and empirical studies to illustrate the advantages of the proposed methodology.

stat.ME↗

arXiv2025

Briteller: Shining a Light on AI Recommendations for Children

Understanding how AI recommendations work can help the younger generation become more informed and critical consumers of the vast amount of information they encounter daily. However, young learners with limited math and computing knowledge often find AI concepts too abstract. To address this, we developed Briteller, a light-based recommendation system that makes learning tangible. By exploring and manipulating light beams, Briteller enables children to understand an AI recommender system's core algorithmic building block, the dot product, through hands-on interactions. Initial evaluations with ten middle school students demonstrated the effectiveness of this approach, using embodied metaphors, such as "merging light" to represent addition. To overcome the limitations of the physical optical setup, we further explored how AR could embody multiplication, expand data vectors with more attributes, and enhance contextual understanding. Our findings provide valuable insights for designing embodied and tangible learning experiences that make AI concepts more accessible to young learners.

cs.HC↗

arXiv2025

A magnetised Galactic halo from inner Galaxy outflows

Magnetic halos of galaxies are crucial for understanding galaxy evolution, galactic-scale outflows, and feedback from star formation activity. Identifying the magnetised halo of the Milky Way is challenging because of the potential contamination from foreground emission arising in local spiral arms. Additionally, it is unclear how our magnetic halo is influenced by recently revealed large-scale structures such as the X-ray emitting eROSITA Bubbles. Here we report the identification of several kpc-scale magnetised structures based on their polarized radio emission and their gamma-ray counterparts, which can be interpreted as the radiation of relativistic electrons in the Galactic magnetic halo. These non-thermal structures extend far above and below the Galactic plane and are spatially coincident with the thermal X-ray emission from the eROSITA Bubbles. The morphological consistency of these structures suggests a common origin, which can be sustained by Galactic outflows driven by active star-forming regions located in the Galactic Disc at 3-5 kpc from the Galactic Centre. These results reveal how X-ray-emitting and magnetised halos of spiral galaxies can be related to intense star formation activities and suggest that the X-shaped coherent magnetic structures observed in their halos can stem from galaxy outflows.

astro-ph.GA↗