arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 667 records · Page 37Linked to original sources

arXiv2024

VFLGAN: Vertical Federated Learning-based Generative Adversarial Network for Vertically Partitioned Data Publication

In the current artificial intelligence (AI) era, the scale and quality of the dataset play a crucial role in training a high-quality AI model. However, good data is not a free lunch and is always hard to access due to privacy regulations like the General Data Protection Regulation (GDPR). A potential solution is to release a synthetic dataset with a similar distribution to that of the private dataset. Nevertheless, in some scenarios, it has been found that the attributes needed to train an AI model belong to different parties, and they cannot share the raw data for synthetic data publication due to privacy regulations. In PETS 2023, Xue et al. proposed the first generative adversary network-based model, VertiGAN, for vertically partitioned data publication. However, after thoroughly investigating, we found that VertiGAN is less effective in preserving the correlation among the attributes of different parties. This article proposes a Vertical Federated Learning-based Generative Adversarial Network, VFLGAN, for vertically partitioned data publication to address the above issues. Our experimental results show that compared with VertiGAN, VFLGAN significantly improves the quality of synthetic data. Taking the MNIST dataset as an example, the quality of the synthetic dataset generated by VFLGAN is 3.2 times better than that generated by VertiGAN w.r.t. the Fréchet Distance. We also designed a more efficient and effective Gaussian mechanism for the proposed VFLGAN to provide the synthetic dataset with a differential privacy guarantee. On the other hand, differential privacy only gives the upper bound of the worst-case privacy guarantee. This article also proposes a practical auditing scheme that applies membership inference attacks to estimate privacy leakage through the synthetic dataset.

cs.LG↗

arXiv2024

MAP: Model Aggregation and Personalization in Federated Learning with Incomplete Classes

In some real-world applications, data samples are usually distributed on local devices, where federated learning (FL) techniques are proposed to coordinate decentralized clients without directly sharing users' private data. FL commonly follows the parameter server architecture and contains multiple personalization and aggregation procedures. The natural data heterogeneity across clients, i.e., Non-I.I.D. data, challenges both the aggregation and personalization goals in FL. In this paper, we focus on a special kind of Non-I.I.D. scene where clients own incomplete classes, i.e., each client can only access a partial set of the whole class set. The server aims to aggregate a complete classification model that could generalize to all classes, while the clients are inclined to improve the performance of distinguishing their observed classes. For better model aggregation, we point out that the standard softmax will encounter several problems caused by missing classes and propose "restricted softmax" as an alternative. For better model personalization, we point out that the hard-won personalized models are not well exploited and propose "inherited private model" to store the personalization experience. Our proposed algorithm named MAP could simultaneously achieve the aggregation and personalization goals in FL. Abundant experimental studies verify the superiorities of our algorithm.

cs.LG↗

arXiv2024

Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworks

Multi-modal learning aims to enhance performance by unifying models from various modalities but often faces the "modality imbalance" problem in real data, leading to a bias towards dominant modalities and neglecting others, thereby limiting its overall effectiveness. To address this challenge, the core idea is to balance the optimization of each modality to achieve a joint optimum. Existing approaches often employ a modal-level control mechanism for adjusting the update of each modal parameter. However, such a global-wise updating mechanism ignores the different importance of each parameter. Inspired by subnetwork optimization, we explore a uniform sampling-based optimization strategy and find it more effective than global-wise updating. According to the findings, we further propose a novel importance sampling-based, element-wise joint optimization method, called Adaptively Mask Subnetworks Considering Modal Significance(AMSS). Specifically, we incorporate mutual information rates to determine the modal significance and employ non-uniform adaptive sampling to select foreground subnetworks from each modality for parameter updates, thereby rebalancing multi-modal learning. Additionally, we demonstrate the reliability of the AMSS strategy through convergence analysis. Building upon theoretical insights, we further enhance the multi-modal mask subnetwork strategy using unbiased estimation, referred to as AMSS+. Extensive experiments reveal the superiority of our approach over comparison methods.

cs.CV↗

arXiv2024

Universal Prompt Tuning for Graph Neural Networks

In recent years, prompt tuning has sparked a research surge in adapting pre-trained models. Unlike the unified pre-training strategy employed in the language field, the graph field exhibits diverse pre-training strategies, posing challenges in designing appropriate prompt-based tuning methods for graph neural networks. While some pioneering work has devised specialized prompting functions for models that employ edge prediction as their pre-training tasks, these methods are limited to specific pre-trained GNN models and lack broader applicability. In this paper, we introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF) for pre-trained GNN models under any pre-training strategy. GPF operates on the input graph's feature space and can theoretically achieve an equivalent effect to any form of prompting function. Consequently, we no longer need to illustrate the prompting function corresponding to each pre-training strategy explicitly. Instead, we employ GPF to obtain the prompted graph for the downstream task in an adaptive manner. We provide rigorous derivations to demonstrate the universality of GPF and make guarantee of its effectiveness. The experimental results under various pre-training strategies indicate that our method performs better than fine-tuning, with an average improvement of about 1.4% in full-shot scenarios and about 3.2% in few-shot scenarios. Moreover, our method significantly outperforms existing specialized prompt-based tuning methods when applied to models utilizing the pre-training strategy they specialize in. These numerous advantages position our method as a compelling alternative to fine-tuning for downstream adaptations.

cs.LG↗

arXiv2024

Cymatics Cup: Shape-Changing Drinks by Leveraging Cymatics

To enhance the dining experience, prior studies in Human-Computer Interaction (HCI) and gastrophysics have demonstrated that modifying the static shape of solid foods can amplify taste perception. However, the exploration of dynamic shape-changing mechanisms in liquid foods remains largely untapped. In the present study, we employ cymatics, a scientific discipline focused on utilizing sound frequencies to generate patterns in liquids and particles to augment the drinking experience. Utilizing speakers, we dynamically reshaped liquids exhibiting five distinct taste profiles and evaluated resultant changes in taste perception and drinking experience. Our research objectives extend beyond merely augmenting taste from visual to tactile sensations; we also prioritize the experiential aspects of drinking. Through a series of experiments and workshops, we revealed a significant impact on taste perception and overall drinking experience when mediated by cymatics effects. Building upon these findings, we designed and developed tableware to integrate cymatics principles into gastronomic experiences.

cs.HC↗

arXiv2024

eDIG-CHANGES II: Project Design and Initial Results on NGC 3556

The extraplanar diffuse ionized gas (eDIG) represents ionized gases traced by optical/UV lines beyond the stellar extent of galaxies. We herein introduce a novel multi-slit narrow-band spectroscopy method to conduct spatially resolved spectroscopy of the eDIG around a sample of nearby edge-on disk galaxies (eDIG-CHANGES). In this paper, we introduce the project design and major scientific goals, as well as a pilot study of NGC 3556 (M108). The eDIG is detected to a vertical extent of a few kpc above the disk, comparable to the X-ray and radio images. We do not see significant vertical variation of the [N II]/H$α$ line ratio. A rough examination of the pressure balance between different circum-galactic medium (CGM) phases indicates the magnetic field is in a rough pressure balance with the X-ray emitting hot gas, and may play an important role in the global motion of both the eDIG and the hot gas in the lower halo. At the location of an HST/COS observed UV bright background AGN $\sim29\rm~kpc$ from the center of NGC 3556, the magnetic pressure is much lower than that of the hot gas and the ionized gas traced by UV absorption lines, although the extrapolation of the pressure profiles may cause some biases in this comparison. By comparing the position-velocity diagrams of the optical and CO lines, we also find the dynamics of the two gas phases are consistent with each other, with no evidence of a global inflow/outflow and a maximum rotation velocity of $\sim150\rm~km~s^{-1}$.

astro-ph.GA↗

arXiv2024

Pressure Balance and Energy Budget of the Nuclear Superbubble of NGC 3079

Superbubbles in the nuclear region of galaxies could be produced by the AGN or nuclear starburst via different driving forces. We report analysis of the multi-wavelength data of the kpc-scale nuclear superbubble in NGC 3079, in order to probe the mechanisms driving the expansion of the superbubble. Based on the Chandra X-ray observations, we derive the hot gas thermal pressure inside the bubble, which is about one order of magnitude higher than that of the warm ionized gas traced by optical lines. We derive a [C II]-based star formation rate of ${\rm SFR}\sim1.3\rm~M_\odot~{\rm yr}^{-1}$ from the nuclear region using the SOFIA/FIFI-LS observation. This SFR infers a radiation pressure toward the bubble shells much lower than the thermal pressure of the gases. The VLA radio image infers a magnetic pressure at the northeast cap above the superbubble less than the thermal pressure of the hot gas enclosed in the bubble, but has a clearly larger extension. The magnetic field may thus still help to reconcile the expansion of the bubble. The observed thermal energy of the hot gas enclosed in the bubble requires an energy injection rate of $\gtrsim10^{42}\rm~ergs~s^{-1}$ within the bubble's dynamical age, which is probably larger than the power provided by the current nuclear starburst and the parsec-scale jet. If this is true, stronger past AGN activity may provide an alternative energy source to drive the observed bubble expansion.

astro-ph.GA↗

arXiv2024

JobFormer: Skill-Aware Job Recommendation with Semantic-Enhanced Transformer

Job recommendation aims to provide potential talents with suitable job descriptions (JDs) consistent with their career trajectory, which plays an essential role in proactive talent recruitment. In real-world management scenarios, the available JD-user records always consist of JDs, user profiles, and click data, in which the user profiles are typically summarized as the user's skill distribution for privacy reasons. Although existing sophisticated recommendation methods can be directly employed, effective recommendation still has challenges considering the information deficit of JD itself and the natural heterogeneous gap between JD and user profile. To address these challenges, we proposed a novel skill-aware recommendation model based on the designed semantic-enhanced transformer to parse JDs and complete personalized job recommendation. Specifically, we first model the relative items of each JD and then adopt an encoder with the local-global attention mechanism to better mine the intra-job and inter-job dependencies from JD tuples. Moreover, we adopt a two-stage learning strategy for skill-aware recommendation, in which we utilize the skill distribution to guide JD representation learning in the recall stage, and then combine the user profiles for final prediction in the ranking stage. Consequently, we can embed rich contextual semantic representations for learning JDs, while skill-aware recommendation provides effective JD-user joint representation for click-through rate (CTR) prediction. To validate the superior performance of our method for job recommendation, we present a thorough empirical analysis of large-scale real-world and public datasets to demonstrate its effectiveness and interpretability.

cs.IR↗

arXiv2024

Flatness of anisotropic minimal graphs in $\mathbb{R}^{n+1}$

We prove a Bernstein theorem for $Φ$-anisotropic minimal hypersurfaces in all dimensional Euclidean spaces that the only entire smooth solutions $u: \mathbb{R}^{n}\rightarrow \mathbb{R}$ of $Φ$-anisotropic minimal hypersurfaces equation are linear functions provided the anisotropic area functional integrand $Φ$ is sufficiently $C^{3}$-close to classical area functional integrand and $|\nabla u(x)|=o(|x|^{\varepsilon})$ for $\varepsilon\leq \varepsilon_{0}(n, Φ)$ with the constant $\varepsilon_{0}(n, Φ)>0$.

math.AP↗

arXiv2024

The Diffusive Ultrasound Modulated Bioluminescence Tomography with Partial Data and Uncertain Optical Parameters

The paper studies an imaging problem in the diffusive ultrasound-modulated bioluminescence tomography with partial boundary measurement in an anisotropic medium. Assuming plane-wave modulation, we transform the imaging problem to an inverse problem with internal data, and derive a reconstruction procedure to recover the bioluminescent source. Subsequently, an uncertainty quantification estimate is established to assess the robustness of the reconstruction. To facilitate practical implementation, we discretize the diffusive model using the staggered grid scheme, resulting in a discrete formulation of the UMBLT inverse problem. A discrete reconstruction procedure is then presented along with a discrete uncertainty quantification estimate. Finally, the reconstruction procedure is quantitatively validated through numerical examples to demonstrate the efficacy and reliability of the proposed approach and estimates.

math.AP↗

arXiv2024

Imaging transformer for MRI denoising with the SNR unit training: enabling generalization across field-strengths, imaging contrasts, and anatomy

The ability to recover MRI signal from noise is key to achieve fast acquisition, accurate quantification, and high image quality. Past work has shown convolutional neural networks can be used with abundant and paired low and high-SNR images for training. However, for applications where high-SNR data is difficult to produce at scale (e.g. with aggressive acceleration, high resolution, or low field strength), training a new denoising network using a large quantity of high-SNR images can be infeasible. In this study, we overcome this limitation by improving the generalization of denoising models, enabling application to many settings beyond what appears in the training data. Specifically, we a) develop a training scheme that uses complex MRIs reconstructed in the SNR units (i.e., the images have a fixed noise level, SNR unit training) and augments images with realistic noise based on coil g-factor, and b) develop a novel imaging transformer (imformer) to handle 2D, 2D+T, and 3D MRIs in one model architecture. Through empirical evaluation, we show this combination improves performance compared to CNN models and improves generalization, enabling a denoising model to be used across field-strengths, image contrasts, and anatomy.

eess.IV↗

arXiv2024

Interpretable Dimensionality Reduction by Feature Preserving Manifold Approximation and Projection

Nonlinear dimensionality reduction lacks interpretability due to the absence of source features in low-dimensional embedding space. We propose an interpretable method featMAP to preserve source features by tangent space embedding. The core of our proposal is to utilize local singular value decomposition (SVD) to approximate the tangent space which is embedded to low-dimensional space by maintaining the alignment. Based on the embedding tangent space, featMAP enables the interpretability by locally demonstrating the source features and feature importance. Furthermore, featMAP embeds the data points by anisotropic projection to preserve the local similarity and original density. We apply featMAP to interpreting digit classification, object detection and MNIST adversarial examples. FeatMAP uses source features to explicitly distinguish the digits and objects and to explain the misclassification of adversarial examples. We also compare featMAP with other state-of-the-art methods on local and global metrics.

cs.CV↗

arXiv2024

The Solution for the CVPR 2023 1st foundation model challenge-Track2

In this paper, we propose a solution for cross-modal transportation retrieval. Due to the cross-domain problem of traffic images, we divide the problem into two sub-tasks of pedestrian retrieval and vehicle retrieval through a simple strategy. In pedestrian retrieval tasks, we use IRRA as the base model and specifically design an Attribute Classification to mine the knowledge implied by attribute labels. More importantly, We use the strategy of Inclusion Relation Matching to make the image-text pairs with inclusion relation have similar representation in the feature space. For the vehicle retrieval task, we use BLIP as the base model. Since aligning the color attributes of vehicles is challenging, we introduce attribute-based object detection techniques to add color patch blocks to vehicle images for color data augmentation. This serves as strong prior information, helping the model perform the image-text alignment. At the same time, we incorporate labeled attributes into the image-text alignment loss to learn fine-grained alignment and prevent similar images and texts from being incorrectly separated. Our approach ranked first in the final B-board test with a score of 70.9.

cs.CV↗

arXiv2024

Determining the chemical composition of diamagnetic mixed solids via measurements of the magnetic susceptibility

Mixed solid compounds are employed in a vast array of applications so an accurate determination of their chemical compositions is of crucial importance. All current characterization methods require specially-treated samples so the availability of a more practical method with similar accuracy should alleviate the quantification process. In this work, we show how the doping concentration $δ$ (or isotope concentration) of a mixed solid compound in powdered form, where both parent compounds are diamagnetic, can be obtained from the measurement of the mass magnetization. We exploit the additive nature of the molar magnetic susceptibility $χ_{Mol}$ and molar mass to construct two equations with the same two unknowns in the $χ_{Mol}$ vs. $δ$ space to simultaneously solve $χ_{Mol}$ and $δ$ of a mixed solid. Eight examples are provided to show the wide applicability of this method: NH$_{4(1-δ)}$D$_{4δ}$Br (where D = $^2$H), NH$_4$I$_{1-δ}$Br$_δ$, (NH$_4$H$_2$)$_{1-δ}$(ND$_4$D$_2$)$_δ$PO$_4$, C$_{48}$H$_{22+6δ}$Br$_{6(1-δ)}$O$_{32}$Zr$_6$, [creatine]$_{1-δ}$[$_D$-glucose]$_δ$, [$_L$-glutamic acid]$_{1-δ}$[$_L$-leucine]$_δ$, [terephthalic acid]$_{1-δ}$[trimesic acid]$_δ$ and [p-terphenyl]$_{1-δ}$[triphenylphosphine]$_δ$. Experimental errors of ~1.2% were obtained for $δ$ from average sample masses of 16.6 mg in powdered form rendering the presented approach an attractive choice for characterizing the ratios of mixed solids.

cond-mat.mtrl-sci↗

arXiv2024

High-Resolution Image Translation Model Based on Grayscale Redefinition

Image-to-image translation is a technique that focuses on transferring images from one domain to another while maintaining the essential content representations. In recent years, image-to-image translation has gained significant attention and achieved remarkable advancements due to its diverse applications in computer vision and image processing tasks. In this work, we propose an innovative method for image translation between different domains. For high-resolution image translation tasks, we use a grayscale adjustment method to achieve pixel-level translation. For other tasks, we utilize the Pix2PixHD model with a coarse-to-fine generator, multi-scale discriminator, and improved loss to enhance the image translation performance. On the other hand, to tackle the issue of sparse training data, we adopt model weight initialization from other task to optimize the performance of the current task.

eess.IV↗

arXiv2024

NJUST-KMG at TRAC-2024 Tasks 1 and 2: Offline Harm Potential Identification

This report provide a detailed description of the method that we proposed in the TRAC-2024 Offline Harm Potential dentification which encloses two sub-tasks. The investigation utilized a rich dataset comprised of social media comments in several Indian languages, annotated with precision by expert judges to capture the nuanced implications for offline context harm. The objective assigned to the participants was to design algorithms capable of accurately assessing the likelihood of harm in given situations and identifying the most likely target(s) of offline harm. Our approach ranked second in two separate tracks, with F1 values of 0.73 and 0.96 respectively. Our method principally involved selecting pretrained models for finetuning, incorporating contrastive learning techniques, and culminating in an ensemble approach for the test set.

cs.CL↗

arXiv2024

Solution for Emotion Prediction Competition of Workshop on Emotionally and Culturally Intelligent AI

This report provide a detailed description of the method that we explored and proposed in the WECIA Emotion Prediction Competition (EPC), which predicts a person's emotion through an artistic work with a comment. The dataset of this competition is ArtELingo, designed to encourage work on diversity across languages and cultures. The dataset has two main challenges, namely modal imbalance problem and language-cultural differences problem. In order to address this issue, we propose a simple yet effective approach called single-multi modal with Emotion-Cultural specific prompt(ECSP), which focuses on using the single modal message to enhance the performance of multimodal models and a well-designed prompt to reduce cultural differences problem. To clarify, our approach contains two main blocks: (1)XLM-R\cite{conneau2019unsupervised} based unimodal model and X$^2$-VLM\cite{zeng2022x} based multimodal model (2) Emotion-Cultural specific prompt. Our approach ranked first in the final test with a score of 0.627.

cs.AI↗

arXiv2024

Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach

Parameter-efficient fine-tuning for pre-trained Vision Transformers aims to adeptly tailor a model to downstream tasks by learning a minimal set of new adaptation parameters while preserving the frozen majority of pre-trained parameters. Striking a balance between retaining the generalizable representation capacity of the pre-trained model and acquiring task-specific features poses a key challenge. Currently, there is a lack of focus on guiding this delicate trade-off. In this study, we approach the problem from the perspective of Singular Value Decomposition (SVD) of pre-trained parameter matrices, providing insights into the tuning dynamics of existing methods. Building upon this understanding, we propose a Residual-based Low-Rank Rescaling (RLRR) fine-tuning strategy. This strategy not only enhances flexibility in parameter tuning but also ensures that new parameters do not deviate excessively from the pre-trained model through a residual design. Extensive experiments demonstrate that our method achieves competitive performance across various downstream image classification tasks, all while maintaining comparable new parameters. We believe this work takes a step forward in offering a unified perspective for interpreting existing methods and serves as motivation for the development of new approaches that move closer to effectively considering the crucial trade-off mentioned above. Our code is available at \href{https://github.com/zstarN70/RLRR.git}{https://github.com/zstarN70/RLRR.git}.

cs.CV↗