arXiv subjects

Yue Yu

Publications and source records attributed to Yue Yu.

At least 253 records · Page 14Linked to original sources

arXiv2024

Octave-wide broadening of ultraviolet dispersive wave driven by soliton-splitting dynamics

Coherent dispersive wave emission, as an important phenomenon of soliton dynamics, manifests itself in multiple platforms of nonlinear optics from fibre waveguides to integrated photonics. Limited by its resonance nature, efficient generation of coherent dispersive wave with ultra-broad bandwidth has, however, proved difficult to realize. Here, we unveil a new regime of soliton dynamics in which the dispersive wave emission process strongly couples with the splitting dynamics of the driving pulse. High-order dispersion and self-steepening effects, accumulated over soliton self-compression, break the system symmetry, giving rise to high-efficiency generation of coherent dispersive wave in the ultraviolet region. Simultaneously, asymmetric soliton splitting results in the appearance of a temporally-delayed ultrashort pulse with high intensity, overlapping and copropagating with the dispersive wave pulse. Intense cross-phase modulations lead to octave-wide broadening of the dispersive wave spectrum, covering 200 to 400 nm wavelengths. The highly-coherent, octave-wide ultraviolet spectrum, generated from the simple capillary fibre set-up, is in great demand for time-resolved spectroscopy, ultrafast electron microscopy and frequency metrology applications, and the critical role of the secondary pulse in this process reveals some new opportunities for all-optical control of versatile soliton dynamics.

physics.optics↗

arXiv2024

VM-UNET-V2 Rethinking Vision Mamba UNet for Medical Image Segmentation

In the field of medical image segmentation, models based on both CNN and Transformer have been thoroughly investigated. However, CNNs have limited modeling capabilities for long-range dependencies, making it challenging to exploit the semantic information within images fully. On the other hand, the quadratic computational complexity poses a challenge for Transformers. Recently, State Space Models (SSMs), such as Mamba, have been recognized as a promising method. They not only demonstrate superior performance in modeling long-range interactions, but also preserve a linear computational complexity. Inspired by the Mamba architecture, We proposed Vison Mamba-UNetV2, the Visual State Space (VSS) Block is introduced to capture extensive contextual information, the Semantics and Detail Infusion (SDI) is introduced to augment the infusion of low-level and high-level features. We conduct comprehensive experiments on the ISIC17, ISIC18, CVC-300, CVC-ClinicDB, Kvasir, CVC-ColonDB and ETIS-LaribPolypDB public datasets. The results indicate that VM-UNetV2 exhibits competitive performance in medical image segmentation tasks. Our code is available at https://github.com/nobodyplayer1/VM-UNetV2.

eess.IV↗

arXiv2024

ACT-MNMT Auto-Constriction Turning for Multilingual Neural Machine Translation

Large language model (LLM) has achieved promising performance in multilingual machine translation tasks through zero/few-shot prompts or prompt-tuning. However, due to the mixture of multilingual data during the pre-training of LLM, the LLM-based translation models face the off-target issue in both prompt-based methods, including a series of phenomena, namely instruction misunderstanding, translation with wrong language and over-generation. For this issue, this paper introduces an \textbf{\underline{A}}uto-\textbf{\underline{C}}onstriction \textbf{\underline{T}}urning mechanism for \textbf{\underline{M}}ultilingual \textbf{\underline{N}}eural \textbf{\underline{M}}achine \textbf{\underline{T}}ranslation (\model), which is a novel supervised fine-tuning mechanism and orthogonal to the traditional prompt-based methods. In this method, \model automatically constructs a constrained template in the target side by adding trigger tokens ahead of the ground truth. Furthermore, trigger tokens can be arranged and combined freely to represent different task semantics, and they can be iteratively updated to maximize the label likelihood. Experiments are performed on WMT test sets with multiple metrics, and the experimental results demonstrate that \model achieves substantially improved performance across multiple translation directions and reduce the off-target phenomena in the translation.

cs.CL↗

arXiv2024

BrainMass: Advancing Brain Network Analysis for Diagnosis with Large-scale Self-Supervised Learning

Foundation models pretrained on large-scale datasets via self-supervised learning demonstrate exceptional versatility across various tasks. Due to the heterogeneity and hard-to-collect medical data, this approach is especially beneficial for medical image analysis and neuroscience research, as it streamlines broad downstream tasks without the need for numerous costly annotations. However, there has been limited investigation into brain network foundation models, limiting their adaptability and generalizability for broad neuroscience studies. In this study, we aim to bridge this gap. In particular, (1) we curated a comprehensive dataset by collating images from 30 datasets, which comprises 70,781 samples of 46,686 participants. Moreover, we introduce pseudo-functional connectivity (pFC) to further generates millions of augmented brain networks by randomly dropping certain timepoints of the BOLD signal. (2) We propose the BrainMass framework for brain network self-supervised learning via mask modeling and feature alignment. BrainMass employs Mask-ROI Modeling (MRM) to bolster intra-network dependencies and regional specificity. Furthermore, Latent Representation Alignment (LRA) module is utilized to regularize augmented brain networks of the same participant with similar topological properties to yield similar latent representations by aligning their latent embeddings. Extensive experiments on eight internal tasks and seven external brain disorder diagnosis tasks show BrainMass's superior performance, highlighting its significant generalizability and adaptability. Nonetheless, BrainMass demonstrates powerful few/zero-shot learning abilities and exhibits meaningful interpretation to various diseases, showcasing its potential use for clinical applications.

cs.CE↗

arXiv2024

Spin-orbit enabled unconventional Stoner magnetism

The Stoner instability remains a cornerstone for understanding metallic ferromagnets. This instability captures the interplay of Coulomb repulsion, Pauli exclusion, and two-fold fermionic spin degeneracy. In materials with spin-orbit coupling, this fermionic spin is generalized to a two-fold degenerate pseudospin which is typically believed to have symmetry properties as spin. Here we identify a distinct symmetry of this pseudospin that forbids it to couple to a Zeeman field. This `spinless' property is required to exist in five non-symmorphic space groups and has non-trivial implications for superconductivity and magnetism. With Coulomb repulsion, Fermi surfaces composed primarily of this spinless pseudospin feature give rise to Stoner instabilities into magnetic states that are qualitatively different than ferromagnets. These spinless-pseudospin ferromagnets break time-reversal symmetry, have a vanishing magnetization, are non-collinear, and exhibit altermagnetic-like energy band spin-splittings. In superconductors, for all pairing symmetries and field orientations, this spinless pseudospin extinguishes paramagnetic limiting. We discuss applications to superconducting UCoGe and magnetic NiS$_{2-x}$Se$_x$.

cond-mat.str-el↗

arXiv2024

HiGen: Hierarchy-Aware Sequence Generation for Hierarchical Text Classification

Hierarchical text classification (HTC) is a complex subtask under multi-label text classification, characterized by a hierarchical label taxonomy and data imbalance. The best-performing models aim to learn a static representation by combining document and hierarchical label information. However, the relevance of document sections can vary based on the hierarchy level, necessitating a dynamic document representation. To address this, we propose HiGen, a text-generation-based framework utilizing language models to encode dynamic text representations. We introduce a level-guided loss function to capture the relationship between text and label name semantics. Our approach incorporates a task-specific pretraining strategy, adapting the language model to in-domain knowledge and significantly enhancing performance for classes with limited examples. Furthermore, we present a new and valuable dataset called ENZYME, designed for HTC, which comprises articles from PubMed with the goal of predicting Enzyme Commission (EC) numbers. Through extensive experiments on the ENZYME dataset and the widely recognized WOS and NYT datasets, our methodology demonstrates superior performance, surpassing existing approaches while efficiently handling data and mitigating class imbalance. The data and code will be released publicly.

cs.CL↗

arXiv2024

Chain-of-Specificity: An Iteratively Refining Method for Eliciting Knowledge from Large Language Models

Large Language Models (LLMs) exhibit remarkable generative capabilities, enabling the generation of valuable information. Despite these advancements, previous research found that LLMs sometimes struggle with adhering to specific constraints (e.g., in specific place or at specific time), at times even overlooking them, which leads to responses that are either too generic or not fully satisfactory. Existing approaches attempted to address this issue by decomposing or rewriting input instructions, yet they fall short in adequately emphasizing specific constraints and in unlocking the underlying knowledge (e.g., programming within the context of software development). In response, this paper proposes a simple yet effective method named Chain-of-Specificity (CoS). Specifically, CoS iteratively emphasizes the specific constraints in the input instructions, unlocks knowledge within LLMs, and refines responses. Experiments conducted on publicly available and self-build complex datasets demonstrate that CoS outperforms existing methods in enhancing generated content especially for the specificity. Besides, as the number of specific constraints increase, other baselines falter, while CoS still performs well. Moreover, we show that distilling responses generated by CoS effectively enhances the ability of smaller models to follow the constrained instructions. Resources of this paper will be released for further research.

cs.AI↗

arXiv2024

Endowing Pre-trained Graph Models with Provable Fairness

Pre-trained graph models (PGMs) aim to capture transferable inherent structural properties and apply them to different downstream tasks. Similar to pre-trained language models, PGMs also inherit biases from human society, resulting in discriminatory behavior in downstream applications. The debiasing process of existing fair methods is generally coupled with parameter optimization of GNNs. However, different downstream tasks may be associated with different sensitive attributes in reality, directly employing existing methods to improve the fairness of PGMs is inflexible and inefficient. Moreover, most of them lack a theoretical guarantee, i.e., provable lower bounds on the fairness of model predictions, which directly provides assurance in a practical scenario. To overcome these limitations, we propose a novel adapter-tuning framework that endows pre-trained graph models with provable fairness (called GraphPAR). GraphPAR freezes the parameters of PGMs and trains a parameter-efficient adapter to flexibly improve the fairness of PGMs in downstream tasks. Specifically, we design a sensitive semantic augmenter on node representations, to extend the node representations with different sensitive attribute semantics for each node. The extended representations will be used to further train an adapter, to prevent the propagation of sensitive attribute semantics from PGMs to task predictions. Furthermore, with GraphPAR, we quantify whether the fairness of each node is provable, i.e., predictions are always fair within a certain range of sensitive attribute semantics. Experimental evaluations on real-world datasets demonstrate that GraphPAR achieves state-of-the-art prediction performance and fairness on node classification task. Furthermore, based on our GraphPAR, around 90\% nodes have provable fairness.

cs.LG↗

arXiv2024

How Many Validation Labels Do You Need? Exploring the Design Space of Label-Efficient Model Ranking

This paper presents LEMR (Label-Efficient Model Ranking) and introduces the MoraBench Benchmark. LEMR is a novel framework that minimizes the need for costly annotations in model selection by strategically annotating instances from an unlabeled validation set. To evaluate LEMR, we leverage the MoraBench Benchmark, a comprehensive collection of model outputs across diverse scenarios. Our extensive evaluation across 23 different NLP tasks in semi-supervised learning, weak supervision, and prompt selection tasks demonstrates LEMR's effectiveness in significantly reducing labeling costs. Key findings highlight the impact of suitable ensemble methods, uncertainty sampling strategies, and model committee selection in enhancing model ranking accuracy. LEMR, supported by the insights from MoraBench, provides a cost-effective and accurate solution for model selection, especially valuable in resource-constrained environments.

cs.LG↗

arXiv2024

Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind

When reading a story, humans can quickly understand new fictional characters with a few observations, mainly by drawing analogies to fictional and real people they already know. This reflects the few-shot and meta-learning essence of humans' inference of characters' mental states, i.e., theory-of-mind (ToM), which is largely ignored in existing research. We fill this gap with a novel NLP dataset, ToM-in-AMC, the first assessment of machines' meta-learning of ToM in a realistic narrative understanding scenario. Our dataset consists of ~1,000 parsed movie scripts, each corresponding to a few-shot character understanding task that requires models to mimic humans' ability of fast digesting characters with a few starting scenes in a new movie. We propose a novel ToM prompting approach designed to explicitly assess the influence of multiple ToM dimensions. It surpasses existing baseline models, underscoring the significance of modeling multiple ToM dimensions for our task. Our extensive human study verifies that humans are capable of solving our problem by inferring characters' mental states based on their previously seen movies. In comparison, our systems based on either state-of-the-art large language models (GPT-4) or meta-learning algorithms lags >20% behind, highlighting a notable limitation in existing approaches' ToM capabilities.

cs.CL↗

arXiv2024

Peridynamic Neural Operators: A Data-Driven Nonlocal Constitutive Model for Complex Material Responses

Neural operators, which can act as implicit solution operators of hidden governing equations, have recently become popular tools for learning the responses of complex real-world physical systems. Nevertheless, most neural operator applications have thus far been data-driven and neglect the intrinsic preservation of fundamental physical laws in data. In this work, we introduce a novel integral neural operator architecture called the Peridynamic Neural Operator (PNO) that learns a nonlocal constitutive law from data. This neural operator provides a forward model in the form of state-based peridynamics, with objectivity and momentum balance laws automatically guaranteed. As applications, we demonstrate the expressivity and efficacy of our model in learning complex material behaviors from both synthetic and experimental data sets. We show that, owing to its ability to capture complex responses, our learned neural operator achieves improved accuracy and efficiency compared to baseline models that use predefined constitutive laws. Moreover, by preserving the essential physical laws within the neural network architecture, the PNO is robust in treating noisy data. The method shows generalizability to different domain configurations, external loadings, and discretizations.

cond-mat.mtrl-sci↗

arXiv2024

Training and Serving System of Foundation Models: A Comprehensive Survey

Foundation models (e.g., ChatGPT, DALL-E, PengCheng Mind, PanGu-$Σ$) have demonstrated extraordinary performance in key technological areas, such as natural language processing and visual recognition, and have become the mainstream trend of artificial general intelligence. This has led more and more major technology giants to dedicate significant human and financial resources to actively develop their foundation model systems, which drives continuous growth of these models' parameters. As a result, the training and serving of these models have posed significant challenges, including substantial computing power, memory consumption, bandwidth demands, etc. Therefore, employing efficient training and serving strategies becomes particularly crucial. Many researchers have actively explored and proposed effective methods. So, a comprehensive survey of them is essential for system developers and researchers. This paper extensively explores the methods employed in training and serving foundation models from various perspectives. It provides a detailed categorization of these state-of-the-art methods, including finer aspects such as network, computing, and storage. Additionally, the paper summarizes the challenges and presents a perspective on the future development direction of foundation model systems. Through comprehensive discussion and analysis, it hopes to provide a solid theoretical basis and practical guidance for future research and applications, promoting continuous innovation and development in foundation model systems.

cs.AI↗

arXiv2024

The Fate of Simple Organics on Titan's Surface: A Theoretical Perspective

Atmospheric photochemistry on Titan continuously transforms methane and nitrogen gases into various organic compounds. This study explores the fate of these molecules when they land on Titan's surface. Our analytical exploration reveals that most simple organics found in Titan's atmosphere, including all nitriles, triple-bonded hydrocarbons, and benzene, land as solids. Only a few compounds are in the liquid phase, while only ethylene remains gaseous. For the simple organics that land as solids, we further examine their interactions with Titan's lake liquids. Utilizing principles of buoyancy, we found that flotation can be achieved via porosity-induced (25-60% porosity) or capillary force-induced buoyancy for HCN ices on ethane-rich lakes. Otherwise, these ices would sink and become lakebed sediments. By evaluating the timescale of flotation, our findings suggest that porosity-induced flotation of millimeter-sized and larger sediments is the only plausible mechanism for floating solids to explain the transient "magic islands" phenomena on Titan's lakes.

astro-ph.EP↗

arXiv2024

Noise-Aware and Equitable Urban Air Traffic Management: An Optimization Approach

Urban air mobility (UAM), a transformative concept for the transport of passengers and cargo, faces several integration challenges in complex urban environments. Community acceptance of aircraft noise is among the most noticeable of these challenges when launching or scaling up a UAM system. Properly managing community noise is fundamental to establishing a UAM system that is environmentally and socially sustainable. In this work, we develop a holistic and equitable approach to manage UAM air traffic and its community noise impact in urban environments. The proposed approach is a hybrid approach that considers a mix of different noise mitigation strategies, including limiting the number of operations, cruising at higher altitudes, and ambient noise masking. We tackle the problem through the lens of network system control and formulate a multi-objective optimization model for managing traffic flow in a multi-layer UAM network while concurrently pursuing demand fulfillment, noise control, and energy saving. Further, we use a social welfare function in the optimization model as the basis for the efficiency-fairness trade-off in both demand fulfillment and noise control. We apply the proposed approach to a comprehensive case study in the city of Austin and perform design trade-offs through both visual and quantitative analyses.

eess.SY↗

arXiv2023

Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles

Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimization, where beyond a certain threshold, the pursuit of higher rewards leads to a decline in human preferences. In this paper, we observe the weakness of KL regularization which is commonly employed in existing RLHF methods to address overoptimization. To mitigate this limitation, we scrutinize the RLHF objective in the offline dataset and propose uncertainty-penalized RLHF (UP-RLHF), which incorporates uncertainty regularization during RL-finetuning. To enhance the uncertainty quantification abilities for reward models, we first propose a diverse low-rank adaptation (LoRA) ensemble by maximizing the nuclear norm of LoRA matrix concatenations. Then we optimize policy models utilizing penalized rewards, determined by both rewards and uncertainties provided by the diverse reward LoRA ensembles. Our experimental results, based on two real human preference datasets, showcase the effectiveness of diverse reward LoRA ensembles in quantifying reward uncertainty. Additionally, uncertainty regularization in UP-RLHF proves to be pivotal in mitigating overoptimization, thereby contributing to the overall performance.

cs.LG↗

arXiv2023

Towards Fair Graph Federated Learning via Incentive Mechanisms

Graph federated learning (FL) has emerged as a pivotal paradigm enabling multiple agents to collaboratively train a graph model while preserving local data privacy. Yet, current efforts overlook a key issue: agents are self-interested and would hesitant to share data without fair and satisfactory incentives. This paper is the first endeavor to address this issue by studying the incentive mechanism for graph federated learning. We identify a unique phenomenon in graph federated learning: the presence of agents posing potential harm to the federation and agents contributing with delays. This stands in contrast to previous FL incentive mechanisms that assume all agents contribute positively and in a timely manner. In view of this, this paper presents a novel incentive mechanism tailored for fair graph federated learning, integrating incentives derived from both model gradient and payoff. To achieve this, we first introduce an agent valuation function aimed at quantifying agent contributions through the introduction of two criteria: gradient alignment and graph diversity. Moreover, due to the high heterogeneity in graph federated learning, striking a balance between accuracy and fairness becomes particularly crucial. We introduce motif prototypes to enhance accuracy, communicated between the server and agents, enhancing global model aggregation and aiding agents in local model optimization. Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.

cs.LG↗

arXiv2023

EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection

In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important. Within this context, machine learning (ML) models, being highly valuable digital assets, have gained significant attention for IP protection. This paper introduces a practical encryption-based framework called \textit{EncryIP}, which seamlessly integrates a public-key encryption scheme into the model learning process. This approach enables the protected model to generate randomized and confused labels, ensuring that only individuals with accurate secret keys, signifying authorized users, can decrypt and reveal authentic labels. Importantly, the proposed framework not only facilitates the protected model to multiple authorized users without requiring repetitive training of the original ML model with IP protection methods but also maintains the model's performance without compromising its accuracy. Compared to existing methods like watermark-based, trigger-based, and passport-based approaches, \textit{EncryIP} demonstrates superior effectiveness in both training protected models and efficiently detecting the unauthorized spread of ML models.

cs.CR↗

arXiv2023

The interior penalty virtual element method for fourth-order singular perturbation problems

This paper is dedicated to the numerical solution of a fourth-order singular perturbation problem using the interior penalty virtual element method (IPVEM) proposed in [42]. The study introduces modifications to the jumps and averages in the penalty term, as well as presents an automated mesh-dependent selection of the penalty parameter. Drawing inspiration from the modified Morley finite element methods, we leverage the conforming interpolation technique to handle the lower part of the bilinear form. Through our analysis, we establish optimal convergence in the energy norm and provide a rigorous proof of uniform convergence concerning the perturbation parameter in the lowest-order case.

math.NA↗