Searcharxiv⌕ Search

arXiv subjects

Wenbin Zhang

Publications and source records attributed to Wenbin Zhang.

At least 73 records · Page 4Linked to original sources
arXiv2024

Variator: Accelerating Pre-trained Models with Plug-and-Play Compression Modules

Pre-trained language models (PLMs) have achieved remarkable results on NLP tasks but at the expense of huge parameter sizes and the consequent computational costs. In this paper, we propose Variator, a parameter-efficient acceleration method that enhances computational efficiency through plug-and-play compression plugins. Compression plugins are designed to reduce the sequence length via compressing multiple hidden vectors into one and trained with original PLMs frozen. Different from traditional model acceleration methods, which compress PLMs to smaller sizes, Variator offers two distinct advantages: (1) In real-world applications, the plug-and-play nature of our compression plugins enables dynamic selection of different compression plugins with varying acceleration ratios based on the current workload. (2) The compression plugin comprises a few compact neural network layers with minimal parameters, significantly saving storage and memory overhead, particularly in scenarios with a growing number of tasks. We validate the effectiveness of Variator on seven datasets. Experimental results show that Variator can save 53% computational costs using only 0.9% additional parameters with a performance drop of less than 2%. Moreover, when the model scales to billions of parameters, Variator matches the strong performance of uncompressed PLMs.

cs.CL↗
arXiv2024

Tracking Surface Charge Dynamics on Single Nanoparticles

Surface charges play a fundamental role in physics and chemistry, particularly in shaping the catalytic properties of nanomaterials. Tracking nanoscale surface charge dynamics remains challenging due to the involved length and time scales. Here, we demonstrate real-time access to the nanoscale charge dynamics on dielectric nanoparticles employing reaction nanoscopy. We present a four-dimensional visualization of the non-linear charge dynamics on strong-field irradiated single SiO$_2$ nanoparticles with femtosecond-nanometer resolution and reveal how surface charges affect surface molecular bonding with quantum dynamical simulations. We performed semi-classical simulations to uncover the roles of diffusion and charge loss in the surface charge redistribution process. Understanding nanoscale surface charge dynamics and its influence on chemical bonding on a single nanoparticle level unlocks an increased ability to address global needs in renewable energy and advanced healthcare.

cond-mat.mes-hall↗
arXiv2023

Individual Fairness under Uncertainty

Algorithmic fairness, the research field of making machine learning (ML) algorithms fair, is an established area in ML. As ML technologies expand their application domains, including ones with high societal impact, it becomes essential to take fairness into consideration during the building of ML systems. Yet, despite its wide range of socially sensitive applications, most work treats the issue of algorithmic bias as an intrinsic property of supervised learning, i.e., the class label is given as a precondition. Unlike prior studies in fairness, we propose an individual fairness measure and a corresponding algorithm that deal with the challenges of uncertainty arising from censorship in class labels, while enforcing similar individuals to be treated similarly from a ranking perspective, free of the Lipschitz condition in the conventional individual fairness definition. We argue that this perspective represents a more realistic model of fairness research for real-world application deployment and show how learning with such a relaxed precondition draws new insights that better explains algorithmic fairness. We conducted experiments on four real-world datasets to evaluate our proposed method compared to other fairness models, demonstrating its superiority in minimizing discrimination while maintaining predictive performance with uncertainty present.

cs.LG↗
arXiv2023

Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory

Visual Commonsense Reasoning (VCR) predicts an answer with corresponding rationale, given a question-image input. VCR is a recently introduced visual scene understanding task with a wide range of applications, including visual question answering, automated vehicle systems, and clinical decision support. Previous approaches to solving the VCR task generally rely on pre-training or exploiting memory with long dependency relationship encoded models. However, these approaches suffer from a lack of generalizability and prior knowledge. In this paper we propose a dynamic working memory based cognitive VCR network, which stores accumulated commonsense between sentences to provide prior knowledge for inference. Extensive experiments show that the proposed model yields significant improvements over existing methods on the benchmark VCR dataset. Moreover, the proposed model provides intuitive interpretation into visual commonsense reasoning. A Python implementation of our mechanism is publicly available at https://github.com/tanjatang/DMVCR

cs.CV↗
arXiv2023

Interpretable Visual Understanding with Cognitive Attention Network

While image understanding on recognition-level has achieved remarkable advancements, reliable visual scene understanding requires comprehensive image understanding on recognition-level but also cognition-level, which calls for exploiting the multi-source information as well as learning different levels of understanding and extensive commonsense knowledge. In this paper, we propose a novel Cognitive Attention Network (CAN) for visual commonsense reasoning to achieve interpretable visual understanding. Specifically, we first introduce an image-text fusion module to fuse information from images and text collectively. Second, a novel inference module is designed to encode commonsense among image, query and response. Extensive experiments on large-scale Visual Commonsense Reasoning (VCR) benchmark dataset demonstrate the effectiveness of our approach. The implementation is publicly available at https://github.com/tanjatang/CAN

cs.CV↗
arXiv2023

The Internet of Responsibilities-Connecting Human Responsibilities using Big Data and Blockchain

Accountability in the workplace is critically important and remains a challenging problem, especially with respect to workplace safety management. In this paper, we introduce a novel notion, the Internet of Responsibilities, for accountability management. Our method sorts through the list of responsibilities with respect to hazardous positions. The positions are interconnected using directed acyclic graphs (DAGs) indicating the hierarchy of responsibilities in the organization. In addition, the system detects and collects responsibilities, and represents risk areas in terms of the positions of the responsibility nodes. Finally, an automatic reminder and assignment system is used to enforce a strict responsibility control without human intervention. Using blockchain technology, we further extend our system with the capability to store, recover and encrypt responsibility data. We show that through the application of the Internet of Responsibility network model driven by Big Data, enterprise and government agencies can attain a highly secured and safe workplace. Therefore, our model offers a combination of interconnected responsibilities, accountability, monitoring, and safety which is crucial for the protection of employees and the success of organizations.

cs.CY↗
arXiv2023

Practical Deep Dispersed Watermarking with Synchronization and Fusion

Deep learning based blind watermarking works have gradually emerged and achieved impressive performance. However, previous deep watermarking studies mainly focus on fixed low-resolution images while paying less attention to arbitrary resolution images, especially widespread high-resolution images nowadays. Moreover, most works usually demonstrate robustness against typical non-geometric attacks (\textit{e.g.}, JPEG compression) but ignore common geometric attacks (\textit{e.g.}, Rotate) and more challenging combined attacks. To overcome the above limitations, we propose a practical deep \textbf{D}ispersed \textbf{W}atermarking with \textbf{S}ynchronization and \textbf{F}usion, called \textbf{\proposed}. Specifically, given an arbitrary-resolution cover image, we adopt a dispersed embedding scheme which sparsely and randomly selects several fixed small-size cover blocks to embed a consistent watermark message by a well-trained encoder. In the extraction stage, we first design a watermark synchronization module to locate and rectify the encoded blocks in the noised watermarked image. We then utilize a decoder to obtain messages embedded in these blocks, and propose a message fusion strategy based on similarity to make full use of the consistency among messages, thus determining a reliable message. Extensive experiments conducted on different datasets convincingly demonstrate the effectiveness of our proposed {\proposed}. Compared with state-of-the-art approaches, our blind watermarking can achieve better performance: averagely improve the bit accuracy by 5.28\% and 5.93\% against single and combined attacks, respectively, and show less file size increment and better visual quality. Our code is available at https://github.com/bytedance/DWSF.

cs.CV↗
arXiv2023

Variance-Preserving-Based Interpolation Diffusion Models for Speech Enhancement

The goal of this study is to implement diffusion models for speech enhancement (SE). The first step is to emphasize the theoretical foundation of variance-preserving (VP)-based interpolation diffusion under continuous conditions. Subsequently, we present a more concise framework that encapsulates both the VP- and variance-exploding (VE)-based interpolation diffusion methods. We demonstrate that these two methods are special cases of the proposed framework. Additionally, we provide a practical example of VP-based interpolation diffusion for the SE task. To improve performance and ease model training, we analyze the common difficulties encountered in diffusion models and suggest amenable hyper-parameters. Finally, we evaluate our model against several methods using a public benchmark to showcase the effectiveness of our approach

eess.AS↗
arXiv2023

Rethinking Learning Rate Tuning in the Era of Large Language Models

Large Language Models (LLMs) represent the recent success of deep learning in achieving remarkable human-like predictive performance. It has become a mainstream strategy to leverage fine-tuning to adapt LLMs for various real-world applications due to the prohibitive expenses associated with LLM training. The learning rate is one of the most important hyperparameters in LLM fine-tuning with direct impacts on both fine-tuning efficiency and fine-tuned LLM quality. Existing learning rate policies are primarily designed for training traditional deep neural networks (DNNs), which may not work well for LLM fine-tuning. We reassess the research challenges and opportunities of learning rate tuning in the coming era of Large Language Models. This paper makes three original contributions. First, we revisit existing learning rate policies to analyze the critical challenges of learning rate tuning in the era of LLMs. Second, we present LRBench++ to benchmark learning rate policies and facilitate learning rate tuning for both traditional DNNs and LLMs. Third, our experimental analysis with LRBench++ demonstrates the key differences between LLM fine-tuning and traditional DNN training and validates our analysis.

cs.LG↗
arXiv2023

Exploring Equation as a Better Intermediate Meaning Representation for Numerical Reasoning

Numerical reasoning is vital for natural language processing models to understand and process numerical information in real-world scenarios. Most current methods first generate the Intermediate Meaning Representations (IMRs) of questions and then generate answers. Current SOTA methods generate programs as IMRs with large language models (LLMs). Intuitively, equations have fewer restrictions and closer semantics to the question than programs, leading to higher generation accuracy. However, current LLMs generate equations worse than programs, where we assume that the equation data is rare in pre-training data compared to programs. So in this paper, we try to use equations as IMRs to solve the numerical reasoning task by addressing two problems: (1) Theoretically, how to prove that the equation is an IMR with higher generation accuracy than programs; (2) Empirically, how to improve the generation accuracy of equations with LLMs. For the first problem, we propose and prove a proposition to theoretically compare the generation accuracy of different IMRs. For the second problem, we present a method called Boosting Numerical Reason\textbfing by Decomposing the Generation of Equations (Bridge), which can improve the accuracy of LLMs in generating equations as IMRs by reducing the tendency of generating constant expressions and programs. Our method improves the performance by 2.2%, 0.9%, and 1.7% on GSM8K, SVAMP, and Algebra datasets compared to the previous state-of-the-art methods under the single reasoning path setting. Our codes and prompts are released in https://github.com/zirui-HIT/Bridge_for_Numerical_Reasoning.

cs.CL↗
arXiv2023

Wave-Packet Surface Propagation for Light-Induced Molecular Dissociation

Recent advances in laser technology have enabled tremendous progress in photochemistry, at the heart of which is the breaking and formation of chemical bonds. Such progress has been greatly facilitated by the development of accurate quantum-mechanical simulation method, which, however, does not necessarily accompany clear dynamical scenarios and is rather often a black box, other than being computationally heavy. Here, we develop a wave-packet surface propagation (WASP) approach to describe the molecular bond-breaking dynamics from a hybrid quantum-classical perspective. Via the introduction of quantum elements including state transitions and phase accumulations to the Newtonian propagation of the nuclear wave-packet, the WASP approach naturally comes with intuitive physical scenarios and accuracies. It is carefully benchmarked with the H2+ molecule and is shown to be capable of precisely reproducing experimental observations. The WASP method is promising for the intuitive visualization of strong-field molecular dynamics and is straightforwardly extensible toward complex molecules.

physics.chem-ph↗
arXiv2023

Preventing Discriminatory Decision-making in Evolving Data Streams

Bias in machine learning has rightly received significant attention over the last decade. However, most fair machine learning (fair-ML) work to address bias in decision-making systems has focused solely on the offline setting. Despite the wide prevalence of online systems in the real world, work on identifying and correcting bias in the online setting is severely lacking. The unique challenges of the online environment make addressing bias more difficult than in the offline setting. First, Streaming Machine Learning (SML) algorithms must deal with the constantly evolving real-time data stream. Second, they need to adapt to changing data distributions (concept drift) to make accurate predictions on new incoming data. Adding fairness constraints to this already complicated task is not straightforward. In this work, we focus on the challenges of achieving fairness in biased data streams while accounting for the presence of concept drift, accessing one sample at a time. We present Fair Sampling over Stream ($FS^2$), a novel fair rebalancing approach capable of being integrated with SML classification algorithms. Furthermore, we devise the first unified performance-fairness metric, Fairness Bonded Utility (FBU), to evaluate and compare the trade-off between performance and fairness of different bias mitigation methods efficiently. FBU simplifies the comparison of fairness-performance trade-offs of multiple techniques through one unified and intuitive evaluation, allowing model designers to easily choose a technique. Overall, extensive evaluations show our measures surpass those of other fair online techniques previously reported in the literature.

cs.LG↗
arXiv2023

A Generic Knowledge Based Medical Diagnosis Expert System

In this paper, we design and implement a generic medical knowledge based system (MKBS) for identifying diseases from several symptoms. In this system, some important aspects like knowledge bases system, knowledge representation, inference engine have been addressed. The system asks users different questions and inference engines will use the certainty factor to prune out low possible solutions. The proposed disease diagnosis system also uses a graphical user interface (GUI) to facilitate users to interact with the expert system. Our expert system is generic and flexible, which can be integrated with any rule bases system in disease diagnosis.

cs.AI↗
arXiv2023

Fair Decision-making Under Uncertainty

There has been concern within the artificial intelligence (AI) community and the broader society regarding the potential lack of fairness of AI-based decision-making systems. Surprisingly, there is little work quantifying and guaranteeing fairness in the presence of uncertainty which is prevalent in many socially sensitive applications, ranging from marketing analytics to actuarial analysis and recidivism prediction instruments. To this end, we study a longitudinal censored learning problem subject to fairness constraints, where we require that algorithmic decisions made do not affect certain individuals or social groups negatively in the presence of uncertainty on class label due to censorship. We argue that this formulation has a broader applicability to practical scenarios concerning fairness. We show how the newly devised fairness notions involving censored information and the general framework for fair predictions in the presence of censorship allow us to measure and mitigate discrimination under uncertainty that bridges the gap with real-world applications. Empirical evaluations on real-world discriminated datasets with censorship demonstrate the practicality of our approach.

cs.LG↗
arXiv2023

Unveiling and Mitigating Bias in Ride-Hailing Pricing for Equitable Policy Making

Ride-hailing services have skyrocketed in popularity due to the convenience they offer, but recent research has shown that their pricing strategies can have a disparate impact on some riders, such as those living in disadvantaged neighborhoods with a greater share of residents of color or residents below the poverty line. Since these communities tend to be more dependent on ride-hailing services due to lack of adequate public transportation, it is imperative to address this inequity. To this end, this paper presents the first thorough study on fair pricing for ride-hailing services by devising applicable fairness measures and corresponding fair pricing mechanisms. By providing discounts that may be subsidized by the government, our approach results in an increased number and more affordable rides for the disadvantaged community. Experiments on real-world Chicago taxi data confirm our theoretical findings which provide a basis for the government to establish fair ride-hailing policies.

cs.CY↗
arXiv2022

Reaction Nanoscopy of Ion Emission from Sub-wavelength Propanediol Droplets

Droplets provide unique opportunities for the investigation of laser-induced surface chemistry. Chemical reactions on the surface of charged droplets are ubiquitous in nature and can provide critical insight into more efficient processes for industrial chemical production. Here, we demonstrate the application of the reaction nanoscopy technique to strong-field ionized nanodroplets of propanediol (PDO). The technique's sensitivity to the near-field around the droplet allows for the in-situ characterization of the average droplet size and charge. The use of ultrashort laser pulses enables control of the amount of surface charge by the laser intensity. Moreover, we demonstrate the surface chemical sensitivity of reaction nanoscopy by comparing droplets of the isomers 1,2-PDO and 1,3-PDO in their ion emission and fragmentation channels. Referencing the ion yields to gas-phase data, we find an enhanced production of methyl cations from droplets of the 1,2-PDO isomer. Density functional theory simulations support that this enhancement is due to the alignment of 1,2-PDO molecules on the surface. The results pave the way towards spatio-temporal observations of charge dynamics and surface reactions on droplets in pump-probe studies.

physics.chem-ph↗
arXiv2022

Daytime sub-ambient radiative cooling with vivid structural colors mediated by coupled nanocavities

Daytime radiative cooling is a promising passive cooling technology for combating global warming. Existing daytime radiative coolers usually show whitish colors due to their broadband high solar reflectivity, which severely impedes applications in real-life situations with aesthetic demands and effective display. However, there is a trade-off between vivid colors and high cooling performance because colors are often produced by absorption of visible light, decreasing net cooling power. To break this trade-off, we design multilayered structures with coupled nanocavities and produce structural colors with high cooling performance. Using this design, we can obtain colorful radiative coolers which show a larger color gamut (occupying 17.7% sRGB area) than reported ones. We further fabricate colorful multilayered radiative coolers (CMRCs) and demonstrate they have temperature drops of 3.4 - 4.4 degrees on average based on outdoor experiments. These CMRCs are promising in thermal management of electronic/optoelectronic devices and outdoor facilities.

physics.optics↗
arXiv2022

A Lagrangian free-stream boundary condition for weakly compressible smoothed particle hydrodynamics

This paper proposes the first free-stream boundary condition in a purely Lagrangian framework for weakly-compressible smoothed particle hydrodynamics (WCSPH). The boundary condition is implemented based on several numerical techniques, including a spatio-temporal method and an ensuring technique for surface particle identification, far-field corrections of density and velocity near the free-stream boundary, and improved in- and outlet conditions which guarantee smooth inflow profile and free outflow particles without the issue of the truncated kernel. The accuracy and effectiveness of the method have been validated by the reference solutions of flow past a flat plate and circular cylinder, respectively. The method has also been tested with more complex flows to demonstrate its applicability, such as fluid-structure interaction (FSI) and 3D flow past a sphere.

physics.flu-dyn↗