arXiv subjects

Lei Xu

Publications and source records attributed to Lei Xu.

At least 145 records · Page 8Linked to original sources

arXiv2024

TPU as Cryptographic Accelerator

Cryptographic schemes like Fully Homomorphic Encryption (FHE) and Zero-Knowledge Proofs (ZKPs), while offering powerful privacy-preserving capabilities, are often hindered by their computational complexity. Polynomial multiplication, a core operation in these schemes, is a major performance bottleneck. While algorithmic advancements and specialized hardware like GPUs and FPGAs have shown promise in accelerating these computations, the recent surge in AI accelerators (TPUs/NPUs) presents a new opportunity. This paper explores the potential of leveraging TPUs/NPUs to accelerate polynomial multiplication, thereby enhancing the performance of FHE and ZKP schemes. We present techniques to adapt polynomial multiplication to these AI-centric architectures and provide a preliminary evaluation of their effectiveness. We also discuss current limitations and outline future directions for further performance improvements, paving the way for wider adoption of advanced cryptographic tools.

cs.CR↗

arXiv2024

Integrating Chemical Language and Molecular Graph in Multimodal Fused Deep Learning for Drug Property Prediction

Accurately predicting molecular properties is a challenging but essential task in drug discovery. Recently, many mono-modal deep learning methods have been successfully applied to molecular property prediction. However, the inherent limitation of mono-modal learning arises from relying solely on one modality of molecular representation, which restricts a comprehensive understanding of drug molecules and hampers their resilience against data noise. To overcome the limitations, we construct multimodal deep learning models to cover different molecular representations. We convert drug molecules into three molecular representations, SMILES-encoded vectors, ECFP fingerprints, and molecular graphs. To process the modal information, Transformer-Encoder, bi-directional gated recurrent units (BiGRU), and graph convolutional network (GCN) are utilized for feature learning respectively, which can enhance the model capability to acquire complementary and naturally occurring bioinformatics information. We evaluated our triple-modal model on six molecule datasets. Different from bi-modal learning models, we adopt five fusion methods to capture the specific features and leverage the contribution of each modal information better. Compared with mono-modal models, our multimodal fused deep learning (MMFDL) models outperform single models in accuracy, reliability, and resistance capability against noise. Moreover, we demonstrate its generalization ability in the prediction of binding constants for protein-ligand complex molecules in the refined set of PDBbind. The advantage of the multimodal model lies in its ability to process diverse sources of data using proper models and suitable fusion methods, which would enhance the noise resistance of the model while obtaining data diversity.

cs.LG↗

arXiv2024

ConSiDERS-The-Human Evaluation Framework: Rethinking Human Evaluation for Generative Large Language Models

In this position paper, we argue that human evaluation of generative large language models (LLMs) should be a multidisciplinary undertaking that draws upon insights from disciplines such as user experience research and human behavioral psychology to ensure that the experimental design and results are reliable. The conclusions from these evaluations, thus, must consider factors such as usability, aesthetics, and cognitive biases. We highlight how cognitive biases can conflate fluent information and truthfulness, and how cognitive uncertainty affects the reliability of rating scores such as Likert. Furthermore, the evaluation should differentiate the capabilities and weaknesses of increasingly powerful large language models -- which requires effective test sets. The scalability of human evaluation is also crucial to wider adoption. Hence, to design an effective human evaluation system in the age of generative NLP, we propose the ConSiDERS-The-Human evaluation framework consisting of 6 pillars -- Consistency, Scoring Criteria, Differentiating, User Experience, Responsible, and Scalability.

cs.CL↗

arXiv2024

Edge detection imaging by quasi-bound states in the continuum

Optical metasurfaces have revolutionized analog computing and image processing at sub-wavelength scales with faster speed and lower power consumption. They typically involve spatial differentiation with engineered angular dispersion. Quasi-bound states in the continuum (quasi-BICs) have recently emerged as a powerful tool for tailoring properties of optical resonances. While quasi-BICs have been explored in various applications that require high $Q$-factors and enhanced field confinement, their full potential in image processing remains unexplored. Here, we demonstrate edge detection imaging by leveraging a quasi-BIC in an all-dielectric metasurface. This metasurface, composed of four nanodisks per unit cell, supports a polarization-independent quasi-BIC through structural perturbations, allowing simultaneously engineering $Q$-factor and angular dispersion. Importantly, we find that with suitable parameters, this quasi-BIC metasurface can perform isotropic two-dimensional spatial differentiation, which is the core element for realizing edge detection. Following the theoretical design, we fabricate the metasurfaces on the silicon-on-insulator platform and experimentally validate their capability of high-quality, efficient, and uniform edge detection imaging under different incident polarizations. Our results illuminate the mechanisms of edge detection with quasi-BIC metasurfaces and highlight new opportunities for their application in ultra-compact, low-power optical computing devices.

physics.optics↗

arXiv2024

Boosting Efficiency in Task-Agnostic Exploration through Causal Knowledge

The effectiveness of model training heavily relies on the quality of available training resources. However, budget constraints often impose limitations on data collection efforts. To tackle this challenge, we introduce causal exploration in this paper, a strategy that leverages the underlying causal knowledge for both data collection and model training. We, in particular, focus on enhancing the sample efficiency and reliability of the world model learning within the domain of task-agnostic reinforcement learning. During the exploration phase, the agent actively selects actions expected to yield causal insights most beneficial for world model training. Concurrently, the causal knowledge is acquired and incrementally refined with the ongoing collection of data. We demonstrate that causal exploration aids in learning accurate world models using fewer data and provide theoretical guarantees for its convergence. Empirical experiments, on both synthetic data and real-world applications, further validate the benefits of causal exploration.

cs.LG↗

arXiv2024

A cyclical route linking fundamental mechanism and AI algorithm: An example from tuning Poisson's ratio in amorphous networks

"AI for science" is widely recognized as a future trend in the development of scientific research. Currently, although machine learning algorithms have played a crucial role in scientific research with numerous successful cases, relatively few instances exist where AI assists researchers in uncovering the underlying physical mechanisms behind a certain phenomenon and subsequently using that mechanism to improve machine learning algorithms' efficiency. This article uses the investigation into the relationship between extreme Poisson's ratio values and the structure of amorphous networks as a case study to illustrate how machine learning methods can assist in revealing underlying physical mechanisms. Upon recognizing that the Poisson's ratio relies on the low-frequency vibrational modes of dynamical matrix, we can then employ a convolutional neural network, trained on the dynamical matrix instead of traditional image recognition, to predict the Poisson's ratio of amorphous networks with a much higher efficiency. Through this example, we aim to showcase the role that artificial intelligence can play in revealing fundamental physical mechanisms, which subsequently improves the machine learning algorithms significantly.

cond-mat.soft↗

arXiv2024

Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing

Unit testing is crucial in software engineering for ensuring quality. However, it's not widely used in parallel and high-performance computing software, particularly scientific applications, due to their smaller, diverse user base and complex logic. These factors make unit testing challenging and expensive, as it requires specialized knowledge and existing automated tools are often ineffective. To address this, we propose an automated method for generating unit tests for such software, considering their unique features like complex logic and parallel processing. Recently, large language models (LLMs) have shown promise in coding and testing. We explored the capabilities of Davinci (text-davinci-002) and ChatGPT (gpt-3.5-turbo) in creating unit tests for C++ parallel programs. Our results show that LLMs can generate mostly correct and comprehensive unit tests, although they have some limitations, such as repetitive assertions and blank test cases.

cs.SE↗

arXiv2024

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

We present DeepSeek-V2, a strong Mixture-of-Experts (MoE) language model characterized by economical training and efficient inference. It comprises 236B total parameters, of which 21B are activated for each token, and supports a context length of 128K tokens. DeepSeek-V2 adopts innovative architectures including Multi-head Latent Attention (MLA) and DeepSeekMoE. MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation. Compared with DeepSeek 67B, DeepSeek-V2 achieves significantly stronger performance, and meanwhile saves 42.5% of training costs, reduces the KV cache by 93.3%, and boosts the maximum generation throughput to 5.76 times. We pretrain DeepSeek-V2 on a high-quality and multi-source corpus consisting of 8.1T tokens, and further perform Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) to fully unlock its potential. Evaluation results show that, even with only 21B activated parameters, DeepSeek-V2 and its chat versions still achieve top-tier performance among open-source models.

cs.CL↗

arXiv2024

When Swarm Learning meets energy series data: A decentralized collaborative learning design based on blockchain

Machine learning models offer the capability to forecast future energy production or consumption and infer essential unknown variables from existing data. However, legal and policy constraints within specific energy sectors render the data sensitive, presenting technical hurdles in utilizing data from diverse sources. Therefore, we propose adopting a Swarm Learning (SL) scheme, which replaces the centralized server with a blockchain-based distributed network to address the security and privacy issues inherent in Federated Learning (FL)'s centralized architecture. Within this distributed Collaborative Learning framework, each participating organization governs nodes for inter-organizational communication. Devices from various organizations utilize smart contracts for parameter uploading and retrieval. Consensus mechanism ensures distributed consistency throughout the learning process, guarantees the transparent trustworthiness and immutability of parameters on-chain. The efficacy of the proposed framework is substantiated across three real-world energy series modeling scenarios with superior performance compared to Local Learning approaches, simultaneously emphasizing enhanced data security and privacy over Centralized Learning and FL method. Notably, as the number of data volume and the count of local epochs increases within a threshold, there is an improvement in model performance accompanied by a reduction in the variance of performance errors. Consequently, this leads to an increased stability and reliability in the outcomes produced by the model.

cs.LG↗

arXiv2024

SWAT: A System-Wide Approach to Tunable Leakage Mitigation in Encrypted Data Stores

Numerous studies have underscored the significant privacy risks associated with various leakage patterns in encrypted data stores. While many solutions have been proposed to mitigate these leakages, they either (1) incur substantial overheads, (2) focus on specific subsets of leakage patterns, or (3) apply the same security notion across various workloads, thereby impeding the attainment of fine-tuned privacy-efficiency trade-offs. In light of various detrimental leakage patterns, this paper starts with an investigation into which specific leakage patterns require our focus in the contexts of key-value, range-query, and dynamic workloads, respectively. Subsequently, we introduce new security notions tailored to the specific privacy requirements of these workloads. Accordingly, we propose and instantiate SWAT, an efficient construction that progressively enables these workloads, while provably mitigating system-wide leakage via a suite of algorithms with tunable privacy-efficiency trade-offs. We conducted extensive experiments and compiled a detailed result analysis, showing the efficiency of our solution. SWATis about an order of magnitude slower than an encryption-only data store that reveals various leakage patterns and is two orders of magnitude faster than a trivial zero-leakage solution. Meanwhile, the performance of SWATremains highly competitive compared to other designs that mitigate specific types of leakage.

cs.CR↗

arXiv2024

Multiple Bound States in the Continuum: Towards Intense Terahertz Matter Interaction

Bound states in the continuum (BICs) are an excellent platform enabling highly efficient light-matter interaction in applications for lasing, nonlinear generation, and sensing. However, the current focus in implementing BICs has primarily been on single sharp resonances, limiting the extent of electric field enhancement for multiple resonances. In this study, we conducted experimental demonstrations to showcase how metasurfaces can enable the control of symmetry-broken and Friedrich-Wintgen BICs by leveraging the asymmetry of split resonant rings. This approach allows for the existence of multiple free-control BIC resonances and tailored enhancement of controlling light-matter interactions. We have conducted further experiments to validate the effectiveness and performance of our approach for identification of the distinct fingerprint of α-lactose with high sensitivity using only one single metasurface. These findings present a novel and efficient platform for the development of miniaturized and chip-scale photonics devices with intense light-matter interaction.

physics.optics↗

arXiv2024

Error Mitigated Metasurface-Based Randomized Measurement Schemes

Estimating properties of quantum states via randomized measurements has become a significant part of quantum information science. In this paper, we design an innovative approach leveraging metasurfaces to perform randomized measurements on photonic qubits, together with error mitigation techniques that suppress realistic metasurface measurement noise. Through fidelity and purity estimation, we confirm the capability of metasurfaces to implement randomized measurements and the unbiased nature of our error-mitigated estimator. Our findings show the potential of metasurface-based randomized measurement schemes in achieving robust and resource-efficient estimation of quantum state properties.

quant-ph↗

arXiv2024

Decentralized FaaS over Multi-Clouds with Blockchain based Management for Supporting Emerging Applications

Function-as-a-Service (FaaS) offers a streamlined cloud computing paradigm, but existing centralized systems suffer from vendor lock-in and single points of failure. We propose DeFaaS, a decentralized FaaS system leveraging blockchain technology and decentralized API management. DeFaaS addresses these limitations by establishing a secure, transparent registry of functions on a blockchain and enabling applications to discover and invoke them. This approach fosters scalability, flexibility, enhanced security, and improved reliability. Furthermore, DeFaaS's architecture extends beyond decentralized FaaS, supporting other distributed computing scenarios like dApps, volunteer computing, and multi-cloud service meshes. DeFaaS represents a significant advancement in decentralized computing with the potential to unlock a multitude of novel applications and use cases.

cs.SE↗

arXiv2024

Teaching Machines to Code: Smart Contract Translation with LLMs

The advent of large language models (LLMs) has marked a significant milestone in the realm of artificial intelligence, with their capabilities often matching or surpassing human expertise in various domains. Among these achievements, their adeptness in translation tasks stands out, closely mimicking the intricate and preliminary processes undertaken by human translators to ensure the fidelity and quality of the translated content. Despite the advancements in utilizing LLMs for translating programming code across different languages, the domain of smart contract translation, particularly into languages not previously encountered by the LLM, remains largely unexplored. In our research, we present a pioneering approach, SolMover, which harnesses the synergy of two distinct LLMs within a unified framework. This framework is designed to grasp coding principles and apply this understanding to the translation of code into an unfamiliar language. Our study delves into the capacity of LLMs to mimic human learning processes, offering an in-depth evaluation of our methodology for converting smart contracts written in Solidity to Move, a language with limited resources. The framework employs one LLM to decipher coding conventions for the new language, creating a blueprint for the second LLM, which, lacking planning abilities, possesses coding expertise. The empirical evidence from our experiments suggests that SolMover substantially enhances performance compared to gpt-3.5-turbo-1106, and achieves superior results over competitors such as Palm2 and Mixtral-8x7B-Instruct. Additionally, our analysis highlights the efficacy of our bug mitigation strategy in elevating code quality across all models, even outside the SolMover framework.

cs.SE↗

arXiv2024

HGIC: A Hand Gesture Based Interactive Control System for Efficient and Scalable Multi-UAV Operations

As technological advancements continue to expand the capabilities of multi unmanned-aerial-vehicle systems (mUAV), human operators face challenges in scalability and efficiency due to the complex cognitive load and operations associated with motion adjustments and team coordination. Such cognitive demands limit the feasible size of mUAV teams and necessitate extensive operator training, impeding broader adoption. This paper developed a Hand Gesture Based Interactive Control (HGIC), a novel interface system that utilize computer vision techniques to intuitively translate hand gestures into modular commands for robot teaming. Through learning control models, these commands enable efficient and scalable mUAV motion control and adjustments. HGIC eliminates the need for specialized hardware and offers two key benefits: 1) Minimal training requirements through natural gestures; and 2) Enhanced scalability and efficiency via adaptable commands. By reducing the cognitive burden on operators, HGIC opens the door for more effective large-scale mUAV applications in complex, dynamic, and uncertain scenarios. HGIC will be open-sourced after the paper being published online for the research community, aiming to drive forward innovations in human-mUAV interactions.

cs.RO↗

arXiv2024

Revisiting Generative Adversarial Networks for Binary Semantic Segmentation on Imbalanced Datasets

Anomalous crack region detection is a typical binary semantic segmentation task, which aims to detect pixels representing cracks on pavement surface images automatically by algorithms. Although existing deep learning-based methods have achieved outcoming results on specific public pavement datasets, the performance would deteriorate dramatically on imbalanced datasets. The input datasets used in such tasks suffer from severely between-class imbalanced problems, hence, it is a core challenge to obtain a robust performance on diverse pavement datasets with generic deep learning models. To address this problem, in this work, we propose a deep learning framework based on conditional Generative Adversarial Networks (cGANs) for the anomalous crack region detection tasks at the pixel level. In particular, the proposed framework containing a cGANs and a novel auxiliary network is developed to enhance and stabilize the generator's performance under two alternative training stages, when estimating a multiscale probability feature map from heterogeneous and imbalanced inputs iteratively. Moreover, several attention mechanisms and entropy strategies are incorporated into the cGANs architecture and the auxiliary network separately to mitigate further the performance deterioration of model training on severely imbalanced datasets. We implement extensive experiments on six accessible pavement datasets. The experimental results from both visual and quantitative evaluation show that the proposed framework can achieve state-of-the-art results on these datasets efficiently and robustly without acceleration of computation complexity.

cs.CV↗

arXiv2024

Dropout Concrete Autoencoder for Band Selection on HSI Scenes

Deep learning-based informative band selection methods on hyperspectral images (HSI) recently have gained intense attention to eliminate spectral correlation and redundancies. However, the existing deep learning-based methods either need additional post-processing strategies to select the descriptive bands or optimize the model indirectly, due to the parameterization inability of discrete variables for the selection procedure. To overcome these limitations, this work proposes a novel end-to-end network for informative band selection. The proposed network is inspired by the advances in concrete autoencoder (CAE) and dropout feature ranking strategy. Different from the traditional deep learning-based methods, the proposed network is trained directly given the required band subset eliminating the need for further post-processing. Experimental results on four HSI scenes show that the proposed dropout CAE achieves substantial and effective performance levels outperforming the competing methods.

cs.CV↗

arXiv2023

Joint Feature and Differentiable $ k $-NN Graph Learning using Dirichlet Energy

Feature selection (FS) plays an important role in machine learning, which extracts important features and accelerates the learning process. In this paper, we propose a deep FS method that simultaneously conducts feature selection and differentiable $ k $-NN graph learning based on the Dirichlet Energy. The Dirichlet Energy identifies important features by measuring their smoothness on the graph structure, and facilitates the learning of a new graph that reflects the inherent structure in new feature subspace. We employ Optimal Transport theory to address the non-differentiability issue of learning $ k $-NN graphs in neural networks, which theoretically makes our method applicable to other graph neural networks for dynamic graph learning. Furthermore, the proposed framework is interpretable, since all modules are designed algorithmically. We validate the effectiveness of our model with extensive experiments on both synthetic and real-world datasets.

cs.LG↗