Searcharxiv⌕ Search

arXiv subjects

Wei Lu

Publications and source records attributed to Wei Lu.

At least 235 records · Page 13Linked to original sources
arXiv2023

Giant Enhancement of Magnonic Frequency Combs by Exceptional Points

With their incomparable time-frequency accuracy, frequency combs have significantly advanced precision spectroscopy, ultra-sensitive detection, and atomic clocks. Traditional methods to create photonic, phononic, and magnonic frequency combs hinge on material nonlinearities which are often weak, necessitating high power densities to surpass their initiation thresholds, which subsequently limits their applications. Here, we introduce a novel nonlinear process to efficiently generate magnonic frequency combs (MFCs) by exploiting exceptional points (EPs) in a coupled system comprising a pump-induced magnon mode and a Kittel mode. Even without any cavity, our method greatly improves the efficiency of nonlinear frequency conversion and achieves optimal MFCs at low pump power. Additionally, our novel nonlinear process enables excellent tunability of EPs using the polarization and power of the pump, simplifying MFC generation and manipulation. Our work establishes a synergistic relationship between non-Hermitian physics and MFCs, which is advantages for coherent/quantum information processing and ultra-sensitive detection.

cond-mat.mes-hall↗
arXiv2023

Contextual Distortion Reveals Constituency: Masked Language Models are Implicit Parsers

Recent advancements in pre-trained language models (PLMs) have demonstrated that these models possess some degree of syntactic awareness. To leverage this knowledge, we propose a novel chart-based method for extracting parse trees from masked language models (LMs) without the need to train separate parsers. Our method computes a score for each span based on the distortion of contextual representations resulting from linguistic perturbations. We design a set of perturbations motivated by the linguistic concept of constituency tests, and use these to score each span by aggregating the distortion scores. To produce a parse tree, we use chart parsing to find the tree with the minimum score. Our method consistently outperforms previous state-of-the-art methods on English with masked LMs, and also demonstrates superior performance in a multilingual setting, outperforming the state of the art in 6 out of 8 languages. Notably, although our method does not involve parameter updates or extensive hyperparameter search, its performance can even surpass some unsupervised parsing methods that require fine-tuning. Our analysis highlights that the distortion of contextual representation resulting from syntactic perturbation can serve as an effective indicator of constituency across languages.

cs.CL↗
arXiv2023

Reduced-order electrochemical models with shape functions for fast, accurate prediction of lithium-ion batteries under high C rates

This paper proposes physical-based, reduced-order electrochemical models that are much faster than the electrochemical pseudo 2D (P2D) model, while providing high accuracy even under the challenging conditions of high C-rate and strong polarization of lithium ion concentration and potential in a battery cell. In particular, an innovative weak form of equations are developed by using shape functions, which reduces the fully coupled electrochemical and transport equations to ordinary differential equations, and provides self-consistent solutions for the evolution of the polynomial coefficients. Results show that the models, named as revised single-particle model (RSPM) and fast-calculating P2D model (FCP2D), give highly reliable prediction of battery operations, including under dynamic driving profiles. They can calculate battery parameters, such as terminal voltage, over-potential, interfacial current density, lithium-ion concentration distribution, and electrolyte potential distribution with a relative error less than 2%. Applicable for moderately high C rates (below 2.5 C), the RSPM is up to more than 33 times faster than the P2D model. The FCP2D is applicable for high C rates (above 2.5 C) and is about 8 times faster than the P2D model. With their high speed and accuracy, these physics-based models can significantly improve the capability and performance of the battery management system and accelerate battery design optimization.

physics.chem-ph↗
arXiv2023

Tab-CoT: Zero-shot Tabular Chain of Thought

The chain-of-though (CoT) prompting methods were successful in various natural language processing (NLP) tasks thanks to their ability to unveil the underlying complex reasoning processes. Such reasoning processes typically exhibit implicitly structured steps. Recent efforts also started investigating methods to encourage more explicitly structured reasoning procedures to be captured. In this work, we propose Tab-CoT, a novel tabular-format CoT prompting method, which allows the complex reasoning process to be explicitly modelled in a highly structured manner. Despite its simplicity, we show that our approach is capable of performing reasoning across multiple dimensions (i.e., both rows and columns). We demonstrate our approach's strong zero-shot and few-shot capabilities through extensive experiments on a range of reasoning tasks.

cs.CL↗
arXiv2023

Better Sampling of Negatives for Distantly Supervised Named Entity Recognition

Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data instead of human annotations. The distantly annotated datasets are often noisy and contain a considerable number of false negatives. The recent approach uses a weighted sampling approach to select a subset of negative samples for training. However, it requires a good classifier to assign weights to the negative samples. In this paper, we propose a simple and straightforward approach for selecting the top negative samples that have high similarities with all the positive samples for training. Our method achieves consistent performance improvements on four distantly supervised NER datasets. Our analysis also shows that it is critical to differentiate the true negatives from the false negatives.

cs.CL↗
arXiv2023

A new method for solving the equation $x^d+(x+1)^d=b$ in $\mathbb{F}_{q^4}$ where $d=q^3+q^2+q-1$

In this paper, we give a new method answer to a recent conjecture proposed by Budaghyan, Calderini, Carlet, Davidova and Kaleyski about the equation $x^d+(x+1)^d=b$ in $\mathbb{F}_{q^4}$, where $n$ is a positive integer, $q=2^n$ and $d=q^3+q^2+q-1$. In particular, we directly determine the differential spectrum of this power function $x^d$ using methods different from those in the literature. Compared with the methods in the literature, our method is more direct and simple.

math.NT↗
arXiv2023

CIT-EmotionNet: CNN Interactive Transformer Network for EEG Emotion Recognition

Emotion recognition using Electroencephalogram (EEG) signals has emerged as a significant research challenge in affective computing and intelligent interaction. However, effectively combining global and local features of EEG signals to improve performance in emotion recognition is still a difficult task. In this study, we propose a novel CNN Interactive Transformer Network for EEG Emotion Recognition, known as CIT-EmotionNet, which efficiently integrates global and local features of EEG signals. Initially, we convert raw EEG signals into spatial-frequency representations, which serve as inputs. Then, we integrate Convolutional Neural Network (CNN) and Transformer within a single framework in a parallel manner. Finally, we design a CNN interactive Transformer module, which facilitates the interaction and fusion of local and global features, thereby enhancing the model's ability to extract both types of features from EEG spatial-frequency representations. The proposed CIT-EmotionNet outperforms state-of-the-art methods, achieving an average recognition accuracy of 98.57\% and 92.09\% on two publicly available datasets, SEED and SEED-IV, respectively.

eess.SP↗
arXiv2023

AIO-P: Expanding Neural Performance Predictors Beyond Image Classification

Evaluating neural network performance is critical to deep neural network design but a costly procedure. Neural predictors provide an efficient solution by treating architectures as samples and learning to estimate their performance on a given task. However, existing predictors are task-dependent, predominantly estimating neural network performance on image classification benchmarks. They are also search-space dependent; each predictor is designed to make predictions for a specific architecture search space with predefined topologies and set of operations. In this paper, we propose a novel All-in-One Predictor (AIO-P), which aims to pretrain neural predictors on architecture examples from multiple, separate computer vision (CV) task domains and multiple architecture spaces, and then transfer to unseen downstream CV tasks or neural architectures. We describe our proposed techniques for general graph representation, efficient predictor pretraining and knowledge infusion techniques, as well as methods to transfer to downstream tasks/spaces. Extensive experimental results show that AIO-P can achieve Mean Absolute Error (MAE) and Spearman's Rank Correlation (SRCC) below 1% and above 0.5, respectively, on a breadth of target downstream CV tasks with or without fine-tuning, outperforming a number of baselines. Moreover, AIO-P can directly transfer to new architectures not seen during training, accurately rank them and serve as an effective performance estimator when paired with an algorithm designed to preserve performance while reducing FLOPs.

cs.CV↗
arXiv2023

GENNAPE: Towards Generalized Neural Architecture Performance Estimators

Predicting neural architecture performance is a challenging task and is crucial to neural architecture design and search. Existing approaches either rely on neural performance predictors which are limited to modeling architectures in a predefined design space involving specific sets of operators and connection rules, and cannot generalize to unseen architectures, or resort to zero-cost proxies which are not always accurate. In this paper, we propose GENNAPE, a Generalized Neural Architecture Performance Estimator, which is pretrained on open neural architecture benchmarks, and aims to generalize to completely unseen architectures through combined innovations in network representation, contrastive pretraining, and fuzzy clustering-based predictor ensemble. Specifically, GENNAPE represents a given neural network as a Computation Graph (CG) of atomic operations which can model an arbitrary architecture. It first learns a graph encoder via Contrastive Learning to encourage network separation by topological features, and then trains multiple predictor heads, which are soft-aggregated according to the fuzzy membership of a neural network. Experiments show that GENNAPE pretrained on NAS-Bench-101 can achieve superior transferability to 5 different public neural network benchmarks, including NAS-Bench-201, NAS-Bench-301, MobileNet and ResNet families under no or minimum fine-tuning. We further introduce 3 challenging newly labelled neural network benchmarks: HiAML, Inception and Two-Path, which can concentrate in narrow accuracy ranges. Extensive experiments show that GENNAPE can correctly discern high-performance architectures in these families. Finally, when paired with a search algorithm, GENNAPE can find architectures that improve accuracy while reducing FLOPs on three families.

cs.LG↗
arXiv2023

MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos

User-generated content (UGC) live videos are often bothered by various distortions during capture procedures and thus exhibit diverse visual qualities. Such source videos are further compressed and transcoded by media server providers before being distributed to end-users. Because of the flourishing of UGC live videos, effective video quality assessment (VQA) tools are needed to monitor and perceptually optimize live streaming videos in the distributing process. In this paper, we address \textbf{UGC Live VQA} problems by constructing a first-of-a-kind subjective UGC Live VQA database and developing an effective evaluation tool. Concretely, 418 source UGC videos are collected in real live streaming scenarios and 3,762 compressed ones at different bit rates are generated for the subsequent subjective VQA experiments. Based on the built database, we develop a \underline{M}ulti-\underline{D}imensional \underline{VQA} (\textbf{MD-VQA}) evaluator to measure the visual quality of UGC live videos from semantic, distortion, and motion aspects respectively. Extensive experimental results show that MD-VQA achieves state-of-the-art performance on both our UGC Live VQA database and existing compressed UGC VQA databases.

cs.CV↗
arXiv2023

Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking Models

Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain underexplored by prior studies. Moreover, the inherit adversarial vulnerabilities might be leveraged by blackhat SEO to defeat better-protected search engines. In this study, we propose an imitation adversarial attack on black-box neural passage ranking models. We first show that the target passage ranking model can be transparentized and imitated by enumerating critical queries/candidates and then train a ranking imitation model. Leveraging the ranking imitation model, we can elaborately manipulate the ranking results and transfer the manipulation attack to the target ranking model. For this purpose, we propose an innovative gradient-based attack method, empowered by the pairwise objective function, to generate adversarial triggers, which causes premeditated disorderliness with very few tokens. To equip the trigger camouflages, we add the next sentence prediction loss and the language model fluency constraint to the objective function. Experimental results on passage ranking demonstrate the effectiveness of the ranking imitation attack model and adversarial triggers against various SOTA neural ranking models. Furthermore, various mitigation analyses and human evaluation show the effectiveness of camouflages when facing potential mitigation approaches. To motivate other scholars to further investigate this novel and important problem, we make the experiment data and code publicly available.

cs.IR↗
arXiv2023

Modeling and design of heterogeneous hierarchical bioinspired spider web structures using generative deep learning and additive manufacturing

Spider webs are incredible biological structures, comprising thin but strong silk filament and arranged into complex hierarchical architectures with striking mechanical properties (e.g., lightweight but high strength, achieving diverse mechanical responses). While simple 2D orb webs can easily be mimicked, the modeling and synthesis of 3D-based web structures remain challenging, partly due to the rich set of design features. Here we provide a detailed analysis of the heterogenous graph structures of spider webs, and use deep learning as a way to model and then synthesize artificial, bio-inspired 3D web structures. The generative AI models are conditioned based on key geometric parameters (including average edge length, number of nodes, average node degree, and others). To identify graph construction principles, we use inductive representation sampling of large experimentally determined spider web graphs, to yield a dataset that is used to train three conditional generative models: 1) An analog diffusion model inspired by nonequilibrium thermodynamics, with sparse neighbor representation, 2) a discrete diffusion model with full neighbor representation, and 3) an autoregressive transformer architecture with full neighbor representation. All three models are scalable, produce complex, de novo bio-inspired spider web mimics, and successfully construct graphs that meet the design objectives. We further propose algorithm that assembles web samples produced by the generative models into larger-scale structures based on a series of geometric design targets, including helical and parametric shapes, mimicking, and extending natural design principles towards integration with diverging engineering objectives. Several webs are manufactured using 3D printing and tested to assess mechanical properties.

cs.LG↗
arXiv2023

A Proof of a Conjecture About a Class of Near Maximum Distance Separable Codes

In this paper, we completely determine the number of solutions to $ \operatorname{Tr}^{q^2}_q(bx+b)+c=0, x\in μ_{q+1}\backslash \{-1\}$ for all $b\in \mathbb{F}_{q^2}, c\in\mathbb{F}_{q}$. As an application, we can give the weight distributions of a class of linear codes, and give a completely answer to a recent conjecture about a class of NMDS codes proposed by Heng.

cs.IT↗
arXiv2023

Online stochastic Newton methods for estimating the geometric median and applications

In the context of large samples, a small number of individuals might spoil basic statistical indicators like the mean. It is difficult to detect automatically these atypical individuals, and an alternative strategy is using robust approaches. This paper focuses on estimating the geometric median of a random variable, which is a robust indicator of central tendency. In order to deal with large samples of data arriving sequentially, online stochastic Newton algorithms for estimating the geometric median are introduced and we give their rates of convergence. Since estimates of the median and those of the Hessian matrix can be recursively updated, we also determine confidences intervals of the median in any designated direction and perform online statistical tests.

stat.ML↗
arXiv2023

A General-Purpose Transferable Predictor for Neural Architecture Search

Understanding and modelling the performance of neural architectures is key to Neural Architecture Search (NAS). Performance predictors have seen widespread use in low-cost NAS and achieve high ranking correlations between predicted and ground truth performance in several NAS benchmarks. However, existing predictors are often designed based on network encodings specific to a predefined search space and are therefore not generalizable to other search spaces or new architecture families. In this paper, we propose a general-purpose neural predictor for NAS that can transfer across search spaces, by representing any given candidate Convolutional Neural Network (CNN) with a Computation Graph (CG) that consists of primitive operators. We further combine our CG network representation with Contrastive Learning (CL) and propose a graph representation learning procedure that leverages the structural information of unlabeled architectures from multiple families to train CG embeddings for our performance predictor. Experimental results on NAS-Bench-101, 201 and 301 demonstrate the efficacy of our scheme as we achieve strong positive Spearman Rank Correlation Coefficient (SRCC) on every search space, outperforming several Zero-Cost Proxies, including Synflow and Jacov, which are also generalizable predictors across search spaces. Moreover, when using our proposed general-purpose predictor in an evolutionary neural architecture search algorithm, we can find high-performance architectures on NAS-Bench-101 and find a MobileNetV3 architecture that attains 79.2% top-1 accuracy on ImageNet.

cs.LG↗
arXiv2023

Unsupervised Non-transferable Text Classification

Training a good deep learning model requires substantial data and computing resources, which makes the resulting neural model a valuable intellectual property. To prevent the neural network from being undesirably exploited, non-transferable learning has been proposed to reduce the model generalization ability in specific target domains. However, existing approaches require labeled data for the target domain which can be difficult to obtain. Furthermore, they do not have the mechanism to still recover the model's ability to access the target domain. In this paper, we propose a novel unsupervised non-transferable learning method for the text classification task that does not require annotated target domain data. We further introduce a secret key component in our approach for recovering the access to the target domain, where we design both an explicit and an implicit method for doing so. Extensive experiments demonstrate the effectiveness of our approach.

cs.CL↗
arXiv2023

Coherent Microwave Emission of a Gain-Driven Polariton

By developing a gain-embedded cavity magnonics platform, we create gain-driven polariton (GDP) that is activated by an amplified electromagnetic field. Distinct effects of gain-driven light-matter interaction, such as polariton auto-oscillations, polariton phase singularity, self-selection of a polariton bright mode, and gain-induced magnon-photon synchronization, are theoretically studied and experimentally manifested. Utilizing the gain-sustained photon coherence of the GDP, we demonstrate polariton-based coherent microwave amplication (~ 40 dB) and achieve high-quality coherent microwave emission (Q > 10^9).

cond-mat.mes-hall↗
arXiv2023

AI vs. Human -- Differentiation Analysis of Scientific Content Generation

Recent neural language models have taken a significant step forward in producing remarkably controllable, fluent, and grammatical text. Although studies have found that AI-generated text is not distinguishable from human-written text for crowd-sourcing workers, there still exist errors in AI-generated text which are even subtler and harder to spot. We primarily focus on the scenario in which scientific AI writing assistant is deeply involved. First, we construct a feature description framework to distinguish between AI-generated text and human-written text from syntax, semantics, and pragmatics based on the human evaluation. Then we utilize the features, i.e., writing style, coherence, consistency, and argument logistics, from the proposed framework to analyze two types of content. Finally, we adopt several publicly available methods to investigate the gap of between AI-generated scientific text and human-written scientific text by AI-generated scientific text detection models. The results suggest that while AI has the potential to generate scientific content that is as accurate as human-written content, there is still a gap in terms of depth and overall quality. The AI-generated scientific content is more likely to contain errors in factual issues. We find that there exists a "writing style" gap between AI-generated scientific text and human-written scientific text. Based on the analysis result, we summarize a series of model-agnostic and distribution-agnostic features for detection tasks in other domains. Findings in this paper contribute to guiding the optimization of AI models to produce high-quality content and addressing related ethical and security concerns.

cs.CL↗