arXiv subjects

Ning Li

Publications and source records attributed to Ning Li.

At least 91 records · Page 5Linked to original sources

arXiv2024

Incremental Online Learning of Randomized Neural Network with Forward Regularization

Online learning of deep neural networks suffers from challenges such as hysteretic non-incremental updating, increasing memory usage, past retrospective retraining, and catastrophic forgetting. To alleviate these drawbacks and achieve progressive immediate decision-making, we propose a novel Incremental Online Learning (IOL) process of Randomized Neural Networks (Randomized NN), a framework facilitating continuous improvements to Randomized NN performance in restrictive online scenarios. Within the framework, we further introduce IOL with ridge regularization (-R) and IOL with forward regularization (-F). -R generates stepwise incremental updates without retrospective retraining and avoids catastrophic forgetting. Moreover, we substituted -R with -F as it enhanced precognition learning ability using semi-supervision and realized better online regrets to offline global experts compared to -R during IOL. The algorithms of IOL for Randomized NN with -R/-F on non-stationary batch stream were derived respectively, featuring recursive weight updates and variable learning rates. Additionally, we conducted a detailed analysis and theoretically derived relative cumulative regret bounds of the Randomized NN learners with -R/-F in IOL under adversarial assumptions using a novel methodology and presented several corollaries, from which we observed the superiority on online learning acceleration and regret bounds of employing -F in IOL. Finally, our proposed methods were rigorously examined across regression and classification tasks on diverse datasets, which distinctly validated the efficacy of IOL frameworks of Randomized NN and the advantages of forward regularization.

cs.LG↗

arXiv2024

Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity

Deep Reinforcement Learning (DRL) has exhibited efficacy in resolving the Local Path Planning (LPP) problem. However, such application in the real world is immensely limited due to the deficient training efficiency and generalization capability of DRL. To alleviate these two issues, a solution named Color is proposed, which consists of an Actor-Sharer-Learner (ASL) training framework and a mobile robot-oriented simulator Sparrow. Specifically, the ASL intends to improve the training efficiency of DRL algorithms. It employs a Vectorized Data Collection (VDC) mode to expedite data acquisition, decouples the data collection from model optimization by multithreading, and partially connects the two procedures by harnessing a Time Feedback Mechanism (TFM) to evade data underuse or overuse. Meanwhile, the Sparrow simulator utilizes a 2D grid-based world, simplified kinematics, and conversion-free data flow to achieve a lightweight design. The lightness facilitates vectorized diversity, allowing diversified simulation setups across extensive copies of the vectorized environments, resulting in a notable enhancement in the generalization capability of the DRL algorithm being trained. Comprehensive experiments, comprising 57 DRL benchmark environments, 32 simulated and 36 real-world LPP scenarios, have been conducted to corroborate the superiority of our method in terms of efficiency and generalization. The code and the video of this paper are accessible at https://github.com/XinJingHao/Color.

cs.AI↗

arXiv2024

Augmenting Minds or Automating Skills: The Differential Role of Human Capital in Generative AI's Impact on Creative Tasks

Generative AI is rapidly reshaping creative work, raising critical questions about its beneficiaries and societal implications. This study challenges prevailing assumptions by exploring how generative AI interacts with diverse forms of human capital in creative tasks. Through two random controlled experiments in flash fiction writing and song composition, we uncover a paradox: while AI democratizes access to creative tools, it simultaneously amplifies cognitive inequalities. Our findings reveal that AI enhances general human capital (cognitive abilities and education) by facilitating adaptability and idea integration but diminishes the value of domain-specific expertise. We introduce a novel theoretical framework that merges human capital theory with the automation-augmentation perspective, offering a nuanced understanding of human-AI collaboration. This framework elucidates how AI shifts the locus of creative advantage from specialized expertise to broader cognitive adaptability. Contrary to the notion of AI as a universal equalizer, our work highlights its potential to exacerbate disparities in skill valuation, reshaping workplace hierarchies and redefining the nature of creativity in the AI era. These insights advance theories of human capital and automation while providing actionable guidance for organizations navigating AI integration amidst workforce inequalities.

cs.HC↗

arXiv2024

Orthogonal Mode Decomposition for Finite Discrete Signals

In this paper, an orthogonal mode decomposition method is proposed to decompose ffnite length real signals on both the real and imaginary axes of the complex plane. The interpolation function space of ffnite length discrete signal is constructed, and the relationship between the dimensionality of the interpolation function space and its subspaces and the band width of the interpolation function is analyzed. It is proved that the intrinsic mode is actually the narrow band signal whose intrinsic instantaneous frequency is always positive (or always negative). Thus, the eigenmode decomposition problem is transformed into the orthogonal projection problem of interpolation function space to its low frequency subspace or narrow band subspace. Different from the existing mode decomposition methods, the orthogonal modal decomposition is a local time-frequency domain algorithm. Each operation extracts a speciffc mode. The global decomposition results obtained under the precise deffnition of eigenmodes have uniqueness and orthogonality. The computational complexity of the orthogonal mode decomposition method is also much smaller than that of the existing mode decomposition methods.

eess.SY↗

arXiv2024

Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following

Large Language Models (LLMs) have demonstrated impressive capabilities in various tasks, including instruction following, which is crucial for aligning model outputs with user expectations. However, evaluating LLMs' ability to follow instructions remains challenging due to the complexity and subjectivity of human language. Current benchmarks primarily focus on single-turn, monolingual instructions, which do not adequately reflect the complexities of real-world applications that require handling multi-turn and multilingual interactions. To address this gap, we introduce Multi-IF, a new benchmark designed to assess LLMs' proficiency in following multi-turn and multilingual instructions. Multi-IF, which utilizes a hybrid framework combining LLM and human annotators, expands upon the IFEval by incorporating multi-turn sequences and translating the English prompts into another 7 languages, resulting in a dataset of 4,501 multilingual conversations, where each has three turns. Our evaluation of 14 state-of-the-art LLMs on Multi-IF reveals that it presents a significantly more challenging task than existing benchmarks. All the models tested showed a higher rate of failure in executing instructions correctly with each additional turn. For example, o1-preview drops from 0.877 at the first turn to 0.707 at the third turn in terms of average accuracy over all languages. Moreover, languages with non-Latin scripts (Hindi, Russian, and Chinese) generally exhibit higher error rates, suggesting potential limitations in the models' multilingual capabilities. We release Multi-IF prompts and the evaluation code base to encourage further research in this critical area.

cs.CL↗

arXiv2024

A Method for Constructing Wavelet Functions on the Real Number Field

A general method to construct wavelet function on real number ffeld is proposed in this article,which is based on finite length sequence.This finite length sequence is called the seed sequence, and the corresponding wavelet function is called the seed sequence wavelet function.The seed sequence wavelet function is continuous and energy concentrated in both time and frequency domains,That is, it has a finite support set in both time and frequency domains. It is proved that if and only if the seed sequence has 0 mean value, the interpolation function satisfy the admissible condition of wavelet function. The conditions corresponding to the higher order vanishing moment of the seed sequence wavelet function are also given in this article. On this basis, the concept of random wavelet function is proposed, and the condition of the regularity of random wavelet is discussed.

eess.SY↗

arXiv2024

Hard Region Aware Network for Remote Sensing Change Detection

Change detection (CD) is essential for various real-world applications, such as urban management and disaster assessment. Numerous CD methods have been proposed, and considerable results have been achieved recently. However, detecting changes in hard regions, i.e., the change boundary and irrelevant pseudo changes caused by background clutters, remains difficult for these methods, since they pose equal attention for all regions in bi-temporal images. This paper proposes a novel change detection network, termed as HRANet, which provides accurate change maps via hard region mining. Specifically, an online hard region estimation branch is constructed to model the pixel-wise hard samples, supervised by the error between predicted change maps and corresponding ground truth during the training process. A cross-layer knowledge review module is introduced to distill temporal change information from low-level to high-level features, thereby enhancing the feature representation capabilities. Finally, the hard region aware features extracted from the online hard region estimation branch and multi-level temporal difference features are aggregated into a unified feature representation to improve the accuracy of CD. Experimental results on two benchmark datasets demonstrate the superior performance of HRANet in the CD task.

cs.CV↗

arXiv2024

ELF-Gym: Evaluating Large Language Models Generated Features for Tabular Prediction

Crafting effective features is a crucial yet labor-intensive and domain-specific task within machine learning pipelines. Fortunately, recent advancements in Large Language Models (LLMs) have shown promise in automating various data science tasks, including feature engineering. But despite this potential, evaluations thus far are primarily based on the end performance of a complete ML pipeline, providing limited insight into precisely how LLMs behave relative to human experts in feature engineering. To address this gap, we propose ELF-Gym, a framework for Evaluating LLM-generated Features. We curated a new dataset from historical Kaggle competitions, including 251 "golden" features used by top-performing teams. ELF-Gym then quantitatively evaluates LLM-generated features by measuring their impact on downstream model performance as well as their alignment with expert-crafted features through semantic and functional similarity assessments. This approach provides a more comprehensive evaluation of disparities between LLMs and human experts, while offering valuable insights into specific areas where LLMs may have room for improvement. For example, using ELF-Gym we empirically demonstrate that, in the best-case scenario, LLMs can semantically capture approximately 56% of the golden features, but at the more demanding implementation level this overlap drops to 13%. Moreover, in other cases LLMs may fail completely, particularly on datasets that require complex features, indicating broad potential pathways for improvement.

cs.CL↗

arXiv2024

A QoE-Aware Split Inference Accelerating Algorithm for NOMA-based Edge Intelligence

Even the AI has been widely used and significantly changed our life, deploying the large AI models on resource limited edge devices directly is not appropriate. Thus, the model split inference is proposed to improve the performance of edge intelligence, in which the AI model is divided into different sub models and the resource-intensive sub model is offloaded to edge server wirelessly for reducing resource requirements and inference latency. However, the previous works mainly concentrate on improving and optimizing the system QoS, ignore the effect of QoE which is another critical item for the users except for QoS. Even the QoE has been widely learned in EC, considering the differences between task offloading in EC and split inference in EI, and the specific issues in QoE which are still not addressed in EC and EI, these algorithms cannot work effectively in edge split inference scenarios. Thus, an effective resource allocation algorithm is proposed in this paper, for accelerating split inference in EI and achieving the tradeoff between inference delay, QoE, and resource consumption, abbreviated as ERA. Specifically, the ERA takes the resource consumption, QoE, and inference latency into account to find the optimal model split strategy and resource allocation strategy. Since the minimum inference delay and resource consumption, and maximum QoE cannot be satisfied simultaneously, the gradient descent based algorithm is adopted to find the optimal tradeoff between them. Moreover, the loop iteration GD approach is developed to reduce the complexity of the GD algorithm caused by parameter discretization. Additionally, the properties of the proposed algorithms are investigated, including convergence, complexity, and approximation error. The experimental results demonstrate that the performance of ERA is much better than that of the previous studies.

cs.LG↗

arXiv2024

Multi-Modal Dialogue State Tracking for Playing GuessWhich Game

GuessWhich is an engaging visual dialogue game that involves interaction between a Questioner Bot (QBot) and an Answer Bot (ABot) in the context of image-guessing. In this game, QBot's objective is to locate a concealed image solely through a series of visually related questions posed to ABot. However, effectively modeling visually related reasoning in QBot's decision-making process poses a significant challenge. Current approaches either lack visual information or rely on a single real image sampled at each round as decoding context, both of which are inadequate for visual reasoning. To address this limitation, we propose a novel approach that focuses on visually related reasoning through the use of a mental model of the undisclosed image. Within this framework, QBot learns to represent mental imagery, enabling robust visual reasoning by tracking the dialogue state. The dialogue state comprises a collection of representations of mental imagery, as well as representations of the entities involved in the conversation. At each round, QBot engages in visually related reasoning using the dialogue state to construct an internal representation, generate relevant questions, and update both the dialogue state and internal representation upon receiving an answer. Our experimental results on the VisDial datasets (v0.5, 0.9, and 1.0) demonstrate the effectiveness of our proposed model, as it achieves new state-of-the-art performance across all metrics and datasets, surpassing previous state-of-the-art models. Codes and datasets from our experiments are freely available at \href{https://github.com/xubuvd/GuessWhich}.

cs.AI↗

arXiv2024

Look into the Future: Deep Contextualized Sequential Recommendation

Sequential recommendation aims to estimate how a user's interests evolve over time via uncovering valuable patterns from user behavior history. Many previous sequential models have solely relied on users' historical information to model the evolution of their interests, neglecting the crucial role that future information plays in accurately capturing these dynamics. However, effectively incorporating future information in sequential modeling is non-trivial since it is impossible to make the current-step prediction for any target user by leveraging his future data. In this paper, we propose a novel framework of sequential recommendation called Look into the Future (LIFT), which builds and leverages the contexts of sequential recommendation. In LIFT, the context of a target user's interaction is represented based on i) his own past behaviors and ii) the past and future behaviors of the retrieved similar interactions from other users. As such, the learned context will be more informative and effective in predicting the target user's behaviors in sequential recommendation without temporal data leakage. Furthermore, in order to exploit the intrinsic information embedded within the context itself, we introduce an innovative pretraining methodology incorporating behavior masking. In our extensive experiments on five real-world datasets, LIFT achieves significant performance improvement on click-through rate prediction and rating prediction tasks in sequential recommendation over strong baselines, demonstrating that retrieving and leveraging relevant contexts from the global user pool greatly benefits sequential recommendation. The experiment code is provided at https://anonymous.4open.science/r/LIFT-277C/Readme.md.

cs.IR↗

arXiv2024

Enhancing Visual Dialog State Tracking through Iterative Object-Entity Alignment in Multi-Round Conversations

Visual Dialog (VD) is a task where an agent answers a series of image-related questions based on a multi-round dialog history. However, previous VD methods often treat the entire dialog history as a simple text input, disregarding the inherent conversational information flows at the round level. In this paper, we introduce Multi-round Dialogue State Tracking model (MDST), a framework that addresses this limitation by leveraging the dialogue state learned from dialog history to answer questions. MDST captures each round of dialog history, constructing internal dialogue state representations defined as 2-tuples of vision-language representations. These representations effectively ground the current question, enabling the generation of accurate answers. Experimental results on the VisDial v1.0 dataset demonstrate that MDST achieves a new state-of-the-art performance in generative setting. Furthermore, through a series of human studies, we validate the effectiveness of MDST in generating long, consistent, and human-like answers while consistently answering a series of questions correctly.

cs.AI↗

arXiv2024

From Text to Insight: Leveraging Large Language Models for Performance Evaluation in Management

This study explores the potential of Large Language Models (LLMs), specifically GPT-4, to enhance objectivity in organizational task performance evaluations. Through comparative analyses across two studies, including various task performance outputs, we demonstrate that LLMs can serve as a reliable and even superior alternative to human raters in evaluating knowledge-based performance outputs, which are a key contribution of knowledge workers. Our results suggest that GPT ratings are comparable to human ratings but exhibit higher consistency and reliability. Additionally, combined multiple GPT ratings on the same performance output show strong correlations with aggregated human performance ratings, akin to the consensus principle observed in performance evaluation literature. However, we also find that LLMs are prone to contextual biases, such as the halo effect, mirroring human evaluative biases. Our research suggests that while LLMs are capable of extracting meaningful constructs from text-based data, their scope is currently limited to specific forms of performance evaluation. By highlighting both the potential and limitations of LLMs, our study contributes to the discourse on AI role in management studies and sets a foundation for future research to refine AI theoretical and practical applications in management.

cs.CL↗

arXiv2024

PromptSAM+: Malware Detection based on Prompt Segment Anything Model

Machine learning and deep learning (ML/DL) have been extensively applied in malware detection, and some existing methods demonstrate robust performance. However, several issues persist in the field of malware detection: (1) Existing work often overemphasizes accuracy at the expense of practicality, rarely considering false positive and false negative rates as important metrics. (2) Considering the evolution of malware, the performance of classifiers significantly declines over time, greatly reducing the practicality of malware detectors. (3) Prior ML/DL-based efforts heavily rely on ample labeled data for model training, largely dependent on feature engineering or domain knowledge to build feature databases, making them vulnerable if correct labels are scarce. With the development of computer vision, vision-based malware detection technology has also rapidly evolved. In this paper, we propose a visual malware general enhancement classification framework, `PromptSAM+', based on a large visual network segmentation model, the Prompt Segment Anything Model(named PromptSAM+). Our experimental results indicate that 'PromptSAM+' is effective and efficient in malware detection and classification, achieving high accuracy and low rates of false positives and negatives. The proposed method outperforms the most advanced image-based malware detection technologies on several datasets. 'PromptSAM+' can mitigate aging in existing image-based malware classifiers, reducing the considerable manpower needed for labeling new malware samples through active learning. We conducted experiments on datasets for both Windows and Android platforms, achieving favorable outcomes. Additionally, our ablation experiments on several datasets demonstrate that our model identifies effective modules within the large visual network.

cs.CR↗

arXiv2024

Fault-tolerant Quantum Chemical Calculations with Improved Machine-Learning Models

Easy and effective usage of computational resources is crucial for scientific calculations. Following our recent work of machine-learning (ML) assisted scheduling optimization [Ref: J. Comput. Chem. 2023, 44, 1174], we further propose 1) the improve ML models for the better predictions of computational loads, and as such, more elaborate load-balancing calculations can be expected; 2) the idea of coded computation, i.e. the integration of gradient coding, in order to introduce fault tolerance during the distributed calculations; and 3) their applications together with re-normalized exciton model with time-dependent density functional theory (REM-TDDFT) for calculating the excited states. Illustrated benchmark calculations include P38 protein, and solvent model with one or several excitable centers. The results show that the improved ML-assisted coded calculations can further improve the load-balancing and cluster utilization, and owing primarily profit in fault tolerance that aiming at the automated quantum chemical calculations for both ground and excited states.

physics.chem-ph↗

arXiv2024

Structure Factors for Hot Neutron Matter from Ab Initio Lattice Simulations with High-Fidelity Chiral Interactions

We present the first ab initio lattice calculations of spin and density correlations in hot neutron matter using high-fidelity interactions at next-to-next-to-next-to-leading order (N3LO) in chiral effective field theory. These correlations have a large impact on neutrino heating and shock revival in core-collapse supernovae and are encapsulated in functions called structure factors. Unfortunately, calculations of structure factors using high-fidelity chiral interactions were well out of reach using existing computational methods. In this work, we solve the problem using a computational approach called the rank-one operator (RO) method. The RO method is a general technique with broad applications to simulations of fermionic many-body systems. It solves the problem of exponential scaling of computational effort when using perturbation theory for higher-body operators and higher-order corrections. Using the RO method, we compute the vector and axial static structure factors for hot neutron matter as a function of temperature and density. The ab initio lattice results are in good agreement with virial expansion calculations at low densities but are more reliable at higher densities. Random phase approximation codes used to estimate neutrino opacity in core-collapse supernovae simulations can now be calibrated with ab initio lattice calculations.

nucl-th↗

arXiv2024

Wavefunction matching for solving quantum many-body problems

Ab initio calculations play an essential role in our fundamental understanding of quantum many-body systems across many subfields, from strongly correlated fermions to quantum chemistry and from atomic and molecular systems to nuclear physics. One of the primary challenges is to perform accurate calculations for systems where the interactions may be complicated and difficult for the chosen computational method to handle. Here we address the problem by introducing a new approach called wavefunction matching. Wavefunction matching transforms the interaction between particles so that the wavefunctions up to some finite range match that of an easily computable interaction. This allows for calculations of systems that would otherwise be impossible due to problems such as Monte Carlo sign cancellations. We apply the method to lattice Monte Carlo simulations of light nuclei, medium-mass nuclei, neutron matter, and nuclear matter. We use high-fidelity chiral effective field theory interactions and find good agreement with empirical data. These results are accompanied by new insights on the nuclear interactions that may help to resolve long-standing challenges in accurately reproducing nuclear binding energies, charge radii, and nuclear matter saturation in ab initio calculations.

nucl-th↗

arXiv2024

Generative AI Enhances Team Performance and Reduces Need for Traditional Teams

Recent advancements in generative artificial intelligence (AI) have transformed collaborative work processes, yet the impact on team performance remains underexplored. Here we examine the role of generative AI in enhancing or replacing traditional team dynamics using a randomized controlled experiment with 435 participants across 122 teams. We show that teams augmented with generative AI significantly outperformed those relying solely on human collaboration across various performance measures. Interestingly, teams with multiple AIs did not exhibit further gains, indicating diminishing returns with increased AI integration. Our analysis suggests that centralized AI usage by a few team members is more effective than distributed engagement. Additionally, individual-AI pairs matched the performance of conventional teams, suggesting a reduced need for traditional team structures in some contexts. However, despite this capability, individual-AI pairs still fell short of the performance levels achieved by AI-assisted teams. These findings underscore that while generative AI can replace some traditional team functions, more comprehensively integrating AI within team structures provides superior benefits, enhancing overall effectiveness beyond individual efforts.

cs.HC↗