arXiv subjects

Jie Lu

Publications and source records attributed to Jie Lu.

At least 109 records · Page 6Linked to original sources

arXiv2024

Methodology and Real-World Applications of Dynamic Uncertain Causality Graph for Clinical Diagnosis with Explainability and Invariance

AI-aided clinical diagnosis is desired in medical care. Existing deep learning models lack explainability and mainly focus on image analysis. The recently developed Dynamic Uncertain Causality Graph (DUCG) approach is causality-driven, explainable, and invariant across different application scenarios, without problems of data collection, labeling, fitting, privacy, bias, generalization, high cost and high energy consumption. Through close collaboration between clinical experts and DUCG technicians, 46 DUCG models covering 54 chief complaints were constructed. Over 1,000 diseases can be diagnosed without triage. Before being applied in real-world, the 46 DUCG models were retrospectively verified by third-party hospitals. The verified diagnostic precisions were no less than 95%, in which the diagnostic precision for every disease including uncommon ones was no less than 80%. After verifications, the 46 DUCG models were applied in the real-world in China. Over one million real diagnosis cases have been performed, with only 17 incorrect diagnoses identified. Due to DUCG's transparency, the mistakes causing the incorrect diagnoses were found and corrected. The diagnostic abilities of the clinicians who applied DUCG frequently were improved significantly. Following the introduction to the earlier presented DUCG methodology, the recommendation algorithm for potential medical checks is presented and the key idea of DUCG is extracted.

cs.AI↗

arXiv2024

A Neighbor-Searching Discrepancy-based Drift Detection Scheme for Learning Evolving Data

Uncertain changes in data streams present challenges for machine learning models to dynamically adapt and uphold performance in real-time. Particularly, classification boundary change, also known as real concept drift, is the major cause of classification performance deterioration. However, accurately detecting real concept drift remains challenging because the theoretical foundations of existing drift detection methods - two-sample distribution tests and monitoring classification error rate, both suffer from inherent limitations such as the inability to distinguish virtual drift (changes not affecting the classification boundary, will introduce unnecessary model maintenance), limited statistical power, or high computational cost. Furthermore, no existing detection method can provide information on the trend of the drift, which could be invaluable for model maintenance. This work presents a novel real concept drift detection method based on Neighbor-Searching Discrepancy, a new statistic that measures the classification boundary difference between two samples. The proposed method is able to detect real concept drift with high accuracy while ignoring virtual drift. It can also indicate the direction of the classification boundary change by identifying the invasion or retreat of a certain class, which is also an indicator of separability change between classes. A comprehensive evaluation of 11 experiments is conducted, including empirical verification of the proposed theory using artificial datasets, and experimental comparisons with commonly used drift handling methods on real-world datasets. The results show that the proposed theory is robust against a range of distributions and dimensions, and the drift detection method outperforms state-of-the-art alternative methods.

cs.LG↗

arXiv2024

A Behavior-Aware Approach for Deep Reinforcement Learning in Non-stationary Environments without Known Change Points

Deep reinforcement learning is used in various domains, but usually under the assumption that the environment has stationary conditions like transitions and state distributions. When this assumption is not met, performance suffers. For this reason, tracking continuous environmental changes and adapting to unpredictable conditions is challenging yet crucial because it ensures that systems remain reliable and flexible in practical scenarios. Our research introduces Behavior-Aware Detection and Adaptation (BADA), an innovative framework that merges environmental change detection with behavior adaptation. The key inspiration behind our method is that policies exhibit different global behaviors in changing environments. Specifically, environmental changes are identified by analyzing variations between behaviors using Wasserstein distances without manually set thresholds. The model adapts to the new environment through behavior regularization based on the extent of changes. The results of a series of experiments demonstrate better performance relative to several current algorithms. This research also indicates significant potential for tackling this long-standing challenge.

cs.LG↗

arXiv2024

Responsible AI: Portraits with Intelligent Bibliometrics

Shifting the focus from principles to practical implementation, responsible artificial intelligence (AI) has garnered considerable attention across academia, industry, and society at large. Despite being in its nascent stages, this emerging field grapples with nebulous concepts and intricate knowledge frameworks. By analyzing three prevailing concepts - explainable AI, trustworthy AI, and ethical AI, this study defined responsible AI and identified its core principles. Methodologically, this study successfully demonstrated the implementation of leveraging AI's capabilities into bibliometrics for enhanced knowledge discovery and the cross-validation of experimentally examined models with domain insights. Empirically, this study investigated 17,799 research articles contributed by the AI community since 2015. This involves recognizing key technological players and their relationships, unveiling the topical landscape and hierarchy of responsible AI, charting its evolution, and elucidating the interplay between the responsibility principles and primary AI techniques. An analysis of a core cohort comprising 380 articles from multiple disciplines captures the most recent advancements in responsible AI. As one of the pioneering bibliometric studies dedicated to exploring responsible AI, this study will provide comprehensive macro-level insights, enhancing the understanding of responsible AI while furnishing valuable knowledge support for AI regulation and governance initiatives.

cs.AI↗

arXiv2024

On the Learnability of Out-of-distribution Detection

Supervised learning aims to train a classifier under the assumption that training and test data are from the same distribution. To ease the above assumption, researchers have studied a more realistic setting: out-of-distribution (OOD) detection, where test data may come from classes that are unknown during training (i.e., OOD data). Due to the unavailability and diversity of OOD data, good generalization ability is crucial for effective OOD detection algorithms, and corresponding learning theory is still an open problem. To study the generalization of OOD detection, this paper investigates the probably approximately correct (PAC) learning theory of OOD detection that fits the commonly used evaluation metrics in the literature. First, we find a necessary condition for the learnability of OOD detection. Then, using this condition, we prove several impossibility theorems for the learnability of OOD detection under some scenarios. Although the impossibility theorems are frustrating, we find that some conditions of these impossibility theorems may not hold in some practical scenarios. Based on this observation, we next give several necessary and sufficient conditions to characterize the learnability of OOD detection in some practical scenarios. Lastly, we offer theoretical support for representative OOD detection works based on our OOD theory.

cs.LG↗

arXiv2024

Layer-diverse Negative Sampling for Graph Neural Networks

Graph neural networks (GNNs) are a powerful solution for various structure learning applications due to their strong representation capabilities for graph data. However, traditional GNNs, relying on message-passing mechanisms that gather information exclusively from first-order neighbours (known as positive samples), can lead to issues such as over-smoothing and over-squashing. To mitigate these issues, we propose a layer-diverse negative sampling method for message-passing propagation. This method employs a sampling matrix within a determinantal point process, which transforms the candidate set into a space and selectively samples from this space to generate negative samples. To further enhance the diversity of the negative samples during each forward pass, we develop a space-squeezing method to achieve layer-wise diversity in multi-layer GNNs. Experiments on various real-world graph datasets demonstrate the effectiveness of our approach in improving the diversity of negative samples and overall learning performance. Moreover, adding negative samples dynamically changes the graph's topology, thus with the strong potential to improve the expressiveness of GNNs and reduce the risk of over-squashing.

cs.LG↗

arXiv2024

A Mixing-Accelerated Primal-Dual Proximal Algorithm for Distributed Nonconvex Optimization

In this paper, we develop a distributed mixing-accelerated primal-dual proximal algorithm, referred to as MAP-Pro, which enables nodes in multi-agent networks to cooperatively minimize the sum of their nonconvex, smooth local cost functions in a decentralized fashion. The proposed algorithm is constructed upon minimizing a computationally inexpensive augmented-Lagrangian-like function and incorporating a time-varying mixing polynomial to expedite information fusion across the network. The convergence results derived for MAP-Pro include a sublinear rate of convergence to a stationary solution and, under the Polyak-Łojasiewics (P-Ł) condition, a linear rate of convergence to the global optimal solution. Additionally, we may embed the well-noted Chebyshev acceleration scheme in MAP-Pro, which generates a specific sequence of mixing polynomials with given degrees and enhances the convergence performance based on MAP-Pro. Finally, we illustrate the competitive convergence speed and communication efficiency of MAP-Pro via a numerical example.

math.OC↗

arXiv2024

Analysis of the electromagnetic form factors and the radiative decays of the vector heavy-light mesons

In this article, we analyze the electromagnetic form factors of the vector heavy-light mesons to the pseudoscalar heavy-light mesons in the framework of three-point QCD sum rules, where the contributions of vacuum condensate terms $\langle\overline{q}q\rangle$, $\langle\overline{q}g_{s}σGq\rangle$, $\langle g_{s}^{2}G^{2}\rangle$, $\langle f^{3}G^{3}\rangle$ and $\langle\overline{q}q\rangle\langle g_{s}^{2}G^{2}\rangle$ are considered. With these results, we also obtain the radiative decay widths of the vector heavy-light mesons and then compare our results with those of other collaboration's. The final results about the radiative decay widths are $Γ(D^{*0}\to D^{0}γ)=1.74^{+0.40}_{-0.37}$ keV, $Γ(D^{*+}\to D^{+}γ)=0.17^{+0.08}_{-0.07}$ keV, $Γ(D_{s}^{*}\to D_{s}γ)=0.029^{+0.009}_{-0.008}$ keV, $Γ(B^{*0}\to B^{0}γ)=0.018^{+0.006}_{-0.005}$ keV, $Γ(B^{*+}\to B^{+}γ)=0.015^{+0.007}_{-0.007}$ keV and $Γ(B^{*}_{s}\to B_{s}γ)=0.016^{+0.003}_{-0.005}$ keV.

hep-ph↗

arXiv2024

A Deep Reinforcement Learning Approach to Efficient Distributed Optimization

In distributed optimization, the practical problem-solving performance is essentially sensitive to algorithm selection, parameter setting, problem type and data pattern. Thus, it is often laborious to acquire a highly efficient method for a given specific problem. In this paper, we propose a learning-based method to achieve efficient distributed optimization over networked systems. Specifically, a deep reinforcement learning (DRL) framework is developed for adaptive configuration within a parameterized unifying algorithmic form, which incorporates an abundance of decentralized first-order and second-order optimization algorithms. We exploit the local consensus and objective information to represent the regularities of problem instances and trace the solving progress, which constitute the states observed by a DRL agent. The framework is trained using Proximal Policy Optimization (PPO) on a number of practical problem instances of similar structures yet different problem data. Experiments on various smooth and non-smooth classes of objective functions demonstrate that our proposed learning-based method outperforms several state-of-the-art distributed optimization algorithms in terms of convergence speed and solution accuracy.

math.OC↗

arXiv2024

Online Boosting Adaptive Learning under Concept Drift for Multistream Classification

Multistream classification poses significant challenges due to the necessity for rapid adaptation in dynamic streaming processes with concept drift. Despite the growing research outcomes in this area, there has been a notable oversight regarding the temporal dynamic relationships between these streams, leading to the issue of negative transfer arising from irrelevant data. In this paper, we propose a novel Online Boosting Adaptive Learning (OBAL) method that effectively addresses this limitation by adaptively learning the dynamic correlation among different streams. Specifically, OBAL operates in a dual-phase mechanism, in the first of which we design an Adaptive COvariate Shift Adaptation (AdaCOSA) algorithm to construct an initialized ensemble model using archived data from various source streams, thus mitigating the covariate shift while learning the dynamic correlations via an adaptive re-weighting strategy. During the online process, we employ a Gaussian Mixture Model-based weighting mechanism, which is seamlessly integrated with the acquired correlations via AdaCOSA to effectively handle asynchronous drift. This approach significantly improves the predictive performance and stability of the target stream. We conduct comprehensive experiments on several synthetic and real-world data streams, encompassing various drifting scenarios and types. The results clearly demonstrate that OBAL achieves remarkable advancements in addressing multistream classification problems by effectively leveraging positive knowledge derived from multiple sources.

cs.LG↗

arXiv2023

Analysis of the strong vertices of $Σ_{c}ΔD^{}$ and $Σ_{b}ΔB^{}$ in QCD sum rules

In this work, we analyze the strong vertices $Σ_{c}ΔD^{*}$ and $Σ_{b}ΔB^{*}$ using the three-point QCD sum rules under the tensor structures $iε^{ρταβ}p_αp'_β$, $p^ρp'^τ$ and $p^ρp^τ$. We firstly calculate the momentum dependent strong coupling constants $g(Q^{2})$ by considering contributions of the perturbative part and the condensate terms $\langle\overline{q}q\rangle$, $\langle g_{s}^{2}GG \rangle$, $\langle\overline{q}g_{s}σGq\rangle$ and $\langle\overline{q}q\rangle^{2}$. By fitting these coupling constants into analytical functions and extrapolating them into time-like regions, we then obtain the on-shell values of strong coupling constants for these vertices. The results are $g_{1Σ_{c}ΔD^{*}}=5.13^{+0.39}_{-0.49}$ GeV$^{-1}$, $g_{2Σ_{c}ΔD^{*}}=-3.03^{+0.27}_{-0.35}$ GeV$^{-2}$, $g_{3Σ_{c}ΔD^{*}}=17.64^{+1.51}_{-1.95}$ GeV$^{-2}$, $g_{1Σ_{b}ΔB^{*}}=20.97^{+2.15}_{-2.39}$ GeV$^{-1}$, $g_{2Σ_{b}ΔB^{*}}=-11.42^{+1.17}_{-1.28}$ GeV$^{-2}$ and $g_{3Σ_{b}ΔB^{*}}=24.87^{+2.57}_{-2.82}$ GeV$^{-2}$. These strong coupling constants are important parameters which can help us to understand the strong decay behaviors of hadrons.

hep-ph↗

arXiv2023

A Distributed Buffering Drift-Plus-Penalty Algorithm for Coupling Constrained Optimization

This paper focuses on distributed constrained optimization over time-varying directed networks, where all agents cooperate to optimize the sum of their locally accessible objective functions subject to a coupled inequality constraint consisting of all their local constraint functions. To address this problem, we develop a buffering drift-plus-penalty algorithm, referred to as B-DPP. The proposed B-DPP algorithm utilizes the idea of drift-plus-penalty minimization in centralized optimization to control constraint violation and objective error, and adapts it to the distributed setting. It also innovatively incorporates a buffer variable into local virtual queue updates to acquire flexible and desirable tracking of constraint violation. We show that B-DPP achieves $O(1/\sqrt{t})$ rates of convergence to both optimality and feasibility, which outperform the alternative methods in the literature. Moreover, with a proper buffer parameter, B-DPP is capable of reaching feasibility within a finite number of iterations, which is a pioneering result in the area. Simulations on a resource allocation problem over 5G virtualized networks demonstrate the competitive convergence performance and efficiency of B-DPP.

math.OC↗

arXiv2023

The strong vertices of bottom mesons $B$, $B^{*}$ and bottomonia $Υ$, $η_{b}$

In this article, the strong coupling constants of vertices $BBΥ$, $BB^{*}Υ$, $B^{*}B^{*}Υ$, $BB^{*}η_{b}$ and $B^{*}B^{*}η_{b}$ are analyzed in the framework of QCD sum rules. In this work, all possible off-shell cases and the contributions of vacuum condensate terms including $\langle\overline{q}q\rangle$, $\langle\overline{q}g_{s}σGq\rangle$, $\langle g_{s}^{2}G^{2}\rangle$, $\langle f^{3}G^{3}\rangle$ and $\langle\overline{q}q\rangle\langle g_{s}^{2}G^{2}\rangle$ are considered. The momentum dependent strong coupling constants are first calculated and then are fitted into analytical functions $g(Q^{2})$ which are used to extrapolate into time-like regions to obtain the final values of strong coupling constants. The final results are $g_{BBΥ}=40.67^{+7.55}_{-4.20}$, $g_{BB^{*}Υ}=11.58^{+2.19}_{-1.09}$ GeV$^{-1}$, $g_{B^{*}B^{*}Υ}=57.02^{+5.32}_{-5.31}$, $g_{BB^{*}η_{b}}=23.39^{+4.74}_{-2.30}$ and $g_{B^{*}B^{*}η_{b}}=12.49^{+2.12}_{-1.35}$ GeV$^{-1}$. These strong coupling constants are important input parameters which reflect the dynamic properties of the interactions among the mesons and quarkonia.

hep-ph↗

arXiv2023

The strong vertices of charmed mesons $D$, $D^{*}$ and charmonia $J/ψ$, $η_{c}$

In this work, the strong coupling constants of the vertices $DDJ/ψ$, $DD^{*}J/ψ$, $D^{*}D^{*}J/ψ$, $DD^{*}η_{c}$ and $D^{*}D^{*}η_{c}$ are calculated within the framework of the QCD sum rules. For each vertex, we analyze the momentum dependence of the coupling constants by considering all possible off-shell cases. In these analyses, we consider the contributions of the vacuum condensate terms $\langle\overline{q}q\rangle$, $\langle\overline{q}g_{s}σGq\rangle$, $\langle g_{s}^{2}G^{2}\rangle$, $\langle f^{3}G^{3}\rangle$ and $\langle\overline{q}q\rangle\langle g_{s}^{2}G^{2}\rangle$. Then, the momentum dependent coupling constants are fitted into analytical functions $g(Q^2)$ and are extrapolated into time-like regions. The values of strong coupling constants are obtained by using on-shell conditions of the intermediate mesons($Q^2=-m^2$). The final results are as follows, $g_{DDJ/ψ}=5.01^{+0.58}_{-0.16}$, $g_{DD^{*}J/ψ}=3.55^{+0.20}_{-0.21}$GeV$^{-1}$, $g_{D^{*}D^{*}J/ψ}=5.10^{+0.59}_{-0.43}$, $g_{DD^{*}η_{c}}=3.68^{+0.39}_{-0.11}$ and $g_{D^{*}D^{*}η_{c}}=4.87^{+0.42}_{-0.40}$GeV$^{-1}$.

hep-ph↗

arXiv2023

Meta OOD Learning for Continuously Adaptive OOD Detection

Out-of-distribution (OOD) detection is crucial to modern deep learning applications by identifying and alerting about the OOD samples that should not be tested or used for making predictions. Current OOD detection methods have made significant progress when in-distribution (ID) and OOD samples are drawn from static distributions. However, this can be unrealistic when applied to real-world systems which often undergo continuous variations and shifts in ID and OOD distributions over time. Therefore, for an effective application in real-world systems, the development of OOD detection methods that can adapt to these dynamic and evolving distributions is essential. In this paper, we propose a novel and more realistic setting called continuously adaptive out-of-distribution (CAOOD) detection which targets on developing an OOD detection model that enables dynamic and quick adaptation to a new arriving distribution, with insufficient ID samples during deployment time. To address CAOOD, we develop meta OOD learning (MOL) by designing a learning-to-adapt diagram such that a good initialized OOD detection model is learned during the training process. In the testing process, MOL ensures OOD detection performance over shifting distributions by quickly adapting to new distributions with a few adaptations. Extensive experiments on several OOD benchmarks endorse the effectiveness of our method in preserving both ID classification accuracy and OOD detection performance on continuously shifting distributions.

cs.LG↗

arXiv2023

Graph Convolutional Neural Networks with Diverse Negative Samples via Decomposed Determinant Point Processes

Graph convolutional networks (GCNs) have achieved great success in graph representation learning by extracting high-level features from nodes and their topology. Since GCNs generally follow a message-passing mechanism, each node aggregates information from its first-order neighbour to update its representation. As a result, the representations of nodes with edges between them should be positively correlated and thus can be considered positive samples. However, there are more non-neighbour nodes in the whole graph, which provide diverse and useful information for the representation update. Two non-adjacent nodes usually have different representations, which can be seen as negative samples. Besides the node representations, the structural information of the graph is also crucial for learning. In this paper, we used quality-diversity decomposition in determinant point processes (DPP) to obtain diverse negative samples. When defining a distribution on diverse subsets of all non-neighbouring nodes, we incorporate both graph structure information and node representations. Since the DPP sampling process requires matrix eigenvalue decomposition, we propose a new shortest-path-base method to improve computational efficiency. Finally, we incorporate the obtained negative samples into the graph convolution operation. The ideas are evaluated empirically in experiments on node classification tasks. These experiments show that the newly proposed methods not only improve the overall performance of standard representation learning but also significantly alleviate over-smoothing problems.

cs.LG↗

arXiv2023

Distributed Online Optimization with Coupled Inequality Constraints over Unbalanced Directed Networks

This paper studies a distributed online convex optimization problem, where agents in an unbalanced network cooperatively minimize the sum of their time-varying local cost functions subject to a coupled inequality constraint. To solve this problem, we propose a distributed dual subgradient tracking algorithm, called DUST, which attempts to optimize a dual objective by means of tracking the primal constraint violations and integrating dual subgradient and push sum techniques. Different from most existing works, we allow the underlying network to be unbalanced with a column stochastic mixing matrix. We show that DUST achieves sublinear dynamic regret and constraint violations, provided that the accumulated variation of the optimal sequence grows sublinearly. If the standard Slater's condition is additionally imposed, DUST acquires a smaller constraint violation bound than the alternative existing methods applicable to unbalanced networks. Simulations on a plug-in electric vehicle charging problem demonstrate the superior convergence of DUST.

math.OC↗

arXiv2023

Exploring wavefunction hybridization of magnon-magnon hybrid state

We investigate magnon magnon hybrid states using a non Hermitian two band Hamiltonian and the concept of wavefunction hybridization. By comparing our model with micromagnetic simulations conducted on a synthetic antiferromagnet with strong magnon magnon coupling, we successfully reproduce not only the resonance frequencies and linewidths but also the phases and amplitudes of the magnon wavefunction. The hybridization effect influences the dissipation rate, leading to the crossing of linewidths. Additionally, we quantify the magnon hybridization within a magnonic Bloch sphere, which enhances the ability to manipulate hybrid magnons for coherent information processing.

cond-mat.mes-hall↗