arXiv subjects

Feng Wu

Publications and source records attributed to Feng Wu.

At least 163 records · Page 9Linked to original sources

arXiv2023

Adaptive Spot-Guided Transformer for Consistent Local Feature Matching

Local feature matching aims at finding correspondences between a pair of images. Although current detector-free methods leverage Transformer architecture to obtain an impressive performance, few works consider maintaining local consistency. Meanwhile, most methods struggle with large scale variations. To deal with the above issues, we propose Adaptive Spot-Guided Transformer (ASTR) for local feature matching, which jointly models the local consistency and scale variations in a unified coarse-to-fine architecture. The proposed ASTR enjoys several merits. First, we design a spot-guided aggregation module to avoid interfering with irrelevant areas during feature aggregation. Second, we design an adaptive scaling module to adjust the size of grids according to the calculated depth information at fine stage. Extensive experimental results on five standard benchmarks demonstrate that our ASTR performs favorably against state-of-the-art methods. Our code will be released on https://astr2023.github.io.

cs.CV↗

arXiv2023

De Novo Molecular Generation via Connection-aware Motif Mining

De novo molecular generation is an essential task for science discovery. Recently, fragment-based deep generative models have attracted much research attention due to their flexibility in generating novel molecules based on existing molecule fragments. However, the motif vocabulary, i.e., the collection of frequent fragments, is usually built upon heuristic rules, which brings difficulties to capturing common substructures from large amounts of molecules. In this work, we propose a new method, MiCaM, to generate molecules based on mined connection-aware motifs. Specifically, it leverages a data-driven algorithm to automatically discover motifs from a molecule library by iteratively merging subgraphs based on their frequency. The obtained motif vocabulary consists of not only molecular motifs (i.e., the frequent fragments), but also their connection information, indicating how the motifs are connected with each other. Based on the mined connection-aware motifs, MiCaM builds a connection-aware generator, which simultaneously picks up motifs and determines how they are connected. We test our method on distribution-learning benchmarks (i.e., generating novel molecules to resemble the distribution of a given training set) and goal-directed benchmarks (i.e., generating molecules with target properties), and achieve significant improvements over previous fragment-based baselines. Furthermore, we demonstrate that our method can effectively mine domain-specific motifs for different tasks.

cs.LG↗

arXiv2023

High-efficiency optical frequency mixing in an all-dielectric metasurface enabled by multiple bound states in the continuum

We present nonlinear optical four-wave mixing in a silicon nanodisk dimer metasurface. Under the oblique incident plane waves, the designed metasurface exhibits a multi-resonant feature with simultaneous excitations of three quasi-bound states in the continuum (BIC). Through employing these quasi-BICs with maximizing electric field energy at the input bump wavelengths, significant enhancement of third-order nonlinear processes including third-harmonic generation, degenerate and non-degenerate four-wave mixing are demonstrated, giving rise to ten new frequencies in the visible wavelengths. This work may lead to a new frontier of ultracompact optical mixer for applications in optical circuitry, ultrasensitive sensing, and quantum nanophotonics.

physics.optics↗

arXiv2023

Energy-Efficient Blockchain-enabled User-Centric Mobile Edge Computing

In the traditional mobile edge computing (MEC) system, the availability of MEC services is greatly limited for the edge users of the cell due to serious signal attenuation and inter-cell interference. User-centric MEC (UC-MEC) can be seen as a promising solution to address this issue. In UC-MEC, each user is served by a dedicated access point (AP) cluster enabled with MEC capability instead of a single MEC server, however, at the expense of more energy consumption and greater privacy risks. To achieve efficient and reliable resource utilization with user-centric services, we propose an energy efficient blockchain-enabled UC-MEC system where blockchain operations and resource optimization are jointly performed. Firstly, we design a resource-aware, reliable, replicated, redundant, and fault-tolerant (R-RAFT) consensus mechanism to implement secure and reliable resource trading. Then, an optimization framework based on alternating direction method of multipliers (ADMM) is proposed to minimize the total energy consumed by wireless transmission, consensus and task computing, where APs clustering, computing resource allocation and bandwidth allocation are jointly considered. Simulation results show superiority of the proposed UC-MEC system over reference schemes, at most 33.96% reduction in the total delay and 48.77% reduction in the total energy consumption.

eess.SP↗

arXiv2023

Joint Optimization of Base Station Clustering and Service Caching in User-Centric MEC

Edge service caching can effectively reduce the delay or bandwidth overhead for acquiring and initializing applications. To address single-base station (BS) transmission limitation and serious edge effect in traditional cellular-based edge service caching networks, in this paper, we proposed a novel user-centric edge service caching framework where each user is jointly provided with edge caching and wireless transmission services by a specific BS cluster instead of a single BS. To minimize the long-term average delay under the constraint of the caching cost, a mixed integer non-linear programming (MINLP) problem is formulated by jointly optimizing the BS clustering and service caching decisions. To tackle the problem, we propose JO-CDSD, an efficiently joint optimization algorithm based on Lyapunov optimization and generalized benders decomposition (GBD). In particular, the long-term optimization problem can be transformed into a primal problem and a master problem in each time slot that is much simpler to solve. The near-optimal clustering and caching strategy can be obtained through solving the primal and master problem alternately. Extensive simulations show that the proposed joint optimization algorithm outperforms other algorithms and can effectively reduce the long-term delay by at most $93.75% and caching cost by at most $53.12%.

eess.SP↗

arXiv2023

Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution

Generalization in partially observed markov decision processes (POMDPs) is critical for successful applications of visual reinforcement learning (VRL) in real scenarios. A widely used idea is to learn task-relevant representations that encode task-relevant information of common features in POMDPs, i.e., rewards and transition dynamics. As transition dynamics in the latent state space -- which are task-relevant and invariant to visual distractions -- are unknown to the agents, existing methods alternatively use transition dynamics in the observation space to extract task-relevant information in transition dynamics. However, such transition dynamics in the observation space involve task-irrelevant visual distractions, degrading the generalization performance of VRL methods. To tackle this problem, we propose the reward sequence distribution conditioned on the starting observation and the predefined subsequent action sequence (RSD-OA). The appealing features of RSD-OA include that: (1) RSD-OA is invariant to visual distractions, as it is conditioned on the predefined subsequent action sequence without task-irrelevant information from transition dynamics, and (2) the reward sequence captures long-term task-relevant information in both rewards and transition dynamics. Experiments demonstrate that our representation learning approach based on RSD-OA significantly improves the generalization performance on unseen environments, outperforming several state-of-the-arts on DeepMind Control tasks with visual distractions.

cs.LG↗

arXiv2023

Effective Multimodal Reinforcement Learning with Modality Alignment and Importance Enhancement

Many real-world applications require an agent to make robust and deliberate decisions with multimodal information (e.g., robots with multi-sensory inputs). However, it is very challenging to train the agent via reinforcement learning (RL) due to the heterogeneity and dynamic importance of different modalities. Specifically, we observe that these issues make conventional RL methods difficult to learn a useful state representation in the end-to-end training with multimodal information. To address this, we propose a novel multimodal RL approach that can do multimodal alignment and importance enhancement according to their similarity and importance in terms of RL tasks respectively. By doing so, we are able to learn an effective state representation and consequentially improve the RL training process. We test our approach on several multimodal RL domains, showing that it outperforms state-of-the-art methods in terms of learning speed and policy quality.

cs.LG↗

arXiv2023

Characterization of loss mechanisms in a fluxonium qubit

Using a fluxonium qubit with in situ tunability of its Josephson energy, we characterize its energy relaxation at different flux biases as well as different Josephson energy values. The relaxation rate at qubit energy values, ranging more than one order of magnitude around the thermal energy $k_B T$, can be quantitatively explained by a combination of dielectric loss and $1/f$ flux noise with a crossover point. The amplitude of the $1/f$ flux noise is consistent with that extracted from the qubit dephasing measurements at the flux sensitive points. In the dielectric loss dominant regime, the loss is consistent with that arises from the electric dipole interaction with two-level-system (TLS) defects. In particular, as increasing Josephson energy thus decreasing qubit frequency at the flux insensitive spot, we find that the qubit exhibits increasingly weaker coupling to TLS defects thus desirable for high-fidelity quantum operations.

quant-ph↗

arXiv2023

Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model

Cutting planes (cuts) are important for solving mixed-integer linear programs (MILPs), which formulate a wide range of important real-world applications. Cut selection -- which aims to select a proper subset of the candidate cuts to improve the efficiency of solving MILPs -- heavily depends on (P1) which cuts should be preferred, and (P2) how many cuts should be selected. Although many modern MILP solvers tackle (P1)-(P2) by manually designed heuristics, machine learning offers a promising approach to learn more effective heuristics from MILPs collected from specific applications. However, many existing learning-based methods focus on learning which cuts should be preferred, neglecting the importance of learning the number of cuts that should be selected. Moreover, we observe from extensive empirical results that (P3) what order of selected cuts should be preferred has a significant impact on the efficiency of solving MILPs as well. To address this challenge, we propose a novel hierarchical sequence model (HEM) to learn cut selection policies via reinforcement learning. Specifically, HEM consists of a two-level model: (1) a higher-level model to learn the number of cuts that should be selected, (2) and a lower-level model -- that formulates the cut selection task as a sequence to sequence learning problem -- to learn policies selecting an ordered subset with the size determined by the higher-level model. To the best of our knowledge, HEM is the first method that can tackle (P1)-(P3) in cut selection simultaneously from a data-driven perspective. Experiments show that HEM significantly improves the efficiency of solving MILPs compared to human-designed and learning-based baselines on both synthetic and large-scale real-world MILPs, including MIPLIB 2017. Moreover, experiments demonstrate that HEM well generalizes to MILPs that are significantly larger than those seen during training.

cs.LG↗

arXiv2022

Wavy optical grating: wideband reflector and Fabry-Perot BICs

In this study, we theoretically and numerically investigate the resonant modes and reflectance of an optical grating consisting of a wavy dielectric slab by applying the spectral element method. The presence of the wavy shape transforms the waveguide modes into leaky resonant modes. A few resonant modes with specific longitudinal wave number have infinitely large Q factor, while the other resonant modes have finite Q factor. For the leaky resonant mode with zero longitudinal wave number, the Q factor is inversely proportional to the amplitude of the wavy shape. An array of multiple low-Q wavy gratings has a high reflectance in a large bandwidth. A double-layer wavy grating forms a Fabry-Perot cavity, which hosts Fabry-Perot bound states in the continuum (BICs) at the resonant frequency. The Q-factor of the Fabry-Perot cavity can be tuned by adjusting the distance between the two wavy slabs. The wavy shape could be generated by a vibrational wave in a flat dielectric slab so that the BICs mode and wideband reflectance could be controlled on-demand.

physics.optics↗

arXiv2022

Possible Lorentz symmetry violation from broken Weyl invariance

In this work, we investigate a theory of linear Weyl gravity coupled to a scalar field and study the scenario in which Lorentz symmetry is broken by a non-vanishing vacuum expectation value of the Weyl field in the flat space limit after Weyl symmetry breaking. We show that a $CPT$-odd Lorentz-violating interaction is generated after symmetry breaking. Features of different symmetry-broken phases and their dependence on the spacetime character of the generated Lorentz-violating background are discussed. Also, we analyze the naturalness of the theory by showing that the light mass scale is protected from large radiative corrections due to an enhanced spacetime symmetry.

hep-th↗

arXiv2022

Two Iterative algorithms for the matrix sign function based on the adaptive filtering technology

In this paper, two new efficient algorithms for calculating the sign function of the large-scale sparse matrix are proposed by combining filtering algorithm with Newton method and Newton Schultz method respectively. Through the theoretical analysis of the error diffusion in the iterative process, we designed an adaptive filtering threshold, which can ensure that the filtering has little impact on the iterative process and the calculation result. Numerical experiments are consistent with our theoretical analysis, which shows that the computational efficiency of our method is much better than that of Newton method and Newton Schultz method, and the computational error is of the same order of magnitude as that of the two methods.

math.NA↗

arXiv2022

Research on Self-adaptive Online Vehicle Velocity Prediction Strategy Considering Traffic Information Fusion

In order to increase the prediction accuracy of the online vehicle velocity prediction (VVP) strategy, a self-adaptive velocity prediction algorithm fused with traffic information was presented for the multiple scenarios. Initially, traffic scenarios were established inside the co-simulation environment. In addition, the algorithm of a general regressive neural network (GRNN) paired with datasets of the ego-vehicle, the front vehicle, and traffic lights was used in traffic scenarios, which increasingly improved the prediction accuracy. To ameliorate the robustness of the algorithm, then the strategy was optimized by particle swarm optimization (PSO) and k-fold cross-validation to find the optimal parameters of the neural network in real-time, which constructed a self-adaptive online PSO-GRNN VVP strategy with multi-information fusion to adapt with different operating situations. The self-adaptive online PSO-GRNN VVP strategy was then deployed to a variety of simulated scenarios to test its efficacy under various operating situations. Finally, the simulation results reveal that in urban and highway scenarios, the prediction accuracy is separately increased by 27.8% and 54.5% when compared to the traditional GRNN VVP strategy with fixed parameters utilizing only the historical ego-vehicle velocity dataset.

eess.SY↗

arXiv2022

Updating velocities in heterogeneous comprehensive learning particle swarm optimization with low-discrepancy sequences

Heterogeneous comprehensive learning particle swarm optimization (HCLPSO) is a type of evolutionary algorithm with enhanced exploration and exploitation capabilities. The low-discrepancy sequence (LDS) is more uniform in covering the search space than random sequences. In this paper, making use of the good uniformity of LDS to improve HCLPSO is researched. Numerical experiments are performed to show that it is impossible to effectively improve the search ability of HCLPSO by only using LDS to generate the initial population. However, if we properly choose some random sequences from the HCLPSO velocities updating formula and replace them with the deterministic LDS, we can obtain a more efficient algorithm. Compared with the original HCLPSO under the same accuracy requirement, the HCLPSO updating the velocities with the deterministic LDS can significantly reduce the iterations required for finding the optimal solution, without decreasing the success rate.

cs.NE↗

arXiv2022

Model-Guided Multi-Contrast Deep Unfolding Network for MRI Super-resolution Reconstruction

Magnetic resonance imaging (MRI) with high resolution (HR) provides more detailed information for accurate diagnosis and quantitative image analysis. Despite the significant advances, most existing super-resolution (SR) reconstruction network for medical images has two flaws: 1) All of them are designed in a black-box principle, thus lacking sufficient interpretability and further limiting their practical applications. Interpretable neural network models are of significant interest since they enhance the trustworthiness required in clinical practice when dealing with medical images. 2) most existing SR reconstruction approaches only use a single contrast or use a simple multi-contrast fusion mechanism, neglecting the complex relationships between different contrasts that are critical for SR improvement. To deal with these issues, in this paper, a novel Model-Guided interpretable Deep Unfolding Network (MGDUN) for medical image SR reconstruction is proposed. The Model-Guided image SR reconstruction approach solves manually designed objective functions to reconstruct HR MRI. We show how to unfold an iterative MGDUN algorithm into a novel model-guided deep unfolding network by taking the MRI observation matrix and explicit multi-contrast relationship matrix into account during the end-to-end optimization. Extensive experiments on the multi-contrast IXI dataset and BraTs 2019 dataset demonstrate the superiority of our proposed model.

eess.IV↗

arXiv2022

A filtering technique for the matrix power series being near-sparse

This work presents a new algorithm for matrix power series which is near-sparse, that is, there are a large number of near-zero elements in it. The proposed algorithm uses a filtering technique to improve the sparsity of the matrices involved in the calculation process of the Paterson-Stockmeyer (PS) scheme. Based on the error analysis considering the transaction error and the error introduced by filtering, the proposed algorithm can obtain similar accuracy as the original PS scheme but is more efficient than it. For the near-sparse matrix power series, the proposed method is also more efficient than the MATLAB built-in codes.

math.NA↗

arXiv2022

Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent Variables

Single-step retrosynthesis is the cornerstone of retrosynthesis planning, which is a crucial task for computer-aided drug discovery. The goal of single-step retrosynthesis is to identify the possible reactants that lead to the synthesis of the target product in one reaction. By representing organic molecules as canonical strings, existing sequence-based retrosynthetic methods treat the product-to-reactant retrosynthesis as a sequence-to-sequence translation problem. However, most of them struggle to identify diverse chemical reactions for a desired product due to the deterministic inference, which contradicts the fact that many compounds can be synthesized through various reaction types with different sets of reactants. In this work, we aim to increase reaction diversity and generate various reactants using discrete latent variables. We propose a novel sequence-based approach, namely RetroDVCAE, which incorporates conditional variational autoencoders into single-step retrosynthesis and associates discrete latent variables with the generation process. Specifically, RetroDVCAE uses the Gumbel-Softmax distribution to approximate the categorical distribution over potential reactions and generates multiple sets of reactants with the variational decoder. Experiments demonstrate that RetroDVCAE outperforms state-of-the-art baselines on both benchmark dataset and homemade dataset. Both quantitative and qualitative results show that RetroDVCAE can model the multi-modal distribution over reaction types and produce diverse reactant candidates.

q-bio.QM↗

arXiv2022

Multi-Agent Path Finding Based on Subdimensional Expansion with Bypass

Multi-agent path finding (MAPF) is an active area in artificial intelligence, which has many real-world applications such as warehouse management, traffic control, robotics, etc. Recently, M* and its variants have greatly improved the ability to solve the MAPF problem. Although subdimensional expansion used in those approaches significantly decreases the dimensionality of the joint search space and reduces the branching factor, they do not make full use of the possible non-uniqueness of the optimal path of each agent. As a result, the updating of the collision sets may bring a large number of redundant computation. In this paper, the idea of bypass is introduced into subdimensional expansion to reduce the redundant computation. Specifically, we propose the BPM* algorithm, which is an implementation of subdimensional expansion with bypass in M*. In the experiments, we show that BPM* outperforms the state-of-the-art in solving several MAPF benchmark problems.

cs.RO↗