arXiv subjects

Wenbin Li

Publications and source records attributed to Wenbin Li.

At least 91 records · Page 5Linked to original sources

arXiv2024

STBench: Assessing the Ability of Large Language Models in Spatio-Temporal Analysis

The rapid evolution of large language models (LLMs) holds promise for reforming the methodology of spatio-temporal data mining. However, current works for evaluating the spatio-temporal understanding capability of LLMs are somewhat limited and biased. These works either fail to incorporate the latest language models or only focus on assessing the memorized spatio-temporal knowledge. To address this gap, this paper dissects LLMs' capability of spatio-temporal data into four distinct dimensions: knowledge comprehension, spatio-temporal reasoning, accurate computation, and downstream applications. We curate several natural language question-answer tasks for each category and build the benchmark dataset, namely STBench, containing 13 distinct tasks and over 60,000 QA pairs. Moreover, we have assessed the capabilities of 13 LLMs, such as GPT-4o, Gemma and Mistral. Experimental results reveal that existing LLMs show remarkable performance on knowledge comprehension and spatio-temporal reasoning tasks, with potential for further enhancement on other tasks through in-context learning, chain-of-though prompting, and fine-tuning. The code and datasets of STBench are released on https://github.com/LwbXc/STBench.

cs.CL↗

arXiv2024

CausalMMM: Learning Causal Structure for Marketing Mix Modeling

In online advertising, marketing mix modeling (MMM) is employed to predict the gross merchandise volume (GMV) of brand shops and help decision-makers to adjust the budget allocation of various advertising channels. Traditional MMM methods leveraging regression techniques can fail in handling the complexity of marketing. Although some efforts try to encode the causal structures for better prediction, they have the strict restriction that causal structures are prior-known and unchangeable. In this paper, we define a new causal MMM problem that automatically discovers the interpretable causal structures from data and yields better GMV predictions. To achieve causal MMM, two essential challenges should be addressed: (1) Causal Heterogeneity. The causal structures of different kinds of shops vary a lot. (2) Marketing Response Patterns. Various marketing response patterns i.e., carryover effect and shape effect, have been validated in practice. We argue that causal MMM needs dynamically discover specific causal structures for different shops and the predictions should comply with the prior known marketing response patterns. Thus, we propose CausalMMM that integrates Granger causality in a variational inference framework to measure the causal relationships between different channels and predict the GMV with the regularization of both temporal and saturation marketing response patterns. Extensive experiments show that CausalMMM can not only achieve superior performance of causal structure learning on synthetic datasets with improvements of 5.7%\sim 7.1%, but also enhance the GMV prediction results on a representative E-commerce platform.

cs.AI↗

arXiv2024

Zero Viscosity Limit of Steady Compressible Shear Flow with Navier-Slip Boundary

We investigate the existence and the zero viscosity limit of steady compressible shear flow with Navier-slip boundary condition in the absence of any external force in a two-dimension domain $Ω=(0,L)\times(0,2)$. More precisely, under the assumption that the Mach number $η<\va^{\f12+}$ and $L\ll1$, we prove the existence of smooth solutions to steady compressible Naiver-Stokes equations near plane Poiseuille-Couette flow as well as the convergence of the solutions obtained above to the solutions of steady incompressible Euler equations when the viscous $\va$ tends to zero.

math.AP↗

arXiv2024

IPixMatch: Boost Semi-supervised Semantic Segmentation with Inter-Pixel Relation

The scarcity of labeled data in real-world scenarios is a critical bottleneck of deep learning's effectiveness. Semi-supervised semantic segmentation has been a typical solution to achieve a desirable tradeoff between annotation cost and segmentation performance. However, previous approaches, whether based on consistency regularization or self-training, tend to neglect the contextual knowledge embedded within inter-pixel relations. This negligence leads to suboptimal performance and limited generalization. In this paper, we propose a novel approach IPixMatch designed to mine the neglected but valuable Inter-Pixel information for semi-supervised learning. Specifically, IPixMatch is constructed as an extension of the standard teacher-student network, incorporating additional loss terms to capture inter-pixel relations. It shines in low-data regimes by efficiently leveraging the limited labeled data and extracting maximum utility from the available unlabeled data. Furthermore, IPixMatch can be integrated seamlessly into most teacher-student frameworks without the need of model modification or adding additional components. Our straightforward IPixMatch method demonstrates consistent performance improvements across various benchmark datasets under different partitioning protocols.

cs.CV↗

arXiv2024

Electronic States in One-Dimensional Helical Crystals: General Properties and Application to InSeI

In this article, we systematically explore several key properties of electronic states in helical materials systems, including the inheritance of orbital angular momentum (OAM) from local atomic orbitals to the entire helical structure, the conservation of helical momentum, and the emergence of helical-induced spin-orbit coupling (hSOC). We then apply this comprehensive theoretical framework to elucidate the electronic structure of one-dimensional (1D) helical crystal InSeI. Our analysis reveals the influence of hSOC, evident in spin-mixing energy gaps within the electronic band structure, as calculated through density functional theory. Utilizing a combination of tight-binding modeling and first-principles calculations, we ascertain the spin-polarized electric response and the chiral-switchable second-order photocurrent response of InSeI, characterized as the Landauer-Buttiker ballistic transport and shift current response. The results highlight the potential of 1D InSeI for applications in spintronics and optoelectronics. The overarching theoretical framework established in this work will prove invaluable for the investigation of other helical electronic systems.

cond-mat.mtrl-sci↗

arXiv2024

Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay

We study continual offline reinforcement learning, a practical paradigm that facilitates forward transfer and mitigates catastrophic forgetting to tackle sequential offline tasks. We propose a dual generative replay framework that retains previous knowledge by concurrent replay of generated pseudo-data. First, we decouple the continual learning policy into a diffusion-based generative behavior model and a multi-head action evaluation model, allowing the policy to inherit distributional expressivity for encompassing a progressive range of diverse behaviors. Second, we train a task-conditioned diffusion model to mimic state distributions of past tasks. Generated states are paired with corresponding responses from the behavior generator to represent old tasks with high-fidelity replayed samples. Finally, by interleaving pseudo samples with real ones of the new task, we continually update the state and behavior generators to model progressively diverse behaviors, and regularize the multi-head critic via behavior cloning to mitigate forgetting. Experiments demonstrate that our method achieves better forward transfer with less forgetting, and closely approximates the results of using previous ground-truth data due to its high-fidelity replay of the sample space. Our code is available at \href{https://github.com/NJU-RL/CuGRO}{https://github.com/NJU-RL/CuGRO}.

cs.LG↗

arXiv2024

ONNXPruner: ONNX-Based General Model Pruning Adapter

Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various models and platforms remains a significant challenge. To address this challenge, we propose ONNXPruner, a versatile pruning adapter designed for the ONNX format models. ONNXPruner streamlines the adaptation process across diverse deep learning frameworks and hardware platforms. A novel aspect of ONNXPruner is its use of node association trees, which automatically adapt to various model architectures. These trees clarify the structural relationships between nodes, guiding the pruning process, particularly highlighting the impact on interconnected nodes. Furthermore, we introduce a tree-level evaluation method. By leveraging node association trees, this method allows for a comprehensive analysis beyond traditional single-node evaluations, enhancing pruning performance without the need for extra operations. Experiments across multiple models and datasets confirm ONNXPruner's strong adaptability and increased efficacy. Our work aims to advance the practical application of model pruning.

cs.LG↗

arXiv2024

Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation

Dataset distillation has emerged as a promising approach in deep learning, enabling efficient training with small synthetic datasets derived from larger real ones. Particularly, distribution matching-based distillation methods attract attention thanks to its effectiveness and low computational cost. However, these methods face two primary limitations: the dispersed feature distribution within the same class in synthetic datasets, reducing class discrimination, and an exclusive focus on mean feature consistency, lacking precision and comprehensiveness. To address these challenges, we introduce two novel constraints: a class centralization constraint and a covariance matching constraint. The class centralization constraint aims to enhance class discrimination by more closely clustering samples within classes. The covariance matching constraint seeks to achieve more accurate feature distribution matching between real and synthetic datasets through local feature covariance matrices, particularly beneficial when sample sizes are much smaller than the number of features. Experiments demonstrate notable improvements with these constraints, yielding performance boosts of up to 6.6% on CIFAR10, 2.9% on SVHN, 2.5% on CIFAR100, and 2.5% on TinyImageNet, compared to the state-of-the-art relevant methods. In addition, our method maintains robust performance in cross-architecture settings, with a maximum performance drop of 1.7% on four architectures. Code is available at https://github.com/VincenDen/IID.

cs.CV↗

arXiv2024

InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules

Generalizing Neural Radiance Fields (NeRF) to new scenes is a significant challenge that existing approaches struggle to address without extensive modifications to vanilla NeRF framework. We introduce InsertNeRF, a method for INStilling gEneRalizabiliTy into NeRF. By utilizing multiple plug-and-play HyperNet modules, InsertNeRF dynamically tailors NeRF's weights to specific reference scenes, transforming multi-scale sampling-aware features into scene-specific representations. This novel design allows for more accurate and efficient representations of complex appearances and geometries. Experiments show that this method not only achieves superior generalization performance but also provides a flexible pathway for integration with other NeRF-like systems, even in sparse input settings. Code will be available https://github.com/bbbbby-99/InsertNeRF.

cs.CV↗

arXiv2024

Identifying Optimal Launch Sites of High-Altitude Latex-Balloons using Bayesian Optimisation for the Task of Station-Keeping

Station-keeping tasks for high-altitude balloons show promise in areas such as ecological surveys, atmospheric analysis, and communication relays. However, identifying the optimal time and position to launch a latex high-altitude balloon is still a challenging and multifaceted problem. For example, tasks such as forest fire tracking place geometric constraints on the launch location of the balloon. Furthermore, identifying the most optimal location also heavily depends on atmospheric conditions. We first illustrate how reinforcement learning-based controllers, frequently used for station-keeping tasks, can exploit the environment. This exploitation can degrade performance on unseen weather patterns and affect station-keeping performance when identifying an optimal launch configuration. Valuing all states equally in the region, the agent exploits the region's geometry by flying near the edge, leading to risky behaviours. We propose a modification which compensates for this exploitation and finds this leads to, on average, higher steps within the target region on unseen data. Then, we illustrate how Bayesian Optimisation (BO) can identify the optimal launch location to perform station-keeping tasks, maximising the expected undiscounted return from a given rollout. We show BO can find this launch location in fewer steps compared to other optimisation methods. Results indicate that, surprisingly, the most optimal location to launch from is not commonly within the target region. Please find further information about our project at https://sites.google.com/view/bo-lauch-balloon/.

cs.RO↗

arXiv2024

Learning on the correct class for domain inverse problems of gravimetry

We consider end-to-end learning approaches for inverse problems of gravimetry. Due to ill-posedness of the inverse gravimetry, the reliability of learning approaches is questionable. To deal with this problem, we propose the strategy of learning on the correct class. The well-posedness theorems are employed when designing the neural-network architecture and constructing the training set. Given the density-contrast function as a priori information, the domain of mass can be uniquely determined under certain constrains, and the domain inverse problem is a correct class of the inverse gravimetry. Under this correct class, we design the neural network for learning by mimicking the level-set formulation for the inverse gravimetry. Numerical examples illustrate that the method is able to recover mass models with non-constant density contrast.

physics.geo-ph↗

arXiv2024

DIO: Dataset of 3D Mesh Models of Indoor Objects for Robotics and Computer Vision Applications

The creation of accurate virtual models of real-world objects is imperative to robotic simulations and applications such as computer vision, artificial intelligence, and machine learning. This paper documents the different methods employed for generating a database of mesh models of real-world objects. These methods address the tedious and time-intensive process of manually generating the models using CAD software. Essentially, DSLR/phone cameras were employed to acquire images of target objects. These images were processed using a photogrammetry software known as Meshroom to generate a dense surface reconstruction of the scene. The result produced by Meshroom was edited and simplified using MeshLab, a mesh-editing software to produce the final model. Based on the obtained models, this process was effective in modelling the geometry and texture of real-world objects with high fidelity. An active 3D scanner was also utilized to accelerate the process for large objects. All generated models and captured images are made available on the website of the project.

cs.RO↗

arXiv2024

AccidentGPT: Large Multi-Modal Foundation Model for Traffic Accident Analysis

Traffic accident analysis is pivotal for enhancing public safety and developing road regulations. Traditional approaches, although widely used, are often constrained by manual analysis processes, subjective decisions, uni-modal outputs, as well as privacy issues related to sensitive data. This paper introduces the idea of AccidentGPT, a foundation model of traffic accident analysis, which incorporates multi-modal input data to automatically reconstruct the accident process video with dynamics details, and furthermore provide multi-task analysis with multi-modal outputs. The design of the AccidentGPT is empowered with a multi-modality prompt with feedback for task-oriented adaptability, a hybrid training schema to leverage labelled and unlabelled data, and a edge-cloud split configuration for data privacy. To fully realize the functionalities of this model, we proposes several research opportunities. This paper serves as the stepping stone to fill the gaps in traditional approaches of traffic accident analysis and attract the research community attention for automatic, objective, and privacy-preserving traffic accident analysis.

cs.LG↗

arXiv2023

A multi-layer refined network model for the identification of essential proteins

The identification of essential proteins in protein-protein interaction networks (PINs) can help to discover drug targets and prevent disease. In order to improve the accuracy of the identification of essential proteins, researchers attempted to obtain a refined PIN by combining multiple biological information to filter out some unreliable interactions in the PIN. Unfortunately, such approaches drastically reduce the number of nodes in the PIN after multiple refinements and result in a sparser PIN. It makes a considerable portion of essential proteins unidentifiable. In this paper, we propose a multi-layer refined network (MR-PIN) that addresses this problem. Firstly, four refined networks are constructed by respectively integrating different biological information into the static PIN to form a multi-layer heterogeneous network. Then scores of proteins in each network layer are calculated by the existing node ranking method, and the importance score of a protein in the MR-PIN is evaluated in terms of the geometric mean of its scores in all layers. Finally, all nodes are sorted by their importance scores to determine their essentiality. To evaluate the effectiveness of the multi-layer refined network model, we apply 16 node ranking methods on the MR-PIN, and compare the results with those on the SPIN, DPIN and RDPIN. Then the predictive performances of these ranking methods are validated in terms of the identification number of essential protein at top100 - top600, sensitivity, specificity, positive predictive value, negative predictive value, F-measure, accuracy, Jackknife, ROCAUC and PRAUC. The experimental results show that the MR-PIN is superior to the existing refined PINs in the identification accuracy of essential proteins.

q-bio.MN↗

arXiv2023

Unleashing Realistic Air Quality Forecasting: Introducing the Ready-to-Use PurpleAirSF Dataset

Air quality forecasting has garnered significant attention recently, with data-driven models taking center stage due to advancements in machine learning and deep learning models. However, researchers face challenges with complex data acquisition and the lack of open-sourced datasets, hindering efficient model validation. This paper introduces PurpleAirSF, a comprehensive and easily accessible dataset collected from the PurpleAir network. With its high temporal resolution, various air quality measures, and diverse geographical coverage, this dataset serves as a useful tool for researchers aiming to develop novel forecasting models, study air pollution patterns, and investigate their impacts on health and the environment. We present a detailed account of the data collection and processing methods employed to build PurpleAirSF. Furthermore, we conduct preliminary experiments using both classic and modern spatio-temporal forecasting models, thereby establishing a benchmark for future air quality forecasting tasks.

cs.LG↗

arXiv2023

A protein network refinement method based on module discovery and biological information

The identification of essential proteins can help in understanding the minimum requirements for cell survival and development. Network-based centrality approaches are commonly used to identify essential proteins from protein-protein interaction networks (PINs). Unfortunately, these approaches are limited by the poor quality of the underlying PIN data. To overcome this problem, researchers have focused on the prediction of essential proteins by combining PINs with other biological data. In this paper, we proposed a network refinement method based on module discovery and biological information to obtain a higher quality PIN. First, to extract the maximal connected subgraph in the PIN and to divide it into different modules by using Fast-unfolding algorithm; then, to detect critical modules based on the homology information, subcellular localization information and topology information within each module, and to construct a more refined network (CM-PIN). To evaluate the effectiveness of the proposed method, we used 10 typical network-based centrality methods (LAC, DC, DMNC, NC, TP, LID, CC, BC, PR, LR) to compare the overall performance of the CM-PIN with those the refined dynamic protein network (RD-PIN). The experimental results showed that the CM-PIN was optimal in terms of precision-recall curve, jackknife curve and other criteria, and can help to identify essential proteins more accurately.

cs.CE↗

arXiv2023

Visual Perception System for Autonomous Driving

The recent surge in interest in autonomous driving stems from its rapidly developing capacity to enhance safety, efficiency, and convenience. A pivotal aspect of autonomous driving technology is its perceptual systems, where core algorithms have yielded more precise algorithms applicable to autonomous driving, including vision-based Simultaneous Localization and Mapping (SLAMs), object detection, and tracking algorithms. This work introduces a visual-based perception system for autonomous driving that integrates trajectory tracking and prediction of moving objects to prevent collisions, while addressing autonomous driving's localization and mapping requirements. The system leverages motion cues from pedestrians to monitor and forecast their movements and simultaneously maps the environment. This integrated approach resolves camera localization and the tracking of other moving objects in the scene, subsequently generating a sparse map to facilitate vehicle navigation. The performance, efficiency, and resilience of this approach are substantiated through comprehensive evaluations of both simulated and real-world datasets.

cs.CV↗

arXiv2023

Chirality-induced spin splitting in 1D InSeI

Spin-orbit coupling in chiral materials can induce chirality-dependent spin splitting, enabling electrical manipulation of spin polarization. Here, we use first-principles calculations to investigate the electronic states of chiral one-dimensional (1D) semiconductor InSeI, which has two enantiomorphic configurations with left- and right-handedness. We find that opposite spin states exist in the left- and right-handed 1D InSeI with significant spin splitting and spin-momentum collinear locking. Although the spin states at the conduction band minimum (CBM) and valence band maximum (VBM) of 1D InSeI are both nearly degenerate, a direct-to-indirect bandgap transition occurs when a moderate tensile strain ($\sim$4%) is applied along the 1D chain direction, leading to a sizable spin splitting ($\sim$0.11 eV) at the CBM. These findings indicate that 1D InSeI is a promising material for chiral spintronics.

cond-mat.mtrl-sci↗