Machine learning (ML) has been actively adopted in Linear Programming (LP) and Mixed-Integer Linear Programming (MILP), whose potential is hindered by instance scarcity. Current synthetic instance generation methods often fall short in closely mirroring the distribution of original datasets or ensuring the feasibility and boundedness of the generated data — a critical requirement for obtaining reliable supervised labels in model training. In this paper, we present a diffusion-based LP/MILP instance generative framework called MILP-FBGen. It strikes a balance between structural similarity and novelty while maintaining feasibility/boundedness via a meticulously designed structure-preserving generation module and a feasibility/boundedness-constrained sampling module. Our method shows superiority on two fronts: 1) preservation of key properties (hardness, feasibility, and boundedness) of LP/MILP instances, and 2) enhanced performance on downstream tasks. Extensive studies show two-fold superiority that our method ensures higher distributional similarity and 100% feasibility in both easy and hard datasets, surpassing current state-of-the-art techniques.

We propose a novel multi-scale neural network for Granger causality discovery (MSNGC) in multivariate time series. Compared with existing counterparts, our model avoids the explicit data segmentation between series and between time lags for the first time. By extracting diverse causal information from the data with different delay ranges and then integrating them effectively via the learned attention weights, it can capture the complete causal relationships between all the series and provide accurate weighted adjacency matrix estimation. Thus, further interpretable inference can be better supported. Specifically, we propose a consistency-based thresholding algorithm for binary causal structure inference, an effect sign detection method to distinguish the positive causal effects from the negative ones, and a self-adaptive lag discovery algorithm to identify the lagged time points. Experiments on multiple benchmarks demonstrate that our model significantly outperforms the state-of-the-art methods.

Standard classification models rely on the assumption that all the classes of interest are equally represented in training datasets. However, visual phenomena exhibit a long-tailed distribution, such that many standard approaches fail to properly model and result in a considerable degeneration on accuracy. The recent methods have produced encouraging results, but their efforts only seek to simulate the statistical relationship between data and labels and compensate for imbalanced data-related issues, without addressing the underlying causal mechanisms. In this paper, a comprehensive structural causal model is developed to excavate the intrinsic causal mechanism between data and labels. Specifically, we assume that each input is constructed from a mix of causal factors and non-causal factors, and only the causal factors cause the classification judgments. In order to extract such causal factors from inputs and then reconstruct the invariant causal mechanisms, we propose a Causal Invariant Transformation algorithm for Long-tailed recognition (CITL), which generates diverse data to avoid the over-fitting on the tail classes and enforces the learnt representations to maintain the causal factors and eliminate the non-causal factors. Our extensive experimental results on several widely used datasets have demonstrated the effectiveness of our proposed CITL approach.

The estimation of Individual Treatment Effect (ITE) is a challenging problem in causal inference, due to the missing counterfactual data and the selection bias. In this paper, we propose a novel representation learning framework via the Learnable Query based transformer for Treatment Effect Estimation (LQTEE). A certain number of queries are learned in a sample-agnostic way and extract global critical features from covariate and treatment data separately. We also propose the hierarchical propensity score regularized adversarial loss to obtain balanced covariate representations, and the mutual orthogonal constraint to force queries to focus on diverse parts of covariates, thus the impact of instrumental variables can be adaptively reduced. Treatment representation learning enables our estimator to support general-purpose treatments, and more importantly, it can reveal the underlying patterns of data-generation process efficiently. Extensive experiments show that our ITE estimator significantly outperforms the state-of-the-art methods.

The up-to-date and accurate building database serves as an important prerequisite to many applications. However, caused by the issues of shape and size variations, texture and distribution diversities, and occlusion and shadow covers of buildings in remote sensing images, it is still challenging to well guarantee the integrity and accuracy of the extracted building instances. This letter proposes a high-resolution capsule network (HR-CapsNet) to conduct building extraction. First, designed with an HR-CapsNet architecture assisted by multiresolution feature propagation and fusion, the HR-CapsNet can provide semantically strong and spatially accurate feature representations to promote the pixel-wise building extraction accuracy. In addition, integrated with an efficient capsule feature attention module, the HR-CapsNet can attend to channel-wise informative and class-specific spatial features to boost the feature encoding quality. Quantitative evaluations, visual inspections, and comparative experiments on two large remote sensing image datasets demonstrate that the HR-CapsNet provides a feasible and competitive solution to building extraction tasks.

Periodically conducting land cover mapping plays a vital role in monitoring the status and changes of the land use. The up-to-date and accurate land use database serves importantly for a wide range of applications. This letter constructs an efficient self-attention capsule network (ESA-CapsNet) for land cover classification of multispectral light detection and ranging (LiDAR) data. First, formulated with a novel capsule encoder–decoder architecture, the ESA-CapsNet performs promisingly in extracting high-level, informative, and strong feature semantics for pixel-wise land cover classification by using the five types of rasterized feature images. Furthermore, designed with a novel capsule-based attention module, the channel and spatial feature encodings are comprehensively exploited to boost the feature saliency and robustness. The ESA-CapsNet is evaluated on two multispectral LiDAR data sets and achieves an advantageous performance with the overall accuracy, average accuracy, and kappa coefficient of over 98.42%, 95.15%, and 0.9776, respectively. Comparative experiments with the existing methods also demonstrate the effectiveness and applicability of the ESA-CapsNet in land cover classification tasks.

The unmanned aerial vehicle (UAV) channel measurements have shown that the propagation environment of UAV channel is non‐stationary. In this study, a three‐dimensional (3D) non‐stationary UAV multiple‐input multiple‐output (MIMO) channel model is proposed. In order to sufficiently describe the propagation environment of UAV‐MIMO channel, the stationary scatterers and moving scatterers are investigated in the proposed model, which are mimicked using 3D cylinder and two‐dimensional (2D) disc, respectively. The Doppler shifts associated with moving scatterers are also considered in the proposed model. The movement of UAV, receiver, and moving scatterers results in non‐stationarities, and time‐variant distances, azimuth angles, and elevation angles are investigated in the proposed model. The statistical properties of the moving scatterers are also investigated in the proposed channel model. In order to validate the proposed model, the spatial correlation is compared with the measurement results, and the numerical results show that the proposed channel model is applicable to describe the UAV‐MIMO communication systems.

In this study, we tested the performance of averaged Stokes parameters in rape biomass inversion over Radarsat-2 data. Five time series Radarsat-2 data were acquired and they covered the whole rape growth season. At each growth stage, 16 Stokes and its child parameters were extracted to analyze their sensitivity to rape biomass. When it comes to biomass inversion, random forest (RF) algorithm were chosen for the rape biomass inversion. The results showed that the total scattered intensity g0 has highest coherence with rape biomass during the whole growth cycle. R2 between them was 0.704. Other parameters including degree of polarization m, the degree of depolarization (1- m), the degree of linear polarization (Pl) and the linear polarization ratio (Uc) showed secondary higher coherence with R2 between 0.3 to 0.4. These parameters also showed higher importance for the parameter importance analysis with RF method. RF method showed potential performance for rape biomass inversion with R2 of 0.585 and RMSE of 71.86 g/m2.

Discovering dependences between variables has a significant impact on the performance of exploration on large datasets. Many useful measures have been presented to identify interesting dependences for pairs of variables, but few for triplets. Here, we proposed a novel measure of dependence for thre e-variable relationships: the maximal total correlation coefficient (MTCC). With a score roughly equaling the determination coefficient R2, MTCC captures a wide range of trivariate one-dimensional manifold dependences, including many common space curves. Applying MTCC to datasets in global health and major-league baseball, we identify a number of almost unknown manifold dependences, especially an impressive superposition of three trivariate relationships.

Feature clustering is a powerful technique for dimensionality reduction. However, existing approaches require the number of clusters to be given in advance or controlled by parameters. In this paper, by combining with affinity propagation (AP), we propose a new feature clustering (FC) algorithm, ca lled APFC, for dimensionality reduction. For a given training dataset, the original features automatically form a bunch of clusters by AP. A new feature can then be extracted from each cluster in three different ways for reducing the dimensionality of the original data. APFC requires no provision of the number of clusters (or extracted features) beforehand. Moreover, it avoids computing the eigenvalues and eigenvectors of covariance matrix which is often necessary in many feature extraction methods. In order to demonstrate the effectiveness and efficiency of APFC, extensive experiments are conducted to compare it with three well-established dimensionality reduction methods on 14 UCI datasets in terms of classification accuracy and computational time.

In this study, 5 compact polarimetric (CP) data were simulated from 5 consecutive fully polarimetric images, which covered the whole rape growth period. Four groups including 25 CP parameters were extracted from each CP image at different rape growth stages, respectively. With the analysis of the relationships between CP parameters and LAI, g3in stokes parameter group, Ucin stokes child parameters group, σRRin backscattering parameters group and PVαin decomposition parameters group were chose to inverse rape LAI. The results showed that, among these four CP parameters, PVαperformed best for rape LAI inversion, the determination coefficient R2 between inversion results and the ground truth data is 0.917, root mean square error (RMSE) is 0.36.

Airport runway recognition technology would play an important role in developing intelligent weapon systems in the future. In this letter, a method of automatically finding runways in forward looking infrared (FLIR) images is proposed based on the knowledge of vision. First, the line segments in the images are extracted by a fast line segment detector (LSD) and an improved line segment linking method. Then, the regions of interest (ROI) of runways are detected using some constraint rules based on the direction, gradient, and width of line segment pairs. Afterward, an ROI length backtracking technique based on texture distribution is presented to retrieve the complete ROI. Finally, using runway regional self-similarity and contextual information, several decision criteria are formulated to accurately recognize the runway. Experimental results on the FLIR images with different imaging ranges show that the proposed algorithm is robust and has a good real-time performance.