arXiv subjects

Muhammad Shahzad

Publications and source records attributed to Muhammad Shahzad.

At least 19 recordsLinked to original sources

arXiv2026

CO-EVOLVE: Bidirectional Co-Evolution of Graph Structure and Semantics for Heterophilous Learning

The integration of Large Language Models (LLMs) and Graph Neural Networks (GNNs) promises to unify semantic understanding with structural reasoning, yet existing methods typically rely on static, unidirectional pipelines. These approaches suffer from fundamental limitations: (1) Bidirectional Error Propagation, where semantic hallucinations in LLMs or structural noise in GNNs permanently poison the downstream modality without opportunity for recourse; (2) Semantic-Structural Dissonance, particularly in heterophilous settings where textual similarity contradicts topological reality; (3) a Blind Leading the Blind phenomenon, where indiscriminate alignment forces models to mirror each other's mistakes regardless of uncertainty. To address these challenges, we propose CO-EVOLVE, a dual-view co-evolution framework that treats graph topology and semantic embeddings as dynamic, mutually reinforcing latent variables. By employing a Gauss-Seidel alternating optimization strategy, our framework establishes a cyclic feedback loop: the GNN injects structural context as Soft Prompts to guide the LLM, while the LLM constructs favorable Dynamic Semantic Graphs to rewire the GNN. We introduce three key innovations to stabilize this evolution: (1) a Hard-Structure Conflict-Aware Contrastive Loss that warps the semantic manifold to respect high-order topological boundaries; (2) an Adaptive Node Gating Mechanism that dynamically fuses static and learnable structures to recover missing links; (3) an Uncertainty-Gated Consistency strategy that enables meta-cognitive alignment, ensuring models only learn from the confident view. Finally, an Entropy-Aware Adaptive Fusion integrates predictions during inference. Extensive experiments on public benchmarks demonstrate that CO-EVOLVE significantly outperforms state-of-the-art baselines, achieving average improvements of 9.07% in Accuracy and 7.19% in F1-score.

cs.IR↗

arXiv2025

Physical remnant of electroweak theta angles

In addition to the well-known quantum chromodynamical theta angle, we show that the Standard Model has another theta angle which is invariant under arbitrary chiral rotations of quarks and leptons. The new theta angle can be identified with the quantum electrodynamical theta angle, which should be viewed as an independent parameter of the Standard Model, and may be observable in spacetime with non-simply connected features, either beyond the visible universe or in an effective background from a laboratory setup.

hep-ph↗

arXiv2025

High-Pressure DFT Study of BeX (X = S, Se, Te): Phonon Spectra, Optical Properties, and Thermodynamic Stability for Advanced Optoelectronic Applications

We present a comprehensive first-principles investigation of the structural, electronic, optical, and thermodynamic properties of BeX compounds (X = S, Se, Te) under hydrostatic pressures ranging from 0 to 10 GPa. Calculations were performed using density functional theory (DFT) within the Generalized Gradient Approximation (GGA) using the Perdew-Burke-Ernzerhof (PBE) functional, as implemented in the CASTEP code. Phonon dispersion analyses confirm the dynamical stability of all compounds across the studied pressure range, as indicated by the absence of imaginary frequencies throughout the Brillouin zone. The electronic band structure reveals pressure-induced band modifications, with BeS retaining the widest bandgap. Optical properties, including the dielectric function, absorption coefficient, reflectivity, and energy loss spectra, were computed for photon energies up to 30 eV. The materials exhibit strong optical absorption in the ultraviolet region, suggesting potential for UV optoelectronic applications. Thermodynamic parameters such as Debye temperature, heat capacity, and entropy were evaluated, showing pressure-dependent trends. Notably, increasing pressure leads to reduced atomic vibrations and heat capacity, while the Gibbs free energy exhibits a consistent slope with temperature, reflecting entropy variation. These results highlight the suitability of BeX compounds for pressure-sensitive optoelectronic and thermoelectric devices, as well as thermal barrier applications.

cond-mat.mtrl-sci↗

arXiv2025

Structured Basis Function Networks: Loss-Centric Multi-Hypothesis Ensembles with Controllable Diversity

Existing approaches to predictive uncertainty rely either on multi-hypothesis prediction, which promotes diversity but lacks principled aggregation, or on ensemble learning, which improves accuracy but rarely captures the structured ambiguity. This implicitly means that a unified framework consistent with the loss geometry remains absent. The Structured Basis Function Network addresses this gap by linking multi-hypothesis prediction and ensembling through centroidal aggregation induced by Bregman divergences. The formulation applies across regression and classification by aligning predictions with the geometry of the loss, and supports both a closed-form least-squares estimator and a gradient-based procedure for general objectives. A tunable diversity mechanism provides parametric control of the bias-variance-diversity trade-off, connecting multi-hypothesis generalisation with loss-aware ensemble aggregation. Experiments validate this relation and use the mechanism to study the complexity-capacity-diversity trade-off across datasets of increasing difficulty with deep-learning predictors.

cs.LG↗

arXiv2025

GlobalGeoTree: A Multi-Granular Vision-Language Dataset for Global Tree Species Classification

Global tree species mapping using remote sensing data is vital for biodiversity monitoring, forest management, and ecological research. However, progress in this field has been constrained by the scarcity of large-scale, labeled datasets. To address this, we introduce GlobalGeoTree, a comprehensive global dataset for tree species classification. GlobalGeoTree comprises 6.3 million geolocated tree occurrences, spanning 275 families, 2,734 genera, and 21,001 species across the hierarchical taxonomic levels. Each sample is paired with Sentinel-2 image time series and 27 auxiliary environmental variables, encompassing bioclimatic, geographic, and soil data. The dataset is partitioned into GlobalGeoTree-6M for model pretraining and curated evaluation subsets, primarily GlobalGeoTree-10kEval for zero-shot and few-shot benchmarking. To demonstrate the utility of the dataset, we introduce a baseline model, GeoTreeCLIP, which leverages paired remote sensing data and taxonomic text labels within a vision-language framework pretrained on GlobalGeoTree-6M. Experimental results show that GeoTreeCLIP achieves substantial improvements in zero- and few-shot classification on GlobalGeoTree-10kEval over existing advanced models. By making the dataset, models, and code publicly available, we aim to establish a benchmark to advance tree species classification and foster innovation in biodiversity research and ecological applications.

cs.CV↗

arXiv2025

Global-local Spatial-temporal Aware Graph Attention Network for Network Traffic Forecasting

Spatial-temporal network traffic forecasting is a challenging task due to the complex spatial relationships and dynamic temporal patterns present in each node. Traditional regression methods are not directly applicable to such graph data. Recently, Graph Neural Networks (GNNs) have been widely used to model spatial-temporal dependencies. However, existing methods face several limitations: (1) They rely solely on a predefined spatial adjacency matrix, overlooking hidden low-level temporal information. (2) They model spatial and temporal information separately, which inevitably leads to a loss of joint dependencies, or they capture only global or local dependencies. To address these issues, we propose the \textbf{G}lobal-\textbf{L}ocal \textbf{S}patial-\textbf{T}emporal \textbf{a}ware \textbf{G}raph \textbf{AT}tention Network (GLSTaGAT). Specifically, we adopt a data-driven spatial-temporal fusion graph that incorporates low-level spatial and temporal information, serving as the foundation for further graph convolutions. The GLSTaGAT block and its pooling variant are proposed to simultaneously capture local and global spatial-temporal dependencies. Additionally, we introduce node normalization to mitigate covariance shifts, enabling a smoother training process. An encoder-only transformer is utilized to model high-level joint dependencies, and a multi-head attention prediction layer is designed for final information aggregation and prediction. Experimental results on real-world datasets demonstrate that GLSTaGAT outperforms the baselines by 32.14\% (MAE), 28.30\% (RMSE), and 20.47\% (SMAPE) on average.

cs.IR↗

arXiv2025

A Reinforcement Learning Framework for Application-Specific TCP Congestion-Control

The Congestion Control (CC) module plays a critical role in the Transmission Control Protocol (TCP), ensuring the stability and efficiency of network data transmission. The CC approaches that are commonly used these days employ heuristics-based rules to adjust the sending rate. Due to their heuristics-based nature, these approaches are not only unable to adapt to changing network conditions but are also agnostic to the diverse requirements that different applications often have. Recently, several learning-based CC approaches have been proposed to adapt to changing network conditions. Unfortunately, they are not designed to take application requirements into account. Prior heuristics-based as well as learning-based CC approaches focus on achieving a singular objective, which is often to maximize throughput, even though a lot of applications care more about latency, packet losses, jitter, and different combinations of various network metrics. Motivated by this, we propose a Deep Reinforcement Learning (DRL) based CC framework, namely ASC, which allows any application to specify any arbitrary objectives that the network traffic of that application should achieve and is able to swiftly adapt to the changes in the objectives of the applications as well as to the changes in the network conditions. Our ASC framework further employs a client-server architecture that serves two purposes: 1) it makes ASC highly scalable in terms of the arrival and departure of TCP connections, and 2) it makes ASC very lightweight for the nodes maintaining the TCP connections. We implemented and extensively evaluated ASC in a variety of settings. Our results show that it can not only achieve various objectives but also outperforms prior approaches even in the specific objectives that those approaches were designed to achieve.

cs.NI↗

arXiv2025

The Fourth Monocular Depth Estimation Challenge

This paper presents the results of the fourth edition of the Monocular Depth Estimation Challenge (MDEC), which focuses on zero-shot generalization to the SYNS-Patches benchmark, a dataset featuring challenging environments in both natural and indoor settings. In this edition, we revised the evaluation protocol to use least-squares alignment with two degrees of freedom to support disparity and affine-invariant predictions. We also revised the baselines and included popular off-the-shelf methods: Depth Anything v2 and Marigold. The challenge received a total of 24 submissions that outperformed the baselines on the test set; 10 of these included a report describing their approach, with most leading methods relying on affine-invariant predictions. The challenge winners improved the 3D F-Score over the previous edition's best result, raising it from 22.58% to 23.05%.

cs.CV↗

arXiv2025

MPTSNet: Integrating Multiscale Periodic Local Patterns and Global Dependencies for Multivariate Time Series Classification

Multivariate Time Series Classification (MTSC) is crucial in extensive practical applications, such as environmental monitoring, medical EEG analysis, and action recognition. Real-world time series datasets typically exhibit complex dynamics. To capture this complexity, RNN-based, CNN-based, Transformer-based, and hybrid models have been proposed. Unfortunately, current deep learning-based methods often neglect the simultaneous construction of local features and global dependencies at different time scales, lacking sufficient feature extraction capabilities to achieve satisfactory classification accuracy. To address these challenges, we propose a novel Multiscale Periodic Time Series Network (MPTSNet), which integrates multiscale local patterns and global correlations to fully exploit the inherent information in time series. Recognizing the multi-periodicity and complex variable correlations in time series, we use the Fourier transform to extract primary periods, enabling us to decompose data into multiscale periodic segments. Leveraging the inherent strengths of CNN and attention mechanism, we introduce the PeriodicBlock, which adaptively captures local patterns and global dependencies while offering enhanced interpretability through attention integration across different periodic scales. The experiments on UEA benchmark datasets demonstrate that the proposed MPTSNet outperforms 21 existing advanced baselines in the MTSC tasks.

cs.LG↗

arXiv2025

Multi-Hypothesis Prediction for Portfolio Optimization: A Structured Ensemble Learning Approach to Risk Diversification

This work proposes a unified framework for portfolio allocation, covering both asset selection and optimization, based on a multiple-hypothesis predict-then-optimize approach. The portfolio is modeled as a structured ensemble, where each predictor corresponds to a specific asset or hypothesis. Structured ensembles formally link predictors' diversity, captured via ensemble loss decomposition, to out-of-sample risk diversification. A structured data set of predictor output is constructed with a parametric diversity control, which influences both the training process and the diversification outcomes. This data set is used as input for a supervised ensemble model, the target portfolio of which must align with the ensemble combiner rule implied by the loss. For squared loss, the arithmetic mean applies, yielding the equal-weighted portfolio as the optimal target. For asset selection, a novel method is introduced which prioritizes assets from more diverse predictor sets, even at the expense of lower average predicted returns, through a diversity-quality trade-off. This form of diversity is applied before the portfolio optimization stage and is compatible with a wide range of allocation techniques. Experiments conducted on the full S&P 500 universe and a data set of 1.300 global bonds of various types over more than two decades validate the theoretical framework. Results show that both sources of diversity effectively extend the boundaries of achievable portfolio diversification, delivering strong performance across both one-step and multi-step allocation tasks.

q-fin.PM↗

arXiv2024

Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation

An image may convey a thousand words, but a video composed of hundreds or thousands of image frames tells a more intricate story. Despite significant progress in multimodal large language models (MLLMs), generating extended videos remains a formidable challenge. As of this writing, OpenAI's Sora, the current state-of-the-art system, is still limited to producing videos that are up to one minute in length. This limitation stems from the complexity of long video generation, which requires more than generative AI techniques for approximating density functions essential aspects such as planning, story development, and maintaining spatial and temporal consistency present additional hurdles. Integrating generative AI with a divide-and-conquer approach could improve scalability for longer videos while offering greater control. In this survey, we examine the current landscape of long video generation, covering foundational techniques like GANs and diffusion models, video generation strategies, large-scale training datasets, quality metrics for evaluating long videos, and future research areas to address the limitations of the existing video generation capabilities. We believe it would serve as a comprehensive foundation, offering extensive information to guide future advancements and research in the field of long video generation.

cs.CV↗

arXiv2024

How Certain are Uncertainty Estimates? Three Novel Earth Observation Datasets for Benchmarking Uncertainty Quantification in Machine Learning

Uncertainty quantification (UQ) is essential for assessing the reliability of Earth observation (EO) products. However, the extensive use of machine learning models in EO introduces an additional layer of complexity, as those models themselves are inherently uncertain. While various UQ methods do exist for machine learning models, their performance on EO datasets remains largely unevaluated. A key challenge in the community is the absence of the ground truth for uncertainty, i.e. how certain the uncertainty estimates are, apart from the labels for the image/signal. This article fills this gap by introducing three benchmark datasets specifically designed for UQ in EO machine learning models. These datasets address three common problem types in EO: regression, image segmentation, and scene classification. They enable a transparent comparison of different UQ methods for EO machine learning models. We describe the creation and characteristics of each dataset, including data sources, preprocessing steps, and label generation, with a particular focus on calculating the reference uncertainty. We also showcase baseline performance of several machine learning models on each dataset, highlighting the utility of these benchmarks for model development and comparison. Overall, this article offers a valuable resource for researchers and practitioners working in artificial intelligence for EO, promoting a more accurate and reliable quality measure of the outputs of machine learning models. The dataset and code are accessible via https://gitlab.lrz.de/ai4eo/WG_Uncertainty.

cs.LG↗

arXiv2024

NimbleD: Enhancing Self-supervised Monocular Depth Estimation with Pseudo-labels and Large-scale Video Pre-training

We introduce NimbleD, an efficient self-supervised monocular depth estimation learning framework that incorporates supervision from pseudo-labels generated by a large vision model. This framework does not require camera intrinsics, enabling large-scale pre-training on publicly available videos. Our straightforward yet effective learning strategy significantly enhances the performance of fast and lightweight models without introducing any overhead, allowing them to achieve performance comparable to state-of-the-art self-supervised monocular depth estimation models. This advancement is particularly beneficial for virtual and augmented reality applications requiring low latency inference. The source code, model weights, and acknowledgments are available at https://github.com/xapaxca/nimbled .

cs.CV↗

arXiv2024

The Third Monocular Depth Estimation Challenge

This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%.

cs.CV↗

arXiv2023

Structured Radial Basis Function Network: Modelling Diversity for Multiple Hypotheses Prediction

Multi-modal problems can be effectively addressed using multiple hypothesis frameworks, but integrating these frameworks into learning models poses significant challenges. This paper introduces a Structured Radial Basis Function Network (s-RBFN) as an ensemble of multiple hypothesis predictors for regression. During the training of the predictors, first the centroidal Voronoi tessellations are formed based on their losses and the true labels, representing geometrically the set of multiple hypotheses. Then, the trained predictors are used to compute a structured dataset with their predictions, including centers and scales for the basis functions. A radial basis function network, with each basis function focused on a particular hypothesis, is subsequently trained using this structured dataset for multiple hypotheses prediction. The s-RBFN is designed to train efficiently while controlling diversity in ensemble learning parametrically. The least-squares approach for training the structured ensemble model provides a closed-form solution for multiple hypotheses and structured predictions. During the formation of the structured dataset, a parameter is employed to avoid mode collapse by controlling tessellation shapes. This parameter provides a mechanism to balance diversity and generalization performance for the s-RBFN. The empirical validation on two multivariate prediction datasets-air quality and energy appliance predictions-demonstrates the superior generalization performance and computational efficiency of the structured ensemble model compared to other models and their single-hypothesis counterparts.

cs.LG↗

arXiv2023

Deep Unsupervised Learning for 3D ALS Point Cloud Change Detection

Change detection from traditional \added{2D} optical images has limited capability to model the changes in the height or shape of objects. Change detection using 3D point cloud \added{from photogrammetry or LiDAR surveying} can fill this gap by providing critical depth information. While most existing machine learning based 3D point cloud change detection methods are supervised, they severely depend on the availability of annotated training data, which is in practice a critical point. To circumnavigate this dependence, we propose an unsupervised 3D point cloud change detection method mainly based on self-supervised learning using deep clustering and contrastive learning. The proposed method also relies on an adaptation of deep change vector analysis to 3D point cloud via nearest point comparison. Experiments conducted on \added{an aerial LiDAR survey dataset} show that the proposed method obtains higher performance in comparison to the traditional unsupervised methods, with a gain of about 9\% in mean accuracy (to reach more than 85\%). Thus, it appears to be a relevant choice in scenario where prior knowledge (labels) is not ensured.

eess.IV↗

arXiv2022

Deep dual stream residual network with contextual attention for pansharpening of remote sensing images

Pansharpening enhances spatial details of high spectral resolution multispectral images using features of high spatial resolution panchromatic image. There are a number of traditional pansharpening approaches but producing an image exhibiting high spectral and spatial fidelity is still an open problem. Recently, deep learning has been used to produce promising pansharpened images; however, most of these approaches apply similar treatment to both multispectral and panchromatic images by using the same network for feature extraction. In this work, we present present a novel dual attention-based two-stream network. It starts with feature extraction using two separate networks for both images, an encoder with attention mechanism to recalibrate the extracted features. This is followed by fusion of the features forming a compact representation fed into an image reconstruction network to produce a pansharpened image. The experimental results on the Pl\'{e}iades dataset using standard quantitative evaluation metrics and visual inspection demonstrates that the proposed approach performs better than other approaches in terms of pansharpened image quality.

cs.CV↗

arXiv2022

A Peek into the Political Biases in Email Spam Filtering Algorithms During US Election 2020

Email services use spam filtering algorithms (SFAs) to filter emails that are unwanted by the user. However, at times, the emails perceived by an SFA as unwanted may be important to the user. Such incorrect decisions can have significant implications if SFAs treat emails of user interest as spam on a large scale. This is particularly important during national elections. To study whether the SFAs of popular email services have any biases in treating the campaign emails, we conducted a large-scale study of the campaign emails of the US elections 2020 by subscribing to a large number of Presidential, Senate, and House candidates using over a hundred email accounts on Gmail, Outlook, and Yahoo. We analyzed the biases in the SFAs towards the left and the right candidates and further studied the impact of the interactions (such as reading or marking emails as spam) of email recipients on these biases. We observed that the SFAs of different email services indeed exhibit biases towards different political affiliations. We present this and several other important observations in this paper.

cs.CY↗