arXiv subjects

Hadi Zare

Publications and source records attributed to Hadi Zare.

At least 19 recordsLinked to original sources

arXiv2026

FirstDiff: One-Step Diffusion-Based Anomaly Detection for Multivariate Time Series via Initial Noise Prediction

Diffusion models have recently shown strong potential for multivariate time-series anomaly detection by learning the distribution of normal data through iterative denoising. Existing diffusion-based approaches, however, typically perform anomaly detection after completing the reverse diffusion process, relying primarily on the final reconstructed signal and overlooking informative representations produced during denoising. This design incurs substantial computational cost and limits the use of intermediate diffusion information for anomaly detection. In this paper, we propose FirstDiff, a diffusion-based anomaly detection framework based on the observation that the predicted diffusion noise at the initial reverse-diffusion evaluation already contains sufficient information for accurate anomaly detection. FirstDiff models the statistical distribution of predicted diffusion noise under normal behavior using validation data, enabling anomaly inference from a single denoising-network evaluation rather than completing the reverse diffusion trajectory. To model complex temporal and inter-sensor dependencies, FirstDiff employs a Diffusion Transformer as the denoising backbone. Extensive experiments on five public benchmark datasets demonstrate that FirstDiff achieves state-of-the-art performance while reducing diffusion inference from the full reverse trajectory to a single denoising-network evaluation.

cs.LG↗

arXiv2026

FlowSonic: Stable Zero-Shot Music Editing via High-Order Trajectory Integration

Zero-shot text-guided editing of real-world music recordings requires balancing semantic modification with faithful preservation of the original musical structure. Although recent diffusion transformers trained with rectified flow have achieved remarkable success in text-to-music generation, extending them to edit existing recordings remains challenging because editing requires accurate deterministic inversion, reliable structural preservation, and numerically stable integration throughout the inversion and generation processes. We present FlowSonic, a zero-shot music editing framework built upon a pretrained diffusion transformer trained with rectified flow. FlowSonic first deterministically inverts a real-world recording into the latent space and preserves its musical structure during editing by reusing cross-attention representations extracted during inversion. To improve the numerical reliability of inversion-based editing, we introduce a high-order ODE solver and systematically investigate how different numerical integration schemes influence trajectory stability, structural preservation, and semantic controllability. Comprehensive experiments on timbre-transfer and genre-modification tasks demonstrate that FlowSonic consistently outperforms existing music editing methods across semantic alignment, harmonic preservation, structural consistency, and perceptual audio quality. We further provide geometric and empirical analyses showing how the proposed numerical integration strategy improves latent trajectory stability and leads to more reliable music editing.

cs.SD↗

arXiv2025

MusRec: Zero-Shot Text-to-Music Editing via Rectified Flow and Diffusion Transformers

Music editing has emerged as an important and practical area of artificial intelligence, with applications ranging from video game and film music production to personalizing existing tracks according to user preferences. However, existing models face significant limitations, such as being restricted to editing synthesized music generated by their own models, requiring highly precise prompts, or necessitating task-specific retraining, thus lacking true zero-shot capability. leveraging recent advances in rectified flow and diffusion transformers, we introduce MusRec, a zero-shot text-to-music editing model capable of performing diverse editing tasks on real-world music efficiently and effectively. Experimental results demonstrate that our approach outperforms existing methods in preserving musical content, structural consistency, and editing fidelity, establishing a strong foundation for controllable music editing in real-world scenarios.

cs.SD↗

arXiv2025

An Innovative Next Activity Prediction Using Process Entropy and Dynamic Attribute-Wise-Transformer in Predictive Business Process Monitoring

Next activity prediction in predictive business process monitoring is crucial for operational efficiency and informed decision-making. While machine learning and Artificial Intelligence have achieved promising results, challenges remain in balancing interpretability and accuracy, particularly due to the complexity and evolving nature of event logs. This paper presents two contributions: (i) an entropy-based model selection framework that quantifies dataset complexity to recommend suitable algorithms, and (ii) the DAW-Transformer (Dynamic Attribute-Wise Transformer), which integrates multi-head attention with a dynamic windowing mechanism to capture long-range dependencies across all attributes. Experiments on six public event logs show that the DAW-Transformer achieves superior performance on high-entropy datasets (e.g., Sepsis, Filtered Hospital Logs), whereas interpretable methods like Decision Trees perform competitively on low-entropy datasets (e.g., BPIC 2020 Prepaid Travel Costs). These results highlight the importance of aligning model choice with dataset entropy to balance accuracy and interpretability.

cs.LG↗

arXiv2024

DCOR: Anomaly Detection in Attributed Networks via Dual Contrastive Learning Reconstruction

Anomaly detection using a network-based approach is one of the most efficient ways to identify abnormal events such as fraud, security breaches, and system faults in a variety of applied domains. While most of the earlier works address the complex nature of graph-structured data and predefined anomalies, the impact of data attributes and emerging anomalies are often neglected. This paper introduces DCOR, a novel approach on attributed networks that integrates reconstruction-based anomaly detection with Contrastive Learning. Utilizing a Graph Neural Network (GNN) framework, DCOR contrasts the reconstructed adjacency and feature matrices from both the original and augmented graphs to detect subtle anomalies. We employed comprehensive experimental studies on benchmark datasets through standard evaluation measures. The results show that DCOR significantly outperforms state-of-the-art methods. Obtained results demonstrate the efficacy of proposed approach in attributed networks with the potential of uncovering new patterns of anomalies.

cs.AI↗

arXiv2023

Neural Graph Collaborative Filtering Using Variational Inference

The customization of recommended content to users holds significant importance in enhancing user experiences across a wide spectrum of applications such as e-commerce, music, and shopping. Graph-based methods have achieved considerable performance by capturing user-item interactions. However, these methods tend to utilize randomly constructed embeddings in the dataset used for training the recommender, which lacks any user preferences. Here, we propose the concept of variational embeddings as a means of pre-training the recommender system to improve the feature propagation through the layers of graph convolutional networks (GCNs). The graph variational embedding collaborative filtering (GVECF) is introduced as a novel framework to incorporate representations learned through a variational graph auto-encoder which are embedded into a GCN-based collaborative filtering. This approach effectively transforms latent high-order user-item interactions into more trainable vectors, ultimately resulting in better performance in terms of recall and normalized discounted cumulative gain(NDCG) metrics. The experiments conducted on benchmark datasets demonstrate that our proposed method achieves up to 13.78% improvement in the recall over the test data.

cs.IR↗

arXiv2021

Low-rank Dictionary Learning for Unsupervised Feature Selection

There exist many high-dimensional data in real-world applications such as biology, computer vision, and social networks. Feature selection approaches are devised to confront with high-dimensional data challenges with the aim of efficient learning technologies as well as reduction of models complexity. Due to the hardship of labeling on these datasets, there are a variety of approaches on feature selection process in an unsupervised setting by considering some important characteristics of data. In this paper, we introduce a novel unsupervised feature selection approach by applying dictionary learning ideas in a low-rank representation. Dictionary learning in a low-rank representation not only enables us to provide a new representation, but it also maintains feature correlation. Then, spectral analysis is employed to preserve sample similarities. Finally, a unified objective function for unsupervised feature selection is proposed in a sparse way by an $\ell_{2,1}$-norm regularization. Furthermore, an efficient numerical algorithm is designed to solve the corresponding optimization problem. We demonstrate the performance of the proposed method based on a variety of standard datasets from different applied domains. Our experimental findings reveal that the proposed method outperforms the state-of-the-art algorithm.

cs.LG↗

arXiv2019

Detection of Community Structures in Networks with Nodal Features based on Generative Probabilistic Approach

Community detection is considered as a fundamental task in analyzing social networks. Even though many techniques have been proposed for community detection, most of them are based exclusively on the connectivity structures. However, there are node features in real networks, such as gender types in social networks, feeding behavior in ecological networks, and location on e-trading networks, that can be further leveraged with the network structure to attain more accurate community detection methods. We propose a novel probabilistic graphical model to detect communities by taking into account both network structure and nodes' features. The proposed approach learns the relevant features of communities through a generative probabilistic model without any prior assumption on the communities. Furthermore, the model is capable of determining the strength of node features and structural elements of the networks on shaping the communities. The effectiveness of the proposed approach over the state-of-the-art algorithms is revealed on synthetic and benchmark networks.

cs.SI↗

arXiv2019

Unsupervised Feature Selection based on Adaptive Similarity Learning and Subspace Clustering

Feature selection methods have an important role on the readability of data and the reduction of complexity of learning algorithms. In recent years, a variety of efforts are investigated on feature selection problems based on unsupervised viewpoint due to the laborious labeling task on large datasets. In this paper, we propose a novel approach on unsupervised feature selection initiated from the subspace clustering to preserve the similarities by representation learning of low dimensional subspaces among the samples. A self-expressive model is employed to implicitly learn the cluster similarities in an adaptive manner. The proposed method not only maintains the sample similarities through subspace clustering, but it also captures the discriminative information based on a regularized regression model. In line with the convergence analysis of the proposed method, the experimental results on benchmark datasets demonstrate the effectiveness of our approach as compared with the state of the art methods.

cs.LG↗

arXiv2019

Leveraging Deep Graph-Based Text Representation for Sentiment Polarity Applications

Over the last few years, machine learning over graph structures has manifested a significant enhancement in text mining applications such as event detection, opinion mining, and news recommendation. One of the primary challenges in this regard is structuring a graph that encodes and encompasses the features of textual data for the effective machine learning algorithm. Besides, exploration and exploiting of semantic relations is regarded as a principal step in text mining applications. However, most of the traditional text mining methods perform somewhat poor in terms of employing such relations. In this paper, we propose a sentence-level graph-based text representation which includes stop words to consider semantic and term relations. Then, we employ a representation learning approach on the combined graphs of sentences to extract the latent and continuous features of the documents. Eventually, the learned features of the documents are fed into a deep neural network for the sentiment classification task. The experimental results demonstrate that the proposed method substantially outperforms the related sentiment analysis approaches based on several benchmark datasets. Furthermore, our method can be generalized on different datasets without any dependency on pre-trained word embeddings.

cs.CL↗

arXiv2019

Deep Learning Approach on Information Diffusion in Heterogeneous Networks

There are many real-world knowledge based networked systems with multi-type interacting entities that can be regarded as heterogeneous networks including human connections and biological evolutions. One of the main issues in such networks is to predict information diffusion such as shape, growth and size of social events and evolutions in the future. While there exist a variety of works on this topic mainly using a threshold-based approach, they suffer from the local viewpoint on the network and sensitivity to the threshold parameters. In this paper, information diffusion is considered through a latent representation learning of the heterogeneous networks to encode in a deep learning model. To this end, we propose a novel meta-path representation learning approach, Heterogeneous Deep Diffusion(HDD), to exploit meta-paths as main entities in networks. At first, the functional heterogeneous structures of the network are learned by a continuous latent representation through traversing meta-paths with the aim of global end-to-end viewpoint. Then, the well-known deep learning architectures are employed on our generated features to predict diffusion processes in the network. The proposed approach enables us to apply it on different information diffusion tasks such as topic diffusion and cascade prediction. We demonstrate the proposed approach on benchmark network datasets through the well-known evaluation measures. The experimental results show that our approach outperforms the earlier state-of-the-art methods.

cs.SI↗

arXiv2019

On the image of the unstable Boardman map

We consider the `unstable Boardman map' (homomorphism if $k>0$) $$b:π^{m+k}Σ^kΩ^lS^{n+l}\simeq[Ω^lS^{n+l},Ω^kS^{m+k}]\longrightarrow \mathrm{Hom}(H_*Ω^lS^{n+l},H_*Ω^kS^{m+k})$$ defined by $h(f)=f_*$. We work at the prime $2$, with $k=0$, and determine the image for various in the following cases : (1) $m=n$ and $l>0$ arbitrary; (2) $m>n$ and $l=1$. We observe that in most of the cases the image is trivial with the exceptions corresponding to the cases when either there is a (commutative) $H$-space structure on $S^n$ or there is a Hopf invariant one element.

math.AT↗

arXiv2019

An algorithmic search for $\mathcal{A}$-annihilated classes in the Dyer-Lashof algebra and $H_*QS^0$ I. Closed form for low lengths and tables in low dimensions

The aim of this work is to publicise some computational results involving tables which contain $\mathcal{A}$-annihilated monomials, excluding square classes, in the Dyer-Lashof algebra and $H_*QS^0$; our computations go up to dimension $1.1\times 10^7$ but the tables in this paper only announce results up to dimension $2^{17}=131072$ and full tables would be available upon request. The theoretical background for our computations is provided by work of Curtis \cite{Curtis} and Wellington \cite{Wellington} on the $\mathcal{A}$-module structure of the Dyer-Lashof algebra as well as $H_*QS^0$. It seems to us that there is a workable algorithm to do these computations which we plan to announce in a future work, partly to avoid making this paper longer than it is. We hope to receive feedback from the experts on these computations and make our algorithm available as soon as we can. We hope that these tables provide a source for researchers in the field, as well as a pool of data to analyse the behaviour of these sequences, their distributions and other asymptotic behaviours. The problem of computing spherical classes in $H_*QS^0$ as well as the symmetric and non-symmetric hit problems have been our main motivations to pursue this project.

math.AT↗

arXiv2018

On Freudenthal theorem, Kahn-Priddy Theorem, and Curits conjecture

We verify Curtis conjecture on a class of elements of ${_2π_*^s}$ that satisfy a certain factorisation property. To be more precise, suppose $f\in{_2π_n^s}$ pulls back to $g\in{_2π_n^s}P$ through the Kahn-Priddy map $λ:QP\to Q_0S^0$ such that $g$ projects nontrivially to an element $g'\in{_2π_n^s}P_{t(n)}$ with $h(g')=0$ where $h:{_2π_*}QP_k\to H_*QP_k$ is the unstable Hurewicz map, and $t(n)=\lceil n/2\rceil$. Then, mod out by elements of ${_2π_*^s}\simeq{_2π_*}QS^0$ satisfying this property, the Curtis conjecture on the image of $h:{_2π_*}QS^0\to H_*QS^0$ holds.

math.AT↗

arXiv2018

Freudenthal theorem and spherical classes in $H_*QS^0$

This note is on spherical classes in $H_*(QS^0;k)$ when $k=\mathbb{Z},\mathbb{Z}/p$ with a special focus on the case of $p=2$ related to Curtis conjecture. We apply Freudenthal theorem to prove a vanishing result for the Hurewicz image of elements in ${π_*^s}$ that factor through certain finite spectra. Either in $p$-local or $p$-complete settings, this immediately implies that elements of well known infinite families in ${_pπ_*^s}$, such as Mahowaldean families, map trivially under the unstable Hurewicz homomorphism ${_pπ_*^s}\simeq{_pπ_*}QS^0\to H_*(QS^0;\mathbb{Z}/p)$. We also observe that the image of the integral unstable Hurewicz homomorphism $π_*^s\simeqπ_*QS^0\to H_*(QS^0;\mathbb{Z})$ when restricted to the submodule of decomposable elements, is given by $\mathbb{Z}\{h(η^2),h(ν^2),h(σ^2)\}$. We apply this latter to completely determine spherical classes in $H_*(Ω^dS^{n+d};\mathbb{Z}/2)$ for certain values of $n>0$ and $d>0$; this verifies a Eccles' conjecture on spherical classes in $H_*QS^n$, $n>0$, on finite loop spaces associated to spheres.

math.AT↗

arXiv2018

Filtered finiteness of the image of the unstable Hurewicz homomorphism with applications to bordism of immersions

After recent work of Hill, Hopkins, and Ravenel on the Kervaire invariant one problem, as well as Adams' solution of the Hopf invariant one problem, an immediate consequence of Curtis conjecture is that the set of spherical classes in $H_*Q_0S^0$ is finite. Similarly, Eccles conjecture, when specialised to $X=S^n$ with $n>0$, together with Adams' Hopf invariant one theorem, implies that the set of spherical classes in $H_*QS^n$ is finite. We prove a filtered version of the above the finiteness properties. We show that if $X$ is an arbitrary $CW$-complex such that $H_*X$ is finite dimensional then the image of the composition ${_2π_*}Ω^lΣ^{l+2}X\to{_2π_*}QΣ^2X\to H_*QΣ^2X$ is finite; the finiteness remains valid if we formally replace $X$ with $S^{-1}$. As an immediate and interesting application, we observe that for any compact Lie group $G$ with $\dim\mathfrak{g}>1$ and for any $n>0$ the image of the composition ${_2π_*}QΣ^{\dim\mathfrak{g}}BG_+^{[n]}\to{_2π_*}QΣ^{\dim\mathfrak{g}}BG_+\to {_2π_*}Q_0S^0\to H_*Q_0S^0$ is finite where $Σ^{\dim\mathfrak{g}}BG_+\to S^0$ is a suitably twisted transfer map. Next, we consider work of Koschorke and Sanderson which using Thom-Pontrjagin construction provides a $1$-$1$ correspondence (a group isomorphism if $m+d>0$) $Φ^{N,ξ}_{m,d}: \mathrm{Imm}_ξ^d(\mathbb{R}^m\times N) \longrightarrow [N_+,Ω^{m+d}Σ^dT(ξ)]$. We apply work of Asadi and Eccles on computing Stiefel-Whitney numbers of immersions to show that given a framed immersion $M\to\mathbb{R}^{n+k}$ and choosing $n$ very large with respect to $d$ and $k$, all self-intersection manifolds of an arbitrary element of $\mathrm{Imm}_ξ^d(\mathbb{R}^m\times N)$ are boundary.

math.AT↗

arXiv2017

Towards a Browder theorem for spherical classes in $Ω^lS^{n+l}$

According to Browder if $4n+2\neq 2^{t+1}-2$ then the Kervaire invariant of the cobordism class of a $(4n+2)$-dimensional manifold $M^{4n+2}$ vanishes and $M^{2^{t+1}-2}$ is of Kervaire invariant one if and only if $h_t^2\in\mathrm{Ext}(\mathbb{Z}/2,\mathbb{Z}/2)$ is a permanent cycle. On the other hand, according to Madsen if $4n+2\neq 2^t-2$ then $M^{4n+2}$ is cobordant to a sphere (hence of Kervaire invariant zero) and $M^{2^{t+1}-2}$ is not cobordant to a sphere (hence of Kervaire invariant one) if and only if certain element $p_{2^{t}-1}^2\in H_*QS^0$ is spherical. Moreover, it is known that $p_{2^t-1}^2$ is spherical if and only if $h_t^2$ is a permanent cycle in the Adams spectral sequence. Moreover, classes $p_{2n+1}^2\in H_*QS^0$ with $2n+1\neq 2^t-1$ are easily eliminated from being spherical. Hence, Browder's theorem admits a presentation and proof in terms of certain square classes being spherical in $H_*QS^0$ (see also work of Akhmetev and Eccles). In this note, we consider the problem of determining spherical classes $H_*Ω^lS^{n+l}$ with $n>0$ and $4\leqslant l\leqslant +\infty$. We show (1) if $ξ^2\in H_*Ω^lS^{n+l}$ is given with $\dimξ+1\neq 2^t$ and $\dim ξ+1\equiv 2\textrm{ mod }4$ and $n>l$, then $ξ^2$ is not spherical. We refer to this as a generalised Browder theorem. We also present some partial results on the degenerate cases, corresponding to $\dimξ\neq 2^t-1$, when $l>n$. (2) For $l\in\{4,5,6,7,8\}$ the only spherical classes in $H_*Ω^lS^{n+l}$ arise from the inclusion of the bottom cell, or the Hopf invariant one elements. This verifies Eccles conjecture when restricted to finite loop spaces with $l<9$.

math.AT↗

arXiv2017

Memory Enriched Big Bang Big Crunch Optimization Algorithm for Data Clustering

Cluster analysis plays an important role in decision making process for many knowledge-based systems. There exist a wide variety of different approaches for clustering applications including the heuristic techniques, probabilistic models, and traditional hierarchical algorithms. In this paper, a novel heuristic approach based on big bang-big crunch algorithm is proposed for clustering problems. The proposed method not only takes advantage of heuristic nature to alleviate typical clustering algorithms such as k-means, but it also benefits from the memory based scheme as compared to its similar heuristic techniques. Furthermore, the performance of the proposed algorithm is investigated based on several benchmark test functions as well as on the well-known datasets. The experimental results show the significant superiority of the proposed method over the similar algorithms.

cs.AI↗