Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.2
2.2
Journals
Symmetry
Special Issues
Symmetry in Artificial Intelligence and Machine Learning: Current Advances
share announcement

Symmetry in Artificial Intelligence and Machine Learning: Current Advances

A Special Issue of Symmetry (ISSN 2073-8994) belonging to the section "A: Computer Science".

Deadline for manuscript submissions: 31 October 2026 | Viewed by 4730

Editors

Dr. Haobing Liu

E-Mail Website
Guest Editor
School of Computer Science and Technology, Ocean University of China, Qingdao 266005, China
Interests: data mining; machine learning; IoT application
Prof. Dr. Yanwei Yu

E-Mail Website
Guest Editor
School of Computer Science and Technology, Ocean University of China, Qingdao 266005, China
Interests: data mining; machine learning; database systems
Special Issues, Collections and Topics in MDPI journals
Dr. Yuxi Wang

E-Mail Website
Guest Editor
School of Computer Science and Technology, Ocean University of China, Qingdao 266005, China
Interests: embodied intelligent perception; multimodal large models; 3D AIGC
Dr. Tianzi Zang

E-Mail Website
Guest Editor
School of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210024, China
Interests: artificial intelligence; data mining; deep learning

Special Issue Information

Dear Colleagues,

The rapid evolution of artificial intelligence (AI) and machine learning (ML) has reshaped industries, scientific research, and daily life. Symmetry has been widely embraced in AI and ML, with notable manifestations: for instance, the symmetric architecture of encoders and decoders in autoencoders enables effective feature reconstruction. Meanwhile, in multi-view learning, the symmetry among diverse data views facilitates the discovery of shared knowledge while preserving view-specific characteristics. However, challenges pertaining to model interpretability, open-world machine learning, and the need for robust, scalable solutions in dynamic environments persist.

This Special Issue aims to provide a platform for researchers to showcase their latest innovations, theoretical insights, and practical applications at the intersection of symmetry, AI, and ML. We are seeking high-quality original papers that address emerging challenges and present groundbreaking solutions in AI/ML. Topics of interest include (but are not limited to) the following:

  • Symmetry in new architectures and algorithms for machine learning.
  • Symmetric neural networks.
  • AI/ML-based symmetric data processing and analysis (e.g., mirror detection, water reflection detection).
  • AI/ML for data mining, computer vision, and natural language processing.
  • Responsible AI (e.g., fairness, interpretability, bias mitigation, and privacy-preserving learning).

Dr. Haobing Liu
Prof. Dr. Yanwei Yu
Dr. Yuxi Wang
Dr. Tianzi Zang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Symmetry is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • artificial intelligence
  • machine learning
  • deep learning
  • symmetry
  • data mining
  • computer vision
  • natural language processing

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (7 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

37 pages, 6769 KB  
Article
TRACE-Chem: Symmetry-Aware Counterfactual Reasoning over Typed Evidence Graphs for Verifiable Multimodal Chemical Record Extraction
by Jiaqi Liu, Changshuai Wang and Hanshen Li
Symmetry 2026, 18(9), 1437; https://doi.org/10.3390/sym18091437 - 27 Aug 2026
Viewed by 168
Abstract
Automatically extracted chemical records can appear complete even when names, depictions, formulas, masses, and spectra disagree. Because databases consume records rather than evidence, such errors propagate silently. TRACE-Chem (Typed Relational Attestation with Counterfactual Editing for Chemistry) is an inference-time framework for verifying and [...] Read more.
Automatically extracted chemical records can appear complete even when names, depictions, formulas, masses, and spectra disagree. Because databases consume records rather than evidence, such errors propagate silently. TRACE-Chem (Typed Relational Attestation with Counterfactual Editing for Chemistry) is an inference-time framework for verifying and repairing them. It organizes source-linked observations, candidate fields, and verifier outcomes in a Symmetric–Asymmetric Evidence Graph (SAEG) separating symmetric identity checks from directional scientific derivations. Counterfactual Localization and Dependency-Constrained Re-decoding (CLDR) masks candidate fault nodes to identify the view whose removal most restores coherence, then revises only dependency-affected fields. Executable checks and spectral compatibility feed a calibrated accept, repair, or abstain decision. On 124 open-access synthesis papers containing 1852 compound and 638 reaction records, TRACE-Chem achieved 84.3% canonical-record hard-match F1, 9.7 percentage points above the same extractor without verification. Against a single-pass multimodal baseline, invalid structures fell from 10.8% to 0.8%, unsupported fields from 14.3% to 2.4%, and expected calibration error from 0.281 to 0.052. Removing derivation direction lowered fault-localization accuracy from 91.2% to 82.8%; removing dependency discounting raised the unsafe-edit rate from 2.4% to 4.1%. Explicitly modeling relational symmetry and asymmetry therefore improves verifiability, calibration, and repair safety in multimodal chemical extraction. Full article
(This article belongs to the Special Issue Symmetry in Artificial Intelligence and Machine Learning: Current Advances)
►▼ Show Figures

Figure 1

27 pages, 15700 KB  
Article
STRATUM-Seg: An Instance Segmentation Network Exploring Symmetry and Asymmetry in Feature Representation for Coal–Gangue Sorting
by Xinyi Zhao and Zhenyu Zhang
Symmetry 2026, 18(8), 1351; https://doi.org/10.3390/sym18081351 - 11 Aug 2026
Viewed by 283
Abstract
Accurate coal–gangue instance segmentation remains challenging because visually similar materials, irregular scale variation, and densely adjacent boundaries must be handled simultaneously. To address these coupled problems, this paper proposes STRATUM-Seg, a compact network based on the nano instance-segmentation variant of You Only Look [...] Read more.
Accurate coal–gangue instance segmentation remains challenging because visually similar materials, irregular scale variation, and densely adjacent boundaries must be handled simultaneously. To address these coupled problems, this paper proposes STRATUM-Seg, a compact network based on the nano instance-segmentation variant of You Only Look Once version 11 (YOLO11n-seg), which coordinates parameter-sharing symmetry with heterogeneous and direction-selective feature processing. In the backbone, the Shared Dilated Pyramid Module applies one kernel across multiple dilation rates to extract multi-receptive-field texture features with limited parameter redundancy. In the neck, the Multi-Kernel Focus Fusion Neck aligns three pyramid levels, re-injects backbone features, and performs two-stage aggregation using heterogeneous depth-wise kernels. In the prediction head, the Difference-Enhanced Convolutional Head combines a shared trunk with direction-selective difference convolutions and inference-time re-parameterization to improve boundary representation. Experiments on the Wangjialing subset of the Dataset for Coal, Gangue, and Foreign Objects (DsCGF) show that STRATUM-Seg increases mask mean average precision (mAP) over intersection-over-union (IoU) thresholds from 0.50 to 0.95 from 0.615 to 0.668 over three independent runs while maintaining a compact deployment-form model and real-time 32-bit floating-point (FP32) end-to-end inference on the evaluated NVIDIA RTX 4090 platform. Full article
(This article belongs to the Special Issue Symmetry in Artificial Intelligence and Machine Learning: Current Advances)
►▼ Show Figures

Figure 1

26 pages, 19311 KB  
Article
From Symmetric Persistence to Asymmetric Gating: A Regime-Aware Network for Ultra-Short-Term Wind Power Forecasting
by Pengbo Zhao, Zhiying Xiao and Jiahao Zhang
Symmetry 2026, 18(8), 1348; https://doi.org/10.3390/sym18081348 - 11 Aug 2026
Viewed by 371
Abstract
Ultra-short-term wind-power forecasting must handle both stable conditions and rapid ramp events, yet many architectures do not explicitly distinguish positive from negative ramp evidence. We evaluate whether that distinction improves multi-step predictions under a chronological wind-power forecasting protocol. RAA-Net combines a persistence-anchored baseline [...] Read more.
Ultra-short-term wind-power forecasting must handle both stable conditions and rapid ramp events, yet many architectures do not explicitly distinguish positive from negative ramp evidence. We evaluate whether that distinction improves multi-step predictions under a chronological wind-power forecasting protocol. RAA-Net combines a persistence-anchored baseline with a causal GRU and separate mappings for upward and downward ramps. A calibration-set blending rule substitutes persistence for selected low-volatility cases. We evaluated two turbines from the public SDWPF dataset at 40–160 min horizons, using chronological train, validation, calibration, and test partitions and three-seed neural-model comparisons against eight baselines. RAA-Net records the lowest reported RMSE at every horizon for both turbines. On the primary turbine, it also records the best reported MAE, R2, nRMSE, and nMAE at each horizon. Component ablations quantify the effects of the directional module, anchor, and blending rule. These findings support direction-specific ramp representations for the evaluated turbines and protocol. Full article
(This article belongs to the Special Issue Symmetry in Artificial Intelligence and Machine Learning: Current Advances)
►▼ Show Figures

Figure 1

36 pages, 4717 KB  
Article
SEAL-MAC: Symmetry-Equivariant Lyapunov Actor–Critic for Queue-Stable MEC Offloading
by Mingchuan Wu, Jian Lu and Yulin Li
Symmetry 2026, 18(8), 1311; https://doi.org/10.3390/sym18081311 - 3 Aug 2026
Viewed by 290
Abstract
Mobile edge computing (MEC) must serve rapidly growing populations of latency-critical and energy-constrained devices, yet distributed offloading faces two coupled problems: learned multi-agent policies depend on the arbitrary numerical ordering of edge servers, which wastes training samples and treats physically equivalent configurations inconsistently, [...] Read more.
Mobile edge computing (MEC) must serve rapidly growing populations of latency-critical and energy-constrained devices, yet distributed offloading faces two coupled problems: learned multi-agent policies depend on the arbitrary numerical ordering of edge servers, which wastes training samples and treats physically equivalent configurations inconsistently, while short-horizon cost minimization overloads attractive servers and destabilizes their queues. This paper presents SEAL-MAC (Symmetry-Equivariant Lyapunov Multi-Agent Actor–Critic), a distributed learning framework that addresses both problems jointly. First, a symmetric resource-set actor with a mirror consistency regularizer enforces server relabeling equivariance of each user’s policy and invariance of its value and Lyapunov critics. Second, a load-symmetric Lyapunov–potential shaping mechanism augments drift-plus-penalty rewards with normalized load-balance signals, coupling queue stability, fairness, and strategic alignment. The shaped interaction is analyzed as a Lyapunov-shaped Markov potential game: exact under orthogonal congestion-separable conditions, and a Markov α-potential game under heterogeneity or interference, yielding conditional finite-time (ϵ+α)-Nash convergence and mean-square queue stability. Each device learns from local observations and O(M) queue broadcasts without exchanging gradients or policies. In simulations with up to 200 users, SEAL-MAC reduces average delay by 9.0%, 95th-percentile delay by 11.8%, energy consumption by 10.6%, and the deadline-violation rate from 3.1% to 1.8% relative to the strongest Lyapunov baseline, halves the empirical one-step deviation gain of an identically shaped Ly-PPO agent (0.048 versus 0.098), and raises the Jain fairness index from 0.88 to 0.94. Full article
(This article belongs to the Special Issue Symmetry in Artificial Intelligence and Machine Learning: Current Advances)
►▼ Show Figures

Figure 1

23 pages, 6130 KB  
Article
Symmetry-Aware Collaborative Attention Network for Robust Weak Seismic Phase Picking
by Yunpeng Wang, Qing Li, Chao Zhang, Yatong Bai, Xiaofei Du, Jianfeng Wang and Yuda He
Symmetry 2026, 18(7), 1229; https://doi.org/10.3390/sym18071229 - 20 Jul 2026
Viewed by 366
Abstract
Reliable seismic phase picking is essential to earthquake monitoring, as it fundamentally affects earthquake location and source inversion. In challenging field conditions, nonstationary waveforms, diverse morphological features and intense background noise all hinder the detection of weak phases. Seismic time series also exhibit [...] Read more.
Reliable seismic phase picking is essential to earthquake monitoring, as it fundamentally affects earthquake location and source inversion. In challenging field conditions, nonstationary waveforms, diverse morphological features and intense background noise all hinder the detection of weak phases. Seismic time series also exhibit inherent spatiotemporal asymmetry. Nevertheless, mainstream networks rely on symmetric and uniform feature extraction strategies. They overlook asymmetric properties of waveforms and introduce additional picking errors. We therefore present SymPhase, a symmetry-aware collaborative attention network, to achieve precise and robust P- and S-phase picking. Using a 1D encoder–decoder backbone, the model combines global enhancement and local refinement. It captures both long-range dependencies and local features, reducing missed weak-phase detections and minimizing arrival-time bias. Extensive tests are conducted on the CEED and DiTing datasets. The results demonstrate that SymPhase outperforms both TCN and PhaseNet. On the CEED dataset, the F1 scores for P and S phases are 0.9797 and 0.9006, with mean absolute errors of 0.0761 s and 0.1003 s. On the difficult DiTing dataset, the S-phase F1 score reaches 0.4724 with a corresponding error of 0.7386 s. These results validate its superior performance for weak signal recognition. With strong accuracy and noise robustness, SymPhase provides a viable solution for automated earthquake monitoring systems. Full article
(This article belongs to the Special Issue Symmetry in Artificial Intelligence and Machine Learning: Current Advances)
►▼ Show Figures

Figure 1

25 pages, 863 KB  
Article
Dual-Domain Symmetry: A Frequency-Aware Residual U-Net for High-Fidelity EEG Artifact Removal
by Jiahao Zhang, Tong Liu, Tianhao Cui, Fanqiang Lin and Yong Jia
Symmetry 2026, 18(6), 988; https://doi.org/10.3390/sym18060988 - 8 Jun 2026
Viewed by 384
Abstract
Electroencephalography (EEG) is a non-invasive technique used to monitor brain activity but is prone to physiological artifacts, especially eye movements (EOG) and muscle contractions (EMG). These artifacts are non-stationary and frequently overlap with neural oscillation bands, making them difficult to separate accurately from [...] Read more.
Electroencephalography (EEG) is a non-invasive technique used to monitor brain activity but is prone to physiological artifacts, especially eye movements (EOG) and muscle contractions (EMG). These artifacts are non-stationary and frequently overlap with neural oscillation bands, making them difficult to separate accurately from genuine EEG activity. Conventional single-domain filters often fail to eliminate such interference, resulting in either residual noise or the unintended suppression of authentic EEG data. To address these limitations, we propose a Frequency-Aware Residual U-Net (FARU-Net), a dual-domain, frequency-aware residual architecture for EEG artifact removal designed to improve restoration fidelity. Unlike models based solely on temporal features, FARU-Net explicitly modulates the spectral properties of the signal in the latent space through a Frequency-aware Bottleneck Module (FBM), while simultaneously refining temporal details. Additionally, Attention Gates (AGs) are integrated into the skip connections to refine feature fusion and reduce residual noise while preserving salient waveform structures. Comparative experiments on the EEGdenoiseNet benchmark demonstrate that FARU-Net achieves strong overall performance for single-channel EEG restoration. Across five independent test groups, the proposed model attains a mean Pearson correlation coefficient (CC) of 0.9681 and a mean signal-to-noise ratio improvement (ΔSNR) of 26.66 dB. These results indicate that the proposed method effectively preserves both waveform morphology and spectral structure compared with conventional U-Net variants and CNN-based models. Full article
(This article belongs to the Special Issue Symmetry in Artificial Intelligence and Machine Learning: Current Advances)
►▼ Show Figures

Figure 1

18 pages, 984 KB  
Article
Deep Multimodal Learning for Heart Sound Classification Using CNN, Transformer, and BiLSTM with Attention
by Ilyas Ait Ichou, Samir Elouaham, Boujemaa Nassiri and Jamal Isknan
Symmetry 2026, 18(4), 556; https://doi.org/10.3390/sym18040556 - 25 Mar 2026
Cited by 2 | Viewed by 1560
Abstract
Phonocardiogram (PCG) signals offer a non-invasive, low-cost screening tool for cardiovascular diseases. However, their noisy and non-stationary nature makes automated classification challenging, and traditional methods often fail to capture complex spectral-temporal patterns. This study proposes a multimodal deep learning architecture for the binary [...] Read more.
Phonocardiogram (PCG) signals offer a non-invasive, low-cost screening tool for cardiovascular diseases. However, their noisy and non-stationary nature makes automated classification challenging, and traditional methods often fail to capture complex spectral-temporal patterns. This study proposes a multimodal deep learning architecture for the binary classification of heart sounds (Healthy vs. Unhealthy). The hybrid model integrates Convolutional Neural Networks (CNNs), Transformer encoders, and Bidirectional Long Short-Term Memory (BiLSTM) networks with an attention mechanism. It utilizes an early-fusion feature extraction pipeline combining MFCCs, Mel-spectrograms, and Chroma descriptors. To ensure robust evaluation and prevent data leakage, SMOTE is applied exclusively to the training folds within a strict zero-leakage, patient-wise 5-fold cross-validation protocol. The proposed framework demonstrates exceptional performance, achieving an average accuracy of 91.67%, a sensitivity of 80.95%, a specificity of 94.46%, and an AUC-ROC of 96.50%. An ablation study confirms that integrating Transformer and BiLSTM modules significantly enhances diagnostic stability over baseline CNNs. Furthermore, with exactly 858,434 parameters (3.27 MB) and interpretable attention maps, this highly optimized model provides a robust assistive solution suitable for deployment in digital stethoscopes and mobile telemedicine systems. Full article
(This article belongs to the Special Issue Symmetry in Artificial Intelligence and Machine Learning: Current Advances)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-7
Back to TopTop