arXiv subjects

Chunhua Yang

Publications and source records attributed to Chunhua Yang.

At least 19 recordsLinked to original sources

arXiv2026

Binary Codes with a Forbidden Distance

The maximum size of a t-intersecting code in the set of words of length n over an alphabet of size m, a problem posed by Frankl and Füredi, was determined independently by Ahlswede and Khachatrian and by Frankl and Tokushige. Extending this result to the forbidden-intersection setting, Keevash, Lifshitz, Long and Minzer proved that, for m greater than two and n sufficiently large in terms of t, (t minus one)-avoiding codes have the same maximum size and the same extremal ball constructions as t-intersecting codes. They also raised the binary case. Here, t-intersecting requires every two distinct words to agree in at least t coordinates, while (t minus one)-avoiding forbids agreement in exactly t minus one coordinates. We solve the binary case for all t at least three and n at least the square of the sum of t and one. If the forbidden Hamming distance n minus t plus one is odd, the maximum size of a (t minus one)-avoiding code strictly exceeds the maximum t-intersecting size. If it is even, the two maxima coincide, but their extremal families differ: some maximum (t minus one)-avoiding codes are not t-intersecting. We also determine all maximum avoiding codes in the even case. For odd forbidden distances, weight parity and a fixed-point-free pairing determine the maximum, while the diameter theorem gives the comparison with t-intersecting codes. For even forbidden distances, parity splitting and coordinate deletion reduce the problem to avoiding two consecutive distances. Connected components, disjoint neighbourhoods, and Harper's vertex-isoperimetric theorem yield the upper bound, which is attained by a t-intersecting construction. The diameter theorem then determines the extremal structure, and elementary binomial estimates give the stated parameter range.

math.CO↗

arXiv2026

Ramanujan Transforms and Maximum Energy of Odd-Total-Exponent Integral Circulants

For a finite graph, its energy is the sum of the absolute values of its adjacency eigenvalues. Let n be the product of powers of distinct odd primes, where all exponents are positive integers, the sum of the exponents is odd, and every prime whose exponent is odd is at least five. Among all nonempty sets of proper divisors of n, the energy of the corresponding integral circulant graph is uniquely maximised by the checkerboard divisor set consisting of those divisors for which the sum of the prime-power exponents is even. The maximum energy is one half of the sum of n and the product, over all prime factors, of explicit polynomial quantities. For exponent k and parameter x, the corresponding polynomial is given by two k plus one times x to the k-th power, together with four times the sum from zero to k minus one of j plus one times x to the j-th power with alternating sign determined by the parity of k minus j. For the proof, we use weighted prime-power Ramanujan transforms, which give an exact energy model in tensor form and extend to a polynomial matrix family for real parameters greater than one. A semidefinite parity theorem shows that the matrix obtained from this polynomial family by an explicit positive diagonal normalisation is a real symmetric contraction whose unique eigenvalue of modulus one is the simple eigenvalue determined by the parity of the exponent; this holds for even exponents at least two and parameters at least three, and for odd exponents at least one and parameters at least five. Tensorising this spectral structure and centring the binary divisor tensor yield a sharp one-norm bound for the corresponding tensor operator on sign vectors. In particular, for n equal to p squared times q cubed, with distinct odd primes p and q and with q at least five, this proves Roldan's conjectured maximality in this range.

math.CO↗

arXiv2026

Maximum Energy of Integral Circulant Graphs with Same-Parity Exponents

The energy of a finite graph is the sum of the absolute values of the eigenvalues of its adjacency matrix. Let n be p to the power a times q to the power b, where p and q are distinct primes at least five and a and b, both positive integers, have the same parity. Among all nonempty sets D of proper divisors of n, the energy of the corresponding integral circulant graph is maximised by exactly two divisor sets: the divisors p to the power i times q to the power j with i plus j odd, and the divisors with i plus j even after removing p to the power a times q to the power b. We also determine the exact maximum energy. For the proof, weighted prime-power Ramanujan transforms yield an exact tensor-product representation of the graph energy, reducing the extremal problem to a weighted cut separating two prescribed vertices. After a sign conjugation, the relevant transforms decompose into embedded path blocks; the nontrivial blocks correspond to a weighted path together with chords of length three of weight negative one. We prove a sharp lower bound for cuts separating the two prescribed vertices in Kronecker products of these path blocks. For products of two such nontrivial blocks, equality holds only for cuts that isolate one of the two prescribed vertices. Combined with the energy-to-cut correspondence, these equality cases yield exactly the two maximising divisor sets.

math.CO↗

arXiv2026

So's Conjecture for Integral Circulant Graphs of Order p^aq

So conjectured that, for a fixed positive integer n, the ordinary adjacency spectrum of an integral circulant graph of order n determines its divisor set. We prove this for graphs of order p to the power a times q, where p and q are primes with p less than q and a is at least one. To handle coincident eigenvalues arising from distinct greatest-common-divisor classes, we use a spectral counting measure. For connected graphs, an exact identity recovers the part of the divisor set consisting of one and q, when present, together with the counting measure for a graph of order p to the power a minus one times q. Strong induction and decomposition into connected components then recover the full divisor set, including the case p equals two and disconnected graphs.

math.CO↗

arXiv2026

Hamilton Starters and Path Decompositions in Directed Circulants

For integers q at least 3 and r at least 1, consider the directed Cayley graph on the cyclic group of order qr whose allowed steps are the integers from 1 through r. A Hamilton cycle H is called a q-layer balanced Hamilton starter if, for every step from 1 through r and every residue class modulo q, H contains exactly one arc of that step whose tail belongs to the given residue class. The r translates of H by successive multiples of q then form a Hamilton decomposition of the digraph. A q-layer balanced Hamilton starter is called chain-compatible if one arc can be selected from each Hamilton cycle in this decomposition so that the selected arcs form a simple directed path. In both constructions, the compatible deletion chain is the arithmetic step-2 path beginning at 0 and ending at 2r. For q equal to 4, a chain-compatible starter is obtained explicitly whenever r is congruent to 1 modulo 4 and r is at least 9, while for q equal to 3 one exists for all sufficiently large r congruent to 5 modulo 6. The proofs are constructive: the four-layer case uses an ABAB step word, while in the three-layer case a directed rotational terrace is lifted to a 3-layer balanced directed 1-factor and a fixed four-arc trade joins its two cycles. Deleting the unique prescribed-path arc from each translated Hamilton cycle gives r Hamilton paths; together with the prescribed path, these form an optimal decomposition of the arc set into r+1 directed paths in both cases.

math.CO↗

arXiv2026

TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation

Accurate carbon emission monitoring is critical for climate policy and emerging regulatory mechanisms such as the EU Carbon Border Adjustment Mechanism, yet city-level high-frequency monitoring data remain extremely scarce, severely limiting data-hungry deep learning models. Time series generation is a natural remedy, but existing GAN and diffusion-based generators often provide limited explicit supervision for the domain structure of carbon emission data: they may match marginal distributional statistics while insufficiently preserving cross-variable correlations between CO$_2$ and co-emitted pollutants and meteorological factors, and tend to collapse the first-difference statistics of atmospheric measurements, producing sequences that are smooth on average but lack the realistic step-wise variability of the underlying signals. We propose TriHead-GAN, a Transformer-based adversarial framework whose triple-head discriminator jointly supervises three complementary aspects of the joint distribution: distributional authenticity via a Wasserstein critic, cross-variable dependency via leakage-free regression of the target variable, and step-wise temporal smoothness via adjacent-difference prediction. The generator combines global self-attention with local temporal convolution, per-step noise injection, and an anti-smoothing loss that matches first-difference statistics. Experiments on the self-collected Changsha Carbon dataset, two public carbon datasets (China, US), and the ETTh1 benchmark show that TriHead-GAN achieves favorable performance over mainstream baselines on the vast majority of settings, and that the resulting synthetic windows improve downstream forecasting accuracy in low-resource carbon monitoring scenarios.

cs.LG↗

arXiv2026

Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation

Human-in-the-loop reinforcement learning (HIL-RL) improves sample efficiency in real-robot manipulation through online human intervention. However, successful trajectories may include suboptimal actions that deviate from the desired task-execution path and force human intervention. Existing HIL-RL methods typically apply the consistent credit assignment principle to all transitions, uniformly propagating discounted terminal rewards through suboptimal segments, ignoring the actual contribution of each transition to task success. This overestimates Q-values for critic learning and indirectly misguides actor updates toward suboptimal behavior patterns. To this end, we propose PACT, a Preference-calibrated Actor-Critic Training framework that leverages the implicit preference signals induced by intervention to perform credit reassignment on identified suboptimal segments while directly guiding policy training for unbiased critic-actor learning. Specifically, we first design a progress model that learns from human demonstration and identifies suboptimal segments for credit correction. Then, from the human action and resampled policy action at the intervention state, we build preference pairs to define a counterfactual advantage that penalizes Bellman targets of the identified suboptimal segment, enabling directional credit calibration. Moreover, we directly align the policy with human corrective actions in the bounded mean space, providing an additional signal beyond critic-guided updates. Across five real-robot manipulation tasks, PACT improves the average success rate by 24.5% and achieves 1.3 times faster convergence, thereby improving both RL sample efficiency and performance. Code is available at https://anonymous.4open.science/r/HILRL-A1X-BC05.

cs.RO↗

arXiv2026

Efficient state transition algorithm with guaranteed optimality

The state transition algorithm (STA), as an intelligent optimization method grounded in constructivist learning, has been demonstrated to be highly effective in solving complex optimization problems. However, the standard STA suffers from slow convergence, particularly in the later stages when dealing with flat landscapes. Additionally, users are required to set the maximum number of iterations based on intuition. To address these issues, an enhanced STA with guaranteed optimality is introduced. This improvement involves three key components. First, novel translation transformations, inspired by predictive modeling, are developed to generate a broader set of candidate solutions by leveraging historical data. Second, adaptive parameter control strategies are incorporated to accelerate convergence. Finally, a dedicated termination condition is designed to ensure that the algorithm converges at the optimal solution, analogous to the zero gradient condition in mathematical programming. The comprehensive experimental results validate the effectiveness and superiority of the proposed method. The source codes for ESTA and EXSTA will be publicly available at: https://github.com/tiezhongyu2005/ESTA.

math.OC↗

arXiv2026

Consistency-Driven Calibration and Matching for Few-Shot Class-Incremental Learning

Few-Shot Class Incremental Learning (FSCIL) is crucial for adapting to the complex open-world environments. Contemporary prospective learning-based space construction methods struggle to balance old and new knowledge, as prototype bias and rigid structures limit the expressive capacity of the embedding space. Different from these strategies, we rethink the optimization dilemma from the perspective of feature-structure dual consistency, and propose a Consistency-driven Calibration and Matching (ConCM) framework that systematically mitigates the knowledge conflict inherent in FSCIL. Specifically, inspired by hippocampal associative memory, we design a memory-aware prototype calibration that extracts generalized semantic attributes from base classes and reintegrates them into novel classes to enhance the conceptual center consistency of features. Further, to consolidate memory associations, we propose dynamic structure matching, which adaptively aligns the calibrated features to a session-specific optimal manifold space, ensuring cross-session structure consistency. This process requires no class-number priors and is theoretically guaranteed to achieve geometric optimality and maximum matching. On large-scale FSCIL benchmarks including mini-ImageNet, CIFAR100 and CUB200, ConCM achieves state-of-the-art performance, with harmonic accuracy gains of up to 3.41% in incremental sessions. Code is available at: https://github.com/wire-wqz/ConCM

cs.LG↗

arXiv2026

MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning

Deep reinforcement learning (RL) has been applied extensively to solve complex decision-making problems. In many real-world scenarios, tasks often have several conflicting objectives and may require multiple agents to cooperate, which are the multi-objective multi-agent decision-making problems. However, only few works have been conducted on this intersection. Existing approaches are limited to separate fields and can only handle multi-agent decision-making with a single objective, or multi-objective decision-making with a single agent. In this paper, we propose MO-MIX to solve the multi-objective multi-agent reinforcement learning (MOMARL) problem. Our approach is based on the centralized training with decentralized execution (CTDE) framework. A weight vector representing preference over the objectives is fed into the decentralized agent network as a condition for local action-value function estimation, while a mixing network with parallel architecture is used to estimate the joint action-value function. In addition, an exploration guide approach is applied to improve the uniformity of the final non-dominated solutions. Experiments demonstrate that the proposed method can effectively solve the multi-objective multi-agent cooperative decision-making problem and generate an approximation of the Pareto set. Our approach not only significantly outperforms the baseline method in all four kinds of evaluation metrics, but also requires less computational cost.

cs.AI↗

arXiv2025

TempoGPT: Enhancing Time Series Reasoning via Quantizing Embedding

Multi-modal language model has made advanced progress in vision and audio, but still faces significant challenges in dealing with complex reasoning tasks in the time series domain. The reasons are twofold. First, labels for multi-modal time series data are coarse and devoid of analysis or reasoning processes. Training with these data cannot improve the model's reasoning capabilities. Second, due to the lack of precise tokenization in processing time series, the representation patterns for temporal and textual information are inconsistent, which hampers the effectiveness of multi-modal alignment. To address these challenges, we propose a multi-modal time series data construction approach and a multi-modal time series language model (TLM), TempoGPT. Specially, we construct multi-modal data for complex reasoning tasks by analyzing the variable-system relationships within a white-box system. Additionally, proposed TempoGPT achieves consistent representation between temporal and textual information by quantizing temporal embeddings, where temporal embeddings are quantized into a series of discrete tokens using a predefined codebook; subsequently, a shared embedding layer processes both temporal and textual tokens. Extensive experiments demonstrate that TempoGPT accurately perceives temporal information, logically infers conclusions, and achieves state-of-the-art in the constructed complex time series reasoning tasks. Moreover, we quantitatively demonstrate the effectiveness of quantizing temporal embeddings in enhancing multi-modal alignment and the reasoning capabilities of TLMs. Code and data are available at https://github.com/zhanghaochuan20/TempoGPT.

cs.LG↗

arXiv2025

AIGC for Industrial Time Series: From Deep Generative Models to Large Generative Models

With the remarkable success of generative models like ChatGPT, Artificial Intelligence Generated Content (AIGC) is undergoing explosive development. Not limited to text and images, generative models can generate industrial time series data, addressing challenges such as the difficulty of data collection and data annotation. Due to their outstanding generation ability, they have been widely used in Internet of Things, metaverse, and cyber-physical-social systems to enhance the efficiency of industrial production. In this paper, we present a comprehensive overview of generative models for industrial time series from deep generative models (DGMs) to large generative models (LGMs). First, a DGM-based AIGC framework is proposed for industrial time series generation. Within this framework, we survey advanced industrial DGMs and present a multi-perspective categorization. Furthermore, we systematically analyze the critical technologies required to construct industrial LGMs from four aspects: large-scale industrial dataset, LGMs architecture for complex industrial characteristics, self-supervised training for industrial time series, and fine-tuning of industrial downstream tasks. Finally, we conclude the challenges and future directions to enable the development of generative models in industry.

cs.LG↗

arXiv2025

Sensorformer: Cross-patch attention with global-patch compression is effective for high-dimensional multivariate time series forecasting

Among the existing Transformer-based multivariate time series forecasting methods, iTransformer, which treats each variable sequence as a token and only explicitly extracts cross-variable dependencies, and PatchTST, which adopts a channel-independent strategy and only explicitly extracts cross-time dependencies, both significantly outperform most Channel-Dependent Transformer that simultaneously extract cross-time and cross-variable dependencies. This indicates that existing Transformer-based multivariate time series forecasting methods still struggle to effectively fuse these two types of information. We attribute this issue to the dynamic time lags in the causal relationships between different variables. Therefore, we propose a new multivariate time series forecasting Transformer, Sensorformer, which first compresses the global patch information and then simultaneously extracts cross-variable and cross-time dependencies from the compressed representations. Sensorformer can effectively capture the correct inter-variable correlations and causal relationships, even in the presence of dynamic causal lags between variables, while also reducing the computational complexity of pure cross-patch self-attention from $O(D^2 \cdot Patch\_num^2 \cdot d\_model)$ to $O(D^2 \cdot Patch\_num \cdot d\_model)$. Extensive comparative and ablation experiments on 9 mainstream real-world multivariate time series forecasting datasets demonstrate the superiority of Sensorformer. The implementation of Sensorformer, following the style of the Time-series-library and scripts for reproducing the main results, is publicly available at https://github.com/BigYellowTiger/Sensorformer

cs.LG↗

arXiv2024

Canonical Correlation Guided Deep Neural Network

Learning representations of two views of data such that the resulting representations are highly linearly correlated is appealing in machine learning. In this paper, we present a canonical correlation guided learning framework, which allows to be realized by deep neural networks (CCDNN), to learn such a correlated representation. It is also a novel merging of multivariate analysis (MVA) and machine learning, which can be viewed as transforming MVA into end-to-end architectures with the aid of neural networks. Unlike the linear canonical correlation analysis (CCA), kernel CCA and deep CCA, in the proposed method, the optimization formulation is not restricted to maximize correlation, instead we make canonical correlation as a constraint, which preserves the correlated representation learning ability and focuses more on the engineering tasks endowed by optimization formulation, such as reconstruction, classification and prediction. Furthermore, to reduce the redundancy induced by correlation, a redundancy filter is designed. We illustrate the performance of CCDNN on various tasks. In experiments on MNIST dataset, the results show that CCDNN has better reconstruction performance in terms of mean squared error and mean absolute error than DCCA and DCCAE. Also, we present the application of the proposed network to industrial fault diagnosis and remaining useful life cases for the classification and prediction tasks accordingly. The proposed method demonstrates superior performance in both tasks when compared to existing methods. Extension of CCDNN to much more deeper with the aid of residual connection is also presented in appendix.

cs.LG↗

arXiv2023

Spatial-temporal associations representation and application for process monitoring using graph convolution neural network

Thank you very much for the attention and concern of colleagues and scholars in this work. With the comments and guidance of experts, editors, and reviewers, this work has been accepted for publishing in the journal "Process Safety and Environmental Protection". The theme of this paper relies on the Spatial-temporal associations of numerous variables in the same industrial processes, which refers to numerous variables obtained in dynamic industrial processes with Spatial-temporal correlation characteristics, i.e., these variables are not only highly correlated in time but also interrelated in space. To handle this problem, three key issues need to be well addressed: variable characteristics modeling and representation, graph network construction (temporal information), and graph characteristics perception. The first issue is implemented by assuming the data follows one improved Gaussian distribution, while the graph network can be defined by the monitoring variables and their edges which are calculated by their characteristics in time. Finally, these networks corresponding to process states at different times are fed into a graph convolutional neural network to implement graph classification to achieve process monitoring. A benchmark experiment (Tennessee Eastman chemical process) and one application study (cobalt purification from zinc solution) are employed to demonstrate the feasibility and applicability of this paper.

cs.LG↗

arXiv2023

Deep Domain Adaptation for Pavement Crack Detection

Deep learning-based pavement cracks detection methods often require large-scale labels with detailed crack location information to learn accurate predictions. In practice, however, crack locations are very difficult to be manually annotated due to various visual patterns of pavement crack. In this paper, we propose a Deep Domain Adaptation-based Crack Detection Network (DDACDN), which learns domain invariant features by taking advantage of the source domain knowledge to predict the multi-category crack location information in the target domain, where only image-level labels are available. Specifically, DDACDN first extracts crack features from both the source and target domain by a two-branch weights-shared backbone network. And in an effort to achieve the cross-domain adaptation, an intermediate domain is constructed by aggregating the three-scale features from the feature space of each domain to adapt the crack features from the source domain to the target domain. Finally, the network involves the knowledge of both domains and is trained to recognize and localize pavement cracks. To facilitate accurate training and validation for domain adaptation, we use two challenging pavement crack datasets CQU-BPDD and RDD2020. Furthermore, we construct a new large-scale Bituminous Pavement Multi-label Disease Dataset named CQU-BPMDD, which contains 38994 high-resolution pavement disease images to further evaluate the robustness of our model. Extensive experiments demonstrate that DDACDN outperforms state-of-the-art pavement crack detection methods in predicting the crack location on the target domain.

cs.CV↗

arXiv2021

Graph neural network-based fault diagnosis: a review

Graph neural network (GNN)-based fault diagnosis (FD) has received increasing attention in recent years, due to the fact that data coming from several application domains can be advantageously represented as graphs. Indeed, this particular representation form has led to superior performance compared to traditional FD approaches. In this review, an easy introduction to GNN, potential applications to the field of fault diagnosis, and future perspectives are given. First, the paper reviews neural network-based FD methods by focusing on their data representations, namely, time-series, images, and graphs. Second, basic principles and principal architectures of GNN are introduced, with attention to graph convolutional networks, graph attention networks, graph sample and aggregate, graph auto-encoder, and spatial-temporal graph convolutional networks. Third, the most relevant fault diagnosis methods based on GNN are validated through the detailed experiments, and conclusions are made that the GNN-based methods can achieve good fault diagnosis performance. Finally, discussions and future challenges are provided.

eess.SY↗

arXiv2021

A Multiobjective State Transition Algorithm Based on Decomposition

Aggregation functions largely determine the convergence and diversity performance of multi-objective evolutionary algorithms in decomposition methods. Nevertheless, the traditional Tchebycheff function does not consider the matching relationship between the weight vectors and candidate solutions. In this paper, the concept of matching degree is proposed which employs vectorial angles between weight vectors and candidate solutions. Based on the matching degree, a new modified Tchebycheff aggregation function is proposed, which integrates matching degree into the Tchebycheff aggregation function. Moreover, the proposed decomposition method has the same functionality with the Tchebycheff aggregation function. Based on the proposed decomposition approach, a new multiobjective optimization algorithm named decomposition-based multi-objective state transition algorithm is proposed. Relevant experimental results show that the proposed algorithm is highly competitive in comparison with other state-of-the-art multiobjetive optimization algorithms.

math.OC↗