Fusing heterogeneous information remains a persistent challenge in modern data analysis. While significant progress has been made, existing approaches often fail to account for the inherent heterogeneity of object patterns across different semantic spaces. To address this limitation, we propose the **Cooperation of Experts (CoE)** framework, which encodes multi-typed information into unified heterogeneous multiplex networks. By transcending modality and connection differences, CoE provides a powerful and flexible model for capturing the intricate structures of real-world complex data. In our framework, dedicated encoders act as domain-specific experts, each specializing in learning distinct relational patterns in specific semantic spaces. To enhance robustness and extract complementary knowledge, these experts collaborate through a novel **large margin** mechanism supported by a tailored optimization strategy. Rigorous theoretical analyses guarantee the framework’s feasibility and stability, while extensive experiments across diverse benchmarks demonstrate its superior performance and broad applicability.

Recent advances in CV and NLP have inspired researchers to develop general-purpose graph foundation models through pre-training across diverse domains. However, a fundamental challenge arises from the substantial differences in graph topologies across domains. Additionally, real-world graphs are often sparse and prone to noisy connections and adversarial attacks. To address these issues, we propose the Multi-Domain Graph Foundation Model (MDGFM), a unified framework that aligns and leverages cross-domain topological information to facilitate robust knowledge transfer. MDGFM bridges different domains by adaptively balancing features and topology while refining original graphs to eliminate noise and align topological structures. To further enhance knowledge transfer, we introduce an efficient prompt-tuning approach. By aligning topologies, MDGFM not only improves multi-domain pre-training but also enables robust knowledge transfer to unseen domains. Theoretical analyses provide guarantees of MDGFM's effectiveness and domain generalization capabilities. Extensive experiments on both homophilic and heterophilic graph datasets validate the robustness and efficacy of our method.

Multimodal graphs, which integrate unstructured heterogeneous data with structured interconnections, offer substantial real-world utility but remain insufficiently explored in unsupervised learning. In this work, we initiate the study of multimodal graph clustering, aiming to bridge this critical gap. Through empirical analysis, we observe that real-world multimodal graphs often exhibit hybrid neighborhood patterns, combining both homophilic and heterophilic relationships. To address this challenge, we propose a novel framework---Disentangled Multimodal Graph Clustering (DMGC) ---which decomposes the original hybrid graph into two complementary views: (1) a homophily-enhanced graph that captures cross-modal class consistency, and (2) heterophily-aware graphs that preserve modality-specific inter-class distinctions. We introduce a Multimodal Dual-frequency Fusion mechanism that jointly filters these disentangled graphs through a dual-pass strategy, enabling effective multimodal integration while mitigating category confusion. Our self-supervised alignment objectives further guide the learning process without requiring labels. Extensive experiments on both multimodal and multi-relational graph datasets demonstrate that DMGC achieves state-of-the-art performance, highlighting its effectiveness and generalizability across diverse settings. Our code is available at https://github.com/Uncnbb/DMGC.

ABSTRACT Aiming at the technical challenges of low latency and high reliability in the complex communication environment of the intelligent industrial network, and the trend of the current Internet of Things architecture is increasingly IP‐based, this paper proposes a fast and accurate IP packet forwarding method applied to the routing node, aiming at dealing with the header control packet error problem under high bit error conditions. This method breaks through the limitations of traditional retransmission mechanism and artificially adding redundant information, and only uses the natural redundant characteristics of the protocol itself to realize the correct separation of the session flow in high error environment. The test results on the public data set show that the proposed method can complete the separation of the session stream with a probability of not less than 99% at the bit error rate of by sacrificing part of the complexity, which provides a new idea and technical means for the fault‐tolerant receiving processing of the header five‐tuple field in complex communication environments.

Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels. However, heterophily has been largely ignored, despite its ubiquitous presence in real-world heterogeneous graphs. In this article, we define semantic heterophily and propose an innovative framework called latent graphs guided unsupervised representation learning (LatGRL) to handle this problem. First, we develop a similarity mining method that couples global structures and attributes, enabling the construction of fine-grained homophilic and heterophilic latent graphs (LGs) to guide the representation learning. Moreover, we propose an adaptive dual-frequency semantic fusion mechanism to address the problem of node-level semantic heterophily. To cope with the massive scale of real-world data, we further design a scalable implementation. Extensive experiments on benchmark datasets validate the effectiveness and efficiency of our proposed framework. The source code and datasets have been made available at https://github.com/zxlearningdeep/LatGRL.

Multi-relational graph clustering has demonstrated remarkable success in uncovering underlying patterns in complex networks. Representative methods manage to align different views motivated by advances in contrastive learning. Our empirical study finds the pervasive presence of imbalance in real-world graphs, which is in principle contradictory to the motivation of alignment. In this paper, we first propose a novel metric, the Aggregation Class Distance, to empirically quantify structural disparities among different graphs. To address the challenge of view imbalance, we propose Balanced Multi-Relational Graph Clustering (BMGC), comprising unsupervised dominant view mining and dual signals guided representation learning. It dynamically mines the dominant view throughout the training process, synergistically improving clustering performance with representation learning. Theoretical analysis ensures the effectiveness of dominant view mining. Extensive experiments and in-depth analysis on real-world and synthetic datasets showcase that BMGC achieves state-of-the-art performance, underscoring its superiority in addressing the view imbalance inherent in multi-relational graphs. The source code and datasets are available at https://github.com/zxlearningdeep/BMGC.

Unsupervised Multiplex Graph Learning (UMGL) aims to learn node representations on various edge types without manual labeling. However, existing research overlooks a key factor: the reliability of the graph structure. Real-world data often exhibit a complex nature and contain abundant task-irrelevant noise, severely compromising UMGL's performance. Moreover, existing methods primarily rely on contrastive learning to maximize mutual information across different graphs, limiting them to multiplex graph redundant scenarios and failing to capture view-unique task-relevant information. In this paper, we focus on a more realistic and challenging task: to unsupervisedly learn a fused graph from multiple graphs that preserve sufficient task-relevant information while removing task-irrelevant noise. Specifically, our proposed Information-aware Unsupervised Multiplex Graph Fusion framework (InfoMGF) uses graph structure refinement to eliminate irrelevant noise and simultaneously maximizes view-shared and view-unique task-relevant information, thereby tackling the frontier of non-redundant multiplex graph. Theoretical analyses further guarantee the effectiveness of InfoMGF. Comprehensive experiments against various baselines on different downstream tasks demonstrate its superior performance and robustness. Surprisingly, our unsupervised method even beats the sophisticated supervised approaches. The source code and datasets are available at https://github.com/zxlearningdeep/InfoMGF.

Mainstream wireless communication networks mostly adopt the layered protocol encapsulation mechanism, which inevitably introduces natural redundancy into protocols. To fully exploit the abundant natural redundancy in protocols (NRP), this paper provides a novel cross-frame and cross-layer perspective for channel coding and decoding (CCD). First, a generalized CCD architecture is developed for the first time to describe the NRP and artificial redundancy in channel codes (ARC) uniformly. The concept of equivalent code rate is proposed correspondingly to evaluate the potential gain of NRP. Second, we summarize the types of NRP, and for each of them, factor graphs and sum-product algorithms (SPAs) are adopted to model and solve the correlation between it and ARC. On this basis, the joint decoding of multi-class NRP and ARC is further considered, and a general SPA-based joint protocol-channel decoding (JPCD) scheme is presented. Finally, tests on the 802.11n TCP/IP/MAC protocol stack demonstrate that the JPCD scheme can significantly improve the decoding performance of both the packet header and payload with a relatively small computational cost. Our work shows great promise in reducing error retransmission, bandwidth overhead, and the difficulty of source recovery.

Abstract The current wireless communication system has higher performance demands for receivers. This paper considers exploiting the natural redundancy (NR) that is widely existed in the transmission sources to improve the receiver's performance of sequence detection. The type of NR discussed in this paper is the inherent redundancy in data caused by the correlation between symbols in the memory sources. Since the correlation between transmitted symbols is too challenging to obtain, deep learning (DL) is introduced into sequence detection, which has a powerful ability to extract complex patterns from data. Specifically, intended for a specific memory source that is convenient for performance analysis, namely the Markov source, an iterative sequence detection algorithm based on the long short‐term memory network is proposed. Simulation results demonstrate that the receiver's performance can be improved by exploiting the NR and the proposed DL‐based sequence detection scheme can obtain optimal bit error rate performance with blind state transition probability of the transmitted Markov source.

A high-performance communication receiver desires a sufficient and accurate recognition of transmitted sources. In this paper, we propose a sequential decoding algorithm for the robust reception of sources with natural redundancy (NR) over the AWGN channel. To fully exploit the abundant NR in the exemplified English text sources, a causal language modeling (CLM) with a powerful Transformer decoder neural network (NN) structure is adopted for modeling the joint probability distribution. For versatility of byte-level tokenization, the UTF-8 encoding scheme is considered for the Wikipedia corpus, namely the English edition of the Wiki-40B dataset. The tree search-based M-algorithm (MA) is integrated with CLM, denoted as CLM-MA algorithm, to synthesize the a priori probability of information sequence and likelihood values of polluted symbols. Both simulation experiments and hardware platform evaluations are conducted to analyze the performance of the CLM-MA algorithm. With an adequately large M value, tremendous performance profit is achievable, especially for high-efficiency modulation levels and extremely noisy conditions. This mechanism of adopting the pre-trained NN model merely desires self-supervised learning architecture and eliminates the requirement of high-cost and accurate labels, which paves a new way for communication receiver design.

This letter deals with frequency domain equalization (FDE) in the presence of residual timing offsets. A novel iterative decision feedback equalizer for single-carrier FDE systems is proposed. Different from conventional schemes based on explicit point time-delay estimates, the proposed scheme operates directly on the oversampled matched filter output. For each iteration, FDE is performed first, and based on which, joint posterior distribution of the channel and timing parameters is obtained. A set of weights obtained from the corresponding posterior distribution, rather than explicit point time-delay estimate, are utilized for the time-delay compensation, eliminating the need of fine timing synchronization. Simulation results show that the proposed scheme enables evident performance improvement in terms of symbol error rate compared with conventional schemes under relative low sampling rate.