Donghong Cai

Donghong Cai, Junru Chen, Yang Yang et al.

Brain signals are important quantitative data for understanding physiological activities and diseases of human brain. Most existing studies pay attention to supervised learning methods, which, however, require high-cost clinical labels. In addition, the huge difference in the clinical patterns of brain signals measured by invasive (e.g., SEEG) and non-invasive (e.g., EEG) methods leads to the lack of a unified method. To handle the above issues, we propose to study the self-supervised learning (SSL) framework for brain signals that can be applied to pre-train either SEEG or EEG data. Intuitively, brain signals, generated by the firing of neurons, are transmitted among different connecting structures in human brain. Inspired by this, we propose MBrain to learn implicit spatial and temporal correlations between different channels (i.e., contacts of the electrode, corresponding to different brain areas) as the cornerstone for uniformly modeling different types of brain signals. Specifically, we represent the spatial correlation by a graph structure, which is built with proposed multi-channel CPC. We theoretically prove that optimizing the goal of multi-channel CPC can lead to a better predictive representation and apply the instantaneou-time-shift prediction task based on it. Then we capture the temporal correlation by designing the delayed-time-shift prediction task. Finally, replace-discriminative-learning task is proposed to preserve the characteristics of each channel. Extensive experiments of seizure detection on both EEG and SEEG large-scale real-world datasets demonstrate that our model outperforms several state-of-the-art time series SSL and unsupervised models, and has the ability to be deployed to clinical practice.

Langlin Huang, Chengsong Huang, Jinyuan Li et al.

Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, in complex tasks, GRPO frequently suffers from the ``zero-advantage problem'': when all sampled rollouts for a query fail, the relative advantage collapses to zero. Consequently, the model loses effective training signals for these questions, wasting the training data and computational budget. While simply increasing the sampling budget for these questions is a common remedy, the static sampling policy inherently constrains reasoning exploration, limiting the success rate. In this paper, we propose Lorem Perturbation for Exploration (LoPE), a simple yet effective training framework to break this exploration bottleneck. We posit that task-irrelevant prompt-space perturbations can shift the model's output distribution enough to unlock orthogonal reasoning pathways for hard questions. Specifically, LoPE prepends sequences stochastically assembled from Lorem Ipsum vocabulary (a pseudo-Latin placeholder text) to the prompts before resampling. Experiments across 1.7B, 4B, and 7B models demonstrate that LoPE significantly outperforms resampling with the original prompts. Further analysis reveals that other Latin-based random sequences with low perplexity are also effective perturbations. Our results establish LoPE as a strong baseline for broadening exploration in LLM reinforcement learning.

Bibo Wu, Fang Fang, Xianbin Wang et al.

Hierarchical federated learning (HFL) shows great advantages over conventional two-layer federated learning (FL) in reducing network overhead and interaction latency while still retaining the data privacy of distributed FL clients. However, the communication and energy overhead still pose a bottleneck for HFL performance, especially as the number of clients raises dramatically. To tackle this issue, we propose a non-orthogonal multiple access (NOMA) enabled HFL system under semi-synchronous cloud model aggregation in this paper, aiming to minimize the total cost of time and energy at each HFL global round. Specifically, we first propose a novel fuzzy logic based client orchestration policy considering client heterogenerity in multiple aspects, including channel quality, data quantity and model staleness. Subsequently, given the fuzzy based client-edge association, a joint edge server scheduling and resource allocation problem is formulated. Utilizing problem decomposition, we firstly derive the closed-form solution for the edge server scheduling subproblem via the penalty dual decomposition (PDD) method. Next, a deep deterministic policy gradient (DDPG) based algorithm is proposed to tackle the resource allocation subproblem considering time-varying environments. Finally, extensive simulations demonstrate that the proposed scheme outperforms the considered benchmarks regarding HFL performance improvement and total cost reduction.

Shan Lu, Zhicheng Dong, Donghong Cai et al.

The loss function of Generative adversarial network(GAN) is an important factor that affects the quality and diversity of the generated samples for anomaly detection. In this paper, we propose an unsupervised multiple time series anomaly detection algorithm based on the GAN with message importance measure(MIM-GAN). In particular, the time series data is divided into subsequences using a sliding window. Then a generator and a discriminator designed based on the Long Short-Term Memory (LSTM) are employed to capture the temporal correlations of the time series data. To avoid the local optimal solution of loss function and the model collapse, we introduce an exponential information measure into the loss function of GAN. Additionally, a discriminant reconstruction score consisting on discrimination and reconstruction loss is taken into account. The global optimal solution for the loss function is derived and the model collapse is proved to be avoided in our proposed MIM-GAN-based anomaly detection algorithm. Experimental results show that the proposed MIM-GAN-based anomaly detection algorithm has superior performance in terms of precision, recall, and F1 score.

Xuan Yang, Quanjin Tao, Xiao Feng et al.

Multimodal pre-training breaks down the modality barriers and allows the individual modalities to be mutually augmented with information, resulting in significant advances in representation learning. However, graph modality, as a very general and important form of data, cannot be easily interacted with other modalities because of its non-regular nature. In this paper, we propose MMGA (Multimodal learning with Graph Alignment), a novel multimodal pre-training framework to incorporate information from graph (social network), image and text modalities on social media to enhance user representation learning. In MMGA, a multi-step graph alignment mechanism is proposed to add the self-supervision from graph modality to optimize the image and text encoders, while using the information from the image and text modalities to guide the graph encoder learning. We conduct experiments on the dataset crawled from Instagram. The experimental results show that MMGA works well on the dataset and improves the fans prediction task's performance. We release our dataset, the first social media multimodal dataset with graph, of 60,000 users labeled with specific topics based on 2 million posts to facilitate future research.

Jinyuan Li, Langlin Huang, Chengsong Huang et al.

Process Reward Models (PRMs) provide step-level feedback for reasoning, but current PRMs usually output only a single reward score for each step. Downstream methods must therefore treat imperfect step-level reward predictions as reliable decision signals, with no indication of when these predictions should be trusted. We propose BetaPRM, a distributional PRM that predicts both a step-level success probability and the reliability of that prediction. Given step-success supervision from Monte Carlo continuations, BetaPRM learns a Beta belief that explains the observed number of successful continuations through a Beta-Binomial likelihood, rather than regressing to the finite-sample success ratio as a point target. This learned reliability signal indicates when a step reward should be trusted, enabling downstream applications to distinguish reliable rewards from uncertain ones. As one application, we introduce Adaptive Computation Allocation (ACA) for PRM-guided Best-of-N reasoning. ACA uses the learned reliability signal to stop when a high-reward solution is reliable and to spend additional computation on uncertain candidate prefixes. Experiments across four backbones and four reasoning benchmarks show that BetaPRM improves PRM-guided Best-of-N selection while preserving standard step-level error detection. Built on this signal, ACA improves the accuracy--token tradeoff over fixed-budget Best-of-16, reducing token usage by up to 33.57% while improving final-answer accuracy.

Jiarui Feng, Donghong Cai, Yixin Chen et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks. However, adapting LLMs to effectively handle structural data, such as knowledge graphs or web data, remains a challenging problem. Some approaches adopt complex strategies to convert graphs into text sequences, resulting in significant token overhead and rendering them impractical for large-scale graphs. Others introduce additional modules to encode graphs into fixed-size token representations for LLMs. However, these methods typically require large-scale post-training on graph-text corpus and complex alignment procedures, yet often yield sub-optimal results due to poor modality alignment. Inspired by in-parameter knowledge injection for test-time adaptation of LLMs, we propose GRIP, a novel framework that equips LLMs with the ability to internalize complex relational information from graphs through carefully designed fine-tuning tasks. This knowledge is efficiently stored within lightweight LoRA parameters, enabling the fine-tuned LLM to perform a wide range of graph-related tasks without requiring access to the original graph at inference time. Extensive experiments across multiple benchmarks validate the effectiveness and efficiency of our approach.

Donghong Cai, Jiarui Feng, Yanbo Wang et al.

Synthetic tabular data generation has attracted growing attention due to its importance for data augmentation, foundation models, and privacy. However, real-world tabular datasets increasingly contain free-form text fields (e.g., reviews or clinical notes) alongside structured numerical and categorical attributes. Generating such heterogeneous tables with joint modeling of different modalities remains challenging. Existing approaches broadly fall into two categories: diffusion-based methods and LLM-based methods. Diffusion models can capture complex dependencies over numerical and categorical features in continuous or discrete spaces, but extending them to open-ended text is nontrivial and often leads to degraded text quality. In contrast, LLM-based generators naturally produce fluent text, yet their discrete tokenization can distort precise or wide-range numerical values, hindering accurate modeling of both numbers and language. In this work, we propose TabDLM, a unified framework for free-form tabular data generation via a joint numerical--language diffusion model built on masked diffusion language models (MDLMs). TabDLM models textual and categorical features through masked diffusion, while modeling numerical features with a continuous diffusion process through learned specialized numeric tokens embedding; bidirectional attention then captures cross-modality interactions within a single model. Extensive experiments on diverse benchmarks demonstrate the effectiveness of TabDLM compared to strong diffusion- and LLM-based baselines.

Gengcan Chen, Donghong Cai, Zahid Khan et al.

In electronic consumer Internet of Things (IoT), consumer electronic devices as edge devices require less computational overhead and the remote state estimation (RSE) of consumer electronic devices is always at risk of denial-of-service (DoS) attacks. Therefore, the adversarial strategy between consumer electronic devices and DoS attackers is critical. This paper focuses on the adversarial strategy between consumer electronic devices and DoS attackers in IoT-enabled RSE Systems. We first propose a remote joint estimation model for distributed measurements to effectively reduce consumer electronic device workload and minimize data leakage risks. The Kalman filter is deployed on the remote estimator, and the DoS attacks with open-loop as well as closed-loop are considered. We further introduce advanced reinforcement learning techniques, including centralized and distributed Minimax-DQN, to address high-dimensional decision-making challenges in both open-loop and closed-loop scenarios. Especially, the Q-network instead of the Q-table is used in the proposed approaches, which effectively solves the challenge of Q-learning. Moreover, the proposed distributed Minimax-DQN reduces the action space to expedite the search for Nash Equilibrium (NE). The experimental results validate that the proposed model can expeditiously restore the RSE error covariance to a stable state in the presence of DoS attacks, exhibiting notable attack robustness. The proposed centralized and distributed Minimax-DQN effectively resolves the NE in both open and closed-loop case, showcasing remarkable performance in terms of convergence. It reveals that substantial advantages in both efficiency and stability are achieved compared with the state-of-the-art methods.

Tingxuan Xu, Jiarui Feng, Justin Melendez et al.

In the past two years, large language model (LLM)-based chatbots, such as ChatGPT, have revolutionized various domains by enabling diverse task completion and question-answering capabilities. However, their application in scientific research remains constrained by challenges such as hallucinations, limited domain-specific knowledge, and lack of explainability or traceability for the response. Graph-based Retrieval-Augmented Generation (GraphRAG) has emerged as a promising approach to improving chatbot reliability by integrating domain-specific contextual information before response generation, addressing some limitations of standard LLMs. Despite its potential, there are only limited studies that evaluate GraphRAG on specific domains that require intensive knowledge, like Alzheimer's disease or other biomedical domains. In this paper, we assess the quality and traceability of two popular GraphRAG systems. We compile a database of 50 papers and 70 expert questions related to Alzheimer's disease, construct a GraphRAG knowledge base, and employ GPT-4o as the LLM for answering queries. We then compare the quality of responses generated by GraphRAG with those from a standard GPT-4o model. Additionally, we discuss and evaluate the traceability of several Retrieval-Augmented Generation (RAG) and GraphRAG systems. Finally, we provide an easy-to-use interface with a pre-built Alzheimer's disease database for researchers to test the performance of both standard RAG and GraphRAG.

Yi Guo, Fang Fang, Donghong Cai et al.

Simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) has been considered as a promising auxiliary device to enhance the performance of the wireless network, where users located at the different sides of the surfaces can be simultaneously served by the transmitting and reflecting signals. In this paper, the energy efficiency (EE) maximization problem for a non-orthogonal multiple access (NOMA) assisted STAR-RIS downlink network is investigated. Due to the fractional form of the EE, it is challenging to solve the EE maximization problem by the traditional convex optimization solutions. In this work, a deep deterministic policy gradient (DDPG)-based algorithm is proposed to maximize the EE by jointly optimizing the transmission beamforming vectors at the base station and the coefficients matrices at the STAR-RIS. Simulation results demonstrate that the proposed algorithm can effectively maximize the system EE considering the time-varying channels.