arXiv subjects

Xiao-Jun Zeng

Publications and source records attributed to Xiao-Jun Zeng.

17 recordsLinked to original sources

arXiv2026

MMDG-Bench: A Benchmark for Multimodal Domain Generalization

Multi-modal Domain Generalization (MMDG) seeks to leverage complementary modalities to enhance model robustness on unseen domains. Despite extensive progress in Multi-modal Learning (MML) and Domain Generalization (DG) as individual fields, their systematic integration remains under-explored. Current MMDG research is largely confined to action recognition and lacks standardized evaluation protocols. To address this, we introduce MMDG-Bench, a comprehensive benchmark featuring two foundational frameworks: DG then MML (D2M) and MML then DG (M2D). We provide unified experimental protocols across diverse tasks, including video-audio-flow action recognition and RGB-Depth-IR face anti-spoofing. By instantiating ten MMDG baselines through pairing a unified MML configuration with five DG techniques under both D2M and M2D orderings, we demonstrate that these structured combinations frequently outperform existing state-of-the-art methods, underscoring the necessity of a unified benchmarking effort. Our analysis yields three key insights: (1) Integrating DG techniques provides consistent generalization gains across various backbones, whereas non-DG methods are highly sensitive to backbone shifts; (2) The optimal framework choice depends on inter-modal stability: D2M excels when modal relations are stable across domains, while M2D is more robust to cross-domain relational variance; (3) Stronger backbones yield amplified performance dividends when integrated into our structured frameworks. MMDG-Bench provides a principled foundation and actionable design guidelines for future research in multi-modal robustness. Code is released at https://github.com/qszhan/MMDG-Bench.

cs.CV↗

arXiv2025

Extract-and-Abstract: Unifying Extractive and Abstractive Summarization within Single Encoder-Decoder Framework

Extract-then-Abstract is a naturally coherent paradigm to conduct abstractive summarization with the help of salient information identified by the extractive model. Previous works that adopt this paradigm train the extractor and abstractor separately and introduce extra parameters to highlight the extracted salients to the abstractor, which results in error accumulation and additional training costs. In this paper, we first introduce a parameter-free highlight method into the encoder-decoder framework: replacing the encoder attention mask with a saliency mask in the cross-attention module to force the decoder to focus only on salient parts of the input. A preliminary analysis compares different highlight methods, demonstrating the effectiveness of our saliency mask. We further propose the novel extract-and-abstract paradigm, ExtAbs., which jointly and seamlessly performs Extractive and Abstractive summarization tasks within single encoder-decoder model to reduce error accumulation. In ExtAbs, the vanilla encoder is augmented to extract salients, and the vanilla decoder is modified with the proposed saliency mask to generate summaries. Built upon BART and PEGASUS, experiments on three datasets show that ExtAbs can achieve superior performance than baselines on the extractive task and performs comparable, or even better than the vanilla models on the abstractive task.

cs.CL↗

arXiv2025

Group-Agent Reinforcement Learning with Heterogeneous Agents

Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function models sent by another agent if they perform better. We have conducted extensive experiments on a total of 43 different Atari 2600 games to demonstrate the superior performance of the proposed method. After the group learning, among the 129 agents examined, 96% are able to achieve a learning speed-up, and 72% are able to learn over 100 times faster. Also, around 41% of those agents have achieved a higher accumulated reward score by learning in less than 5% of the time steps required by a single agent when learning on its own.

cs.LG↗

arXiv2025

Bottom-Up Reputation Promotes Cooperation with Multi-Agent Reinforcement Learning

Reputation serves as a powerful mechanism for promoting cooperation in multi-agent systems, as agents are more inclined to cooperate with those of good social standing. While existing multi-agent reinforcement learning methods typically rely on predefined social norms to assign reputations, the question of how a population reaches a consensus on judgement when agents hold private, independent views remains unresolved. In this paper, we propose a novel bottom-up reputation learning method, Learning with Reputation Reward (LR2), designed to promote cooperative behaviour through rewards shaping based on assigned reputation. Our agent architecture includes a dilemma policy that determines cooperation by considering the impact on neighbours, and an evaluation policy that assigns reputations to affect the actions of neighbours while optimizing self-objectives. It operates using local observations and interaction-based rewards, without relying on centralized modules or predefined norms. Our findings demonstrate the effectiveness and adaptability of LR2 across various spatial social dilemma scenarios. Interestingly, we find that LR2 stabilizes and enhances cooperation not only with reward reshaping from bottom-up reputation but also by fostering strategy clustering in structured populations, thereby creating environments conducive to sustained cooperation.

cs.MA↗

arXiv2024

Time Series Analysis for Education: Methods, Applications, and Future Directions

Recent advancements in the collection and analysis of sequential educational data have brought time series analysis to a pivotal position in educational research, highlighting its essential role in facilitating data-driven decision-making. However, there is a lack of comprehensive summaries that consolidate these advancements. To the best of our knowledge, this paper is the first to provide a comprehensive review of time series analysis techniques specifically within the educational context. We begin by exploring the landscape of educational data analytics, categorizing various data sources and types relevant to education. We then review four prominent time series methods-forecasting, classification, clustering, and anomaly detection-illustrating their specific application points in educational settings. Subsequently, we present a range of educational scenarios and applications, focusing on how these methods are employed to address diverse educational tasks, which highlights the practical integration of multiple time series methods to solve complex educational problems. Finally, we conclude with a discussion on future directions, including personalized learning analytics, multimodal data fusion, and the role of large language models (LLMs) in educational time series. The contributions of this paper include a detailed taxonomy of educational data, a synthesis of time series techniques with specific educational applications, and a forward-looking perspective on emerging trends and future research opportunities in educational analysis. The related papers and resources are available and regularly updated at the project page.

cs.LG↗

arXiv2024

Temporal Interaction and its Role in the Evolution of Cooperation

This research investigates the impact of dynamic, time-varying interactions on cooperative behaviour in social dilemmas. Traditional research has focused on deterministic rules governing pairwise interactions, yet the impact of interaction frequency and synchronization in groups on cooperation remains underexplored. Addressing this gap, our work introduces two temporal interaction mechanisms to model the stochastic or periodic participation of individuals in public goods games, acknowledging real-life variances due to exogenous temporal factors and geographical time differences. We consider that the interaction state significantly influences both game payoff calculations and the strategy updating process, offering new insights into the emergence and sustainability of cooperation. Our results indicate that maximum game participation frequency is suboptimal under a stochastic interaction mechanism. Instead, an intermediate activation probability maximizes cooperation, suggesting a vital balance between interaction frequency and inactivity security. Furthermore, local synchronization of interactions within specific areas is shown to be beneficial, as time differences hinder the spread of cross-structures but promote the formation of dense cooperative clusters with smoother boundaries. We also note that stronger clustering in networks, larger group sizes and lower noise increase cooperation. This research contributes to understanding the role of node-based temporality and probabilistic interactions in social dilemmas, offering insights into fostering cooperation.

physics.soc-ph↗

arXiv2024

Enhancing Cooperation through Selective Interaction and Long-term Experiences in Multi-Agent Reinforcement Learning

The significance of network structures in promoting group cooperation within social dilemmas has been widely recognized. Prior studies attribute this facilitation to the assortment of strategies driven by spatial interactions. Although reinforcement learning has been employed to investigate the impact of dynamic interaction on the evolution of cooperation, there remains a lack of understanding about how agents develop neighbour selection behaviours and the formation of strategic assortment within an explicit interaction structure. To address this, our study introduces a computational framework based on multi-agent reinforcement learning in the spatial Prisoner's Dilemma game. This framework allows agents to select dilemma strategies and interacting neighbours based on their long-term experiences, differing from existing research that relies on preset social norms or external incentives. By modelling each agent using two distinct Q-networks, we disentangle the coevolutionary dynamics between cooperation and interaction. The results indicate that long-term experience enables agents to develop the ability to identify non-cooperative neighbours and exhibit a preference for interaction with cooperative ones. This emergent self-organizing behaviour leads to the clustering of agents with similar strategies, thereby increasing network reciprocity and enhancing group cooperation.

cs.MA↗

arXiv2024

Mapping-to-Parameter Nonlinear Functional Regression with Novel B-spline Free Knot Placement Algorithm

We propose a novel approach to nonlinear functional regression, called the Mapping-to-Parameter function model, which addresses complex and nonlinear functional regression problems in parameter space by employing any supervised learning technique. Central to this model is the mapping of function data from an infinite-dimensional function space to a finite-dimensional parameter space. This is accomplished by concurrently approximating multiple functions with a common set of B-spline basis functions by any chosen order, with their knot distribution determined by the Iterative Local Placement Algorithm, a newly proposed free knot placement algorithm. In contrast to the conventional equidistant knot placement strategy that uniformly distributes knot locations based on a predefined number of knots, our proposed algorithms determine knot location according to the local complexity of the input or output functions. The performance of our knot placement algorithms is shown to be robust in both single-function approximation and multiple-function approximation contexts. Furthermore, the effectiveness and advantage of the proposed prediction model in handling both function-on-scalar regression and function-on-function regression problems are demonstrated through several real data applications, in comparison with four groups of state-of-the-art methods.

cs.LG↗

arXiv2023

Group-Agent Reinforcement Learning

It can largely benefit the reinforcement learning (RL) process of each agent if multiple geographically distributed agents perform their separate RL tasks cooperatively. Different from multi-agent reinforcement learning (MARL) where multiple agents are in a common environment and should learn to cooperate or compete with each other, in this case each agent has its separate environment and only communicates with others to share knowledge without any cooperative or competitive behaviour as a learning outcome. In fact, this scenario exists widely in real life whose concept can be utilised in many applications, but is not well understood yet and not well formulated. As the first effort, we propose group-agent system for RL as a formulation of this scenario and the third type of RL system with respect to single-agent and multi-agent systems. We then propose a distributed RL framework called DDAL (Decentralised Distributed Asynchronous Learning) designed for group-agent reinforcement learning (GARL). We show through experiments that DDAL achieved desirable performance with very stable training and has good scalability.

cs.LG↗

arXiv2023

To transfer or not transfer: Unified transferability metric and analysis

In transfer learning, transferability is one of the most fundamental problems, which aims to evaluate the effectiveness of arbitrary transfer tasks. Existing research focuses on classification tasks and neglects domain or task differences. More importantly, there is a lack of research to determine whether to transfer or not. To address these, we propose a new analytical approach and metric, Wasserstein Distance based Joint Estimation (WDJE), for transferability estimation and determination in a unified setting: classification and regression problems with domain and task differences. The WDJE facilitates decision-making on whether to transfer or not by comparing the target risk with and without transfer. To enable the comparison, we approximate the target transfer risk by proposing a non-symmetric, easy-to-understand and easy-to-calculate target risk bound that is workable even with limited target labels. The proposed bound relates the target risk to source model performance, domain and task differences based on Wasserstein distance. We also extend our bound into unsupervised settings and establish the generalization bound from finite empirical samples. Our experiments in image classification and remaining useful life regression prediction illustrate the effectiveness of the WDJE in determining whether to transfer or not, and the proposed bound in approximating the target transfer risk.

cs.LG↗

arXiv2023

EDU-level Extractive Summarization with Varying Summary Lengths

Extractive models usually formulate text summarization as extracting fixed top-$k$ salient sentences from the document as a summary. Few works exploited extracting finer-grained Elementary Discourse Unit (EDU) with little analysis and justification for the extractive unit selection. Further, the selection strategy of the fixed top-$k$ salient sentences fits the summarization need poorly, as the number of salient sentences in different documents varies and therefore a common or best $k$ does not exist in reality. To fill these gaps, this paper first conducts the comparison analysis of oracle summaries based on EDUs and sentences, which provides evidence from both theoretical and experimental perspectives to justify and quantify that EDUs make summaries with higher automatic evaluation scores than sentences. Then, considering this merit of EDUs, this paper further proposes an EDU-level extractive model with Varying summary Lengths and develops the corresponding learning algorithm. EDU-VL learns to encode and predict probabilities of EDUs in the document, generate multiple candidate summaries with varying lengths based on various $k$ values, and encode and score candidate summaries, in an end-to-end training manner. Finally, EDU-VL is experimented on single and multi-document benchmark datasets and shows improved performances on ROUGE scores in comparison with state-of-the-art extractive models, and further human evaluation suggests that EDU-constituent summaries maintain good grammaticality and readability.

cs.CL↗

arXiv2022

Towards Better Dermoscopic Image Feature Representation Learning for Melanoma Classification

Deep learning-based melanoma classification with dermoscopic images has recently shown great potential in automatic early-stage melanoma diagnosis. However, limited by the significant data imbalance and obvious extraneous artifacts, i.e., the hair and ruler markings, discriminative feature extraction from dermoscopic images is very challenging. In this study, we seek to resolve these problems respectively towards better representation learning for lesion features. Specifically, a GAN-based data augmentation (GDA) strategy is adapted to generate synthetic melanoma-positive images, in conjunction with the proposed implicit hair denoising (IHD) strategy. Wherein the hair-related representations are implicitly disentangled via an auxiliary classifier network and reversely sent to the melanoma-feature extraction backbone for better melanoma-specific representation learning. Furthermore, to train the IHD module, the hair noises are additionally labeled on the ISIC2020 dataset, making it the first large-scale dermoscopic dataset with annotation of hair-like artifacts. Extensive experiments demonstrate the superiority of the proposed framework as well as the effectiveness of each component. The improved dataset publicly avaliable at https://github.com/kirtsy/DermoscopicDataset.

eess.IV↗

arXiv2021

Multiple Dynamic Pricing for Demand Response with Adaptive Clustering-based Customer Segmentation in Smart Grids

In this paper, we propose a realistic multiple dynamic pricing approach to demand response in the retail market. First, an adaptive clustering-based customer segmentation framework is proposed to categorize customers into different groups to enable the effective identification of usage patterns. Second, customized demand models with important market constraints which capture the price-demand relationship explicitly, are developed for each group of customers to improve the model accuracy and enable meaningful pricing. Third, the multiple pricing based demand response is formulated as a profit maximization problem subject to realistic market constraints. The overall aim of the proposed scalable and practical method aims to achieve 'right' prices for 'right' customers so as to benefit various stakeholders in the system such as grid operators, customers and retailers. The proposed multiple pricing framework is evaluated via simulations based on real-world datasets.

eess.SY↗

arXiv2021

UPANets: Learning from the Universal Pixel Attention Networks

Among image classification, skip and densely-connection-based networks have dominated most leaderboards. Recently, from the successful development of multi-head attention in natural language processing, it is sure that now is a time of either using a Transformer-like model or hybrid CNNs with attention. However, the former need a tremendous resource to train, and the latter is in the perfect balance in this direction. In this work, to make CNNs handle global and local information, we proposed UPANets, which equips channel-wise attention with a hybrid skip-densely-connection structure. Also, the extreme-connection structure makes UPANets robust with a smoother loss landscape. In experiments, UPANets surpassed most well-known and widely-used SOTAs with an accuracy of 96.47% in Cifar-10, 80.29% in Cifar-100, and 67.67% in Tiny Imagenet. Most importantly, these performances have high parameters efficiency and only trained in one customer-based GPU. We share implementing code of UPANets in https://github.com/hanktseng131415go/UPANets.

cs.CV↗

arXiv2018

An Integrated Optimization + Learning Approach to Optimal Dynamic Pricing for the Retailer with Multi-type Customers in Smart Grids

In this paper, we consider a realistic and meaningful scenario in the context of smart grids where an electricity retailer serves three different types of customers, i.e., customers with an optimal home energy management system embedded in their smart meters (C-HEMS), customers with only smart meters (C-SM), and customers without smart meters (C-NONE). The main objective of this paper is to support the retailer to make optimal day-ahead dynamic pricing decisions in such a mixed customer pool. To this end, we propose a two-level decision-making framework where the retailer acting as upper-level agent firstly announces its electricity prices of next 24 hours and customers acting as lower-level agents subsequently schedule their energy usages accordingly. For the lower level problem, we model the price responsiveness of different customers according to their unique characteristics. For the upper level problem, we optimize the dynamic prices for the retailer to maximize its profit subject to realistic market constraints. The above two-level model is tackled by genetic algorithms (GA) based distributed optimization methods while its feasibility and effectiveness are confirmed via simulation results.

eess.SY↗

arXiv2015

A Hybrid Optimization Approach to Demand Response Management for the Smart Grid

This paper proposes a hybrid approach to optimal day-ahead pricing for demand response management. At the customer-side, compared with the existing work, a detailed, comprehensive and complete energy management system, which includes all possible types of appliances, all possible applications, and an effective waiting time cost model is proposed to manage the energy usages in households (lower level problem). At the retailer-side, the best retail prices are determined to maximize the retailer's profit (upper level problem). The interactions between the electricity retailer and its customers can be cast as a bilevel optimization problem. To overcome the weakness and infeasibility of conventional Karush--Kuhn--Tucker (KKT) approach for this particular type of bilevel problem, a hybrid pricing optimization approach, which adopts the multi-population genetic algorithms for the upper level problem and distributed individual optimization algorithms for the lower level problem, is proposed. Numerical results show the applicability and effectiveness of the proposed approach and its benefit to the retailer and its customers by improving the retailer's profit and reducing the customers' bills.

eess.SY↗

arXiv2010

Twitter mood predicts the stock market

Behavioral economics tells us that emotions can profoundly affect individual behavior and decision-making. Does this also apply to societies at large, i.e., can societies experience mood states that affect their collective decision making? By extension is the public mood correlated or even predictive of economic indicators? Here we investigate whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average (DJIA) over time. We analyze the text content of daily Twitter feeds by two mood tracking tools, namely OpinionFinder that measures positive vs. negative mood and Google-Profile of Mood States (GPOMS) that measures mood in terms of 6 dimensions (Calm, Alert, Sure, Vital, Kind, and Happy). We cross-validate the resulting mood time series by comparing their ability to detect the public's response to the presidential election and Thanksgiving day in 2008. A Granger causality analysis and a Self-Organizing Fuzzy Neural Network are then used to investigate the hypothesis that public mood states, as measured by the OpinionFinder and GPOMS mood time series, are predictive of changes in DJIA closing values. Our results indicate that the accuracy of DJIA predictions can be significantly improved by the inclusion of specific public mood dimensions but not others. We find an accuracy of 87.6% in predicting the daily up and down changes in the closing values of the DJIA and a reduction of the Mean Average Percentage Error by more than 6%.

cs.CE↗