Graph unlearning, motivated by emerging right to be forgotten regulations, seeks to remove the influence of specific subsets of data (e.g., noisy, poisoned, or privacy-sensitive data) from pre-trained graph learning models. While much attention has focused on the technical feasibility of unlearning, its implications for fairness remain largely unexamined. To address this critical gap, this paper introduces GUIC, the first framework that jointly ensures certified unlearning and individual fairness in graph-based models, introducing a novel perspective on responsible model updates in graph unlearning. Specifically, GUIC employs a principled distance-based rule to pinpoint individual biases arising from node removals and applies a computationally efficient certificate-driven update, preserving the local Lipschitz constraints crucial for individual fairness. Different from computationally expensive retraining or fairness-regularized optimization methods, GUIC provides a lightweight yet verifiable alternative with theoretical fairness guarantees. Experiments on multiple real-world datasets show that our method consistently surpasses existing approaches across key performance metrics.

Graph neural networks (GNNs) excel at modeling graph-structured data but often inherit and amplify biases, leading to substantial efforts in developing fair GNNs. However, most existing approaches assume full access to sensitive attribute information, which is often impractical in real-world scenarios due to privacy concerns or risks of discrimination. To address this limitation, this paper focuses on graph fairness with limited sensitive attribute information, ensuring applicability to real-world contexts where current methods fall short. Specifically, we introduce an innovative fairness optimization strategy, propose a novel framework named FGLISA, and provide a theoretical perspective linking limited sensitive attribute information access to fairness objectives, thus enabling fair graph learning in real-world applications with limited sensitive attribute information. Experiments on diverse real-world datasets and tasks validate the effectiveness of our approach in achieving both fairness and predictive performance.

Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on human experience, often lacking autonomy and emission awareness, and is prone to human errors that may compromise safety. In this paper, we propose a Curriculum Reinforcement Learning (CRL) framework integrated with a realistic, data-driven marine simulation environment and a machine learning-based fuel consumption prediction module. The simulation environment is constructed using real-world vessel movement data and enhanced with a Diffusion Model to simulate dynamic maritime conditions. Vessel fuel consumption is estimated using historical operational data and learning-based regression. The surrounding environment is represented as image-based inputs to capture spatial complexity. We design a lightweight, policy-based CRL agent with a comprehensive reward mechanism that considers safety, emissions, timeliness, and goal completion. This framework effectively handles complex tasks progressively while ensuring stable and efficient learning in continuous action spaces. We validate the proposed approach in a sea area of the Indian Ocean, demonstrating its efficacy in enabling sustainable and safe vessel navigation.

Large Language Models (LLMs) are increasingly deployed in finance, where unsafe behavior can lead to serious compliance and regulatory risks.However, most red-teaming research focuses on overtly harmful content and overlooks attacks that appear legitimate on the surface yet induce compliance-violating responses.We address this gap by introducing a controllable black-box multi-turn riskconcealed red-teaming framework (CoRT) that progressively conceals surface-level risk while exploiting non-compliant behaviors.CoRT contains two key components: (i) a Risk Concealment Attacker (RCA) that generates multi-turn prompts via iterative refinement, and (ii) a Risk Concealment Controller (RCC) that predicts a turn-level Risk Concealment Score (RCS) to steer RCA's follow-up style.We also build a domain-specific benchmark, FIN-Bench, with 522 instructions spanning six financial risk categories.Experiments on nine widely used LLMs show that CoRT (RCA) achieves 93.19% average attack success rate (ASR), and CoRT (RCA+RCC) further improves the average ASR to 95.00%.

Hao Wu, Hongru Sun, Wanqing Li, Xinguo Yu, Hao Ming, Xiao Luo, Wenbin Zhang, Jiahong Zhao, Yi Guo, Jie Yang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Ophthalmic diseases such significantly impair the vision of numerous individuals globally. Accurate and real-time 3D reconstruction of macular edema and retinal tears is crucial for improving surgical efficiency and success rates. However, lesion areas often exhibit considerable noise and high heterogeneity, and the imaging devices employed may introduce electronic noise and artifacts. Current 2D medical image segmentation techniques fail to achieve optimal outcomes. To overcome these challenges, we propose the Tri-Path Fourier-Temporal Modulation Network (TriFTM-Net). TriFTM-Net synergistically integrates spatial, frequency, and spatiotemporal features. This design effectively augments both feature representation and extraction. TriFTM-Net comprises three critical modules: the Tri-Path Spectral Hierarchical Encoder (TPSHE), which amplifies feature representation by integrating tri-path features; the Feature Re-Modulation (FRM), which reduces noise interference and enhances feature extraction; and the Hierarchical Feature Reconstruction Module (HFRM), which improves detail preservation in upsampled images. Comparative analysis with thirteen baseline methods demonstrates that our approach achieves the highest Dice scores, IoU, and Kappa coefficient on the OIMHS dataset.Our code is publicly available at https://github.com/IMOP-lab/TriFTM-Net.

Structured pruning for large language models (LLMs) has garnered significant academic interest due to its ability to efficiently compress and accelerate LLMs by eliminating redundant weight groups at a coarse-grained granularity. Current structured pruning methods for LLMs typically depend on a singular granularity for assessing weight importance, resulting in notable performance degradation in downstream tasks. Intriguingly, our empirical investigations reveal that utilizing unstructured pruning, which achieves better performance retention by pruning weights at a finer granularity, \emph{i.e.}, individual weights, yields significantly varied sparse LLM structures when juxtaposed to structured pruning. This suggests that evaluating both holistic and individual assessments for weight importance are essential for LLM pruning. Building on this insight, we introduce the Hybrid-grained Weight Importance Assessment (HyWIA), a novel method that merges fine-grained and coarse-grained evaluations of weight importance for the pruning of LLMs. Leveraging an attention mechanism, HyWIA adaptively determines the optimal blend of granularity in weight importance assessments in an end-to-end pruning manner. Extensive experiments on LLaMA-V1/V2, Vicuna, Baichuan, and Bloom across various benchmarks demonstrate the effectiveness of HyWIA in pruning LLMs. For example, HyWIA surpasses the cutting-edge LLM-Pruner by an average margin of 2.82% in accuracy across seven downstream tasks when pruning LLaMA-7B by 50%.

Learning high-level representations for graphs is crucial for tasks like node classification, where graph pooling aggregates node features to provide a holistic view that enhances predictive performance. Despite numerous methods that have been proposed in this promising and rapidly developing research field, most efforts to generalize the pooling operation to graphs are primarily performance-driven, with fairness issues largely overlooked: i) the process of graph pooling could exacerbate disparities in distribution among various subgroups; ii) the resultant graph structure augmentation may inadvertently strengthen intra-group connectivity, leading to unintended inter-group isolation. To this end, this paper extends the initial effort on fair graph pooling to the development of fair graph neural networks, while also providing a unified framework to collectively address group and individual graph fairness. Our experimental evaluations on multiple datasets demonstrate that the proposed method not only outperforms state-of-the-art baselines in terms of fairness but also achieves comparable predictive performance.

Fair Graph Neural Networks (GNNs) have been extensively studied in graph-based applications. However, most approaches to fair GNNs assume the full availability of demographic information by default, which is often unrealistic due to legal restrictions or privacy concerns, leaving a noticeable gap in methods for addressing bias under such constraints. To this end, we propose a novel method for fair graph learning without demographic information. Our approach leverages a Bayesian variational autoencoder to infer missing demographic information and uses disentangled latent variables to separately capture demographics-related and label-related information, reducing interference when inferring demographic proxies. Additionally, we incorporate a fairness regularizer that enables measuring model fairness without demographics while optimizing the fairness objective. Extensive experiments on three real-world graph datasets demonstrate the proposed method’s effectiveness in improving both fairness and utility.

Language Models (LMs) achieve outstanding performance across diverse applications but often produce biased outcomes, raising concerns about their trustworthy deployment. These concerns call for fairness research specific to LMs; however, most existing work in machine learning assumes access to model internals or training data, conditions that rarely hold in practice. As LMs continue to exert growing societal influence, it becomes increasingly important to understand and address fairness challenges unique to these models. To this end, our tutorial begins by showcasing real-world examples of bias to highlight their practical implications and uncover underlying sources. We then define fairness concepts tailored to LMs, review methods for bias evaluation and mitigation, and present a multi-dimensional taxonomy of benchmark datasets for fairness assessment. We conclude by outlining open research challenges, aiming to provide the community with both conceptual clarity and practical tools for fostering fairness in LMs. All tutorial resources are publicly accessible at https://github.com/vanbanTruong/fairness-in-large-language-models.

As generative artificial intelligence (AI) becomes increasingly prevalent in creative industries, intellectual property issues have come to the forefront, especially regarding AI-generated content that closely resembles human-created works. Recent high-profile incidents involving AI-generated outputs reproducing copyrighted materials underscore the urgent need to reassess current copyright frameworks and establish effective safeguards against infringement. To this end, this tutorial provides a structured overview of copyright challenges in generative AI across the entire development lifecycle. It begins by outlining key copyright principles relevant to generative models, then explores methods for detecting and evaluating potential infringement in generated outputs. The session also introduces strategies to safeguard creative content and training data from unauthorized replication, including mitigation techniques during model training. Finally, it reviews existing regulatory frameworks, highlights unresolved research questions, and offers recommendations to guide future work in this evolving area.

To enhance software development and maintenance efficiency, code summarization has become a research hotspot. In recent years, due to the generation capabilities of Large Language Models (LLMs), researchers have begun to propose LLMs into code-related tasks. Existing code summarization techniques are insufficient due to their limited ability to deeply comprehend code structure and semantics, frequently yielding verbose or imprecise summaries. To address these challenges, we present FRCS-LLM, a novel code summarization framework that integrates LLMs with pre-trained models to enhance performance and accuracy. Our framework first leverages simulated expert prompts to direct LLMs in generating initial code descriptions, thereby maximizing their linguistic capabilities while minimizing redundancy. We then employ pre-trained models to perform deep fusion of code snippets and functionality descriptions through multimodal joint modeling, extracting both syntactic and semantic information to generate precise, natural, and concise summaries. We evaluate FRCS-LLM on public Java and Python datasets, compared to the strongest baseline, achieving improvements of 2.4%, 3.5%, and 2.0% in BLEU, METEOR, and ROUGE_L metrics on the Java dataset, and improvements of 4.1%, 6.8%, and 3.6% on the Python dataset. Our framework also achieves superior performance in relevance, conciseness, and naturalness, producing summaries that effectively capture code semantics while maintaining completeness, fluency, and grammatical accuracy.

Fairness in artificial intelligence (AI) has become a growing concern due to discriminatory outcomes in AI-based decision-making systems. While various methods have been proposed to mitigate bias, most rely on complete demographic information, an assumption often impractical due to legal constraints and the risk of reinforcing discrimination. This survey examines fairness in AI when demographics are incomplete, addressing the gap between traditional approaches and real-world challenges. We introduce a novel taxonomy of fairness notions in this setting, clarifying their relationships and distinctions. Additionally, we summarize existing techniques that promote fairness beyond complete demographics and highlight open research questions to encourage further progress in the field.

Generative models have achieved impressive results in text to image tasks, significantly advancing visual content creation. However, this progress comes at a cost, as such models rely heavily on large-scale training data and may unintentionally replicate copyrighted elements, creating serious legal and ethical challenges for real-world deployment. To address these concerns, researchers have proposed various strategies to mitigate copyright risks, most of which are prompt based methods that filter or rewrite user inputs to prevent explicit infringement. While effective in handling obvious cases, these approaches often fall short in more subtle situations, where seemingly benign prompts can still lead to infringing outputs. To address these limitations, this paper introduces Assessing and Mitigating Copyright Risks (AMCR), a comprehensive framework which i) builds upon prompt-based strategies by systematically restructuring risky prompts into safe and non-sensitive forms, ii) detects partial infringements through attention-based similarity analysis, and iii) adaptively mitigates risks during generation to reduce copyright violations without compromising image quality. Extensive experiments validate the effectiveness of AMCR in revealing and mitigating latent copyright risks, offering practical insights and benchmarks for the safer deployment of generative models.

Fine-tuning helps large language models (LLM) recover degraded information and enhance task performance. Although Low-Rank Adaptation (LoRA) is widely used and effective for fine-tuning, we have observed that its scaling factor can limit or even reduce performance as the rank size increases. To address this issue, we propose RoRA (Rank-adaptive Reliability Optimization), a simple yet effective method for optimizing LoRA’s scaling factor. By replacing α/r with $\alpha /\sqrt r $, RoRA ensures improved performance as rank size increases. Moreover, RoRA enhances low-rank adaptation in fine-tuning uncompressed models and excels in the more challenging task of accuracy recovery when fine-tuning pruned models. Extensive experiments demonstrate the effectiveness of RoRA in fine-tuning both uncompressed and pruned models. RoRA surpasses the state-of-the-art (SOTA) in average accuracy and robustness on LLaMA-7B/13B, LLaMA2-7B, and LLaMA3-8B, specifically outperforming LoRA and DoRA by 6.5% and 2.9% on LLaMA-7B, respectively. In pruned model fine-tuning, RoRA shows significant advantages; for SHEARED-LLAMA-1.3, a LLaMA-7B with 81.4% pruning, RoRA achieves 5.7% higher average accuracy than LoRA and 3.9% higher than DoRA.

Graph Contrastive Learning (GCL) emerges as a powerful approach in recommendation systems, leveraging graph structures to learn effective representations. However, existing contrastive sampling strategies often introduce unintended biases, most notably, the misclassification of genuine positive samples as negatives, which undermines representation quality and overall recommendation performance. Accordingly, this paper revisits the conventional contrastive sampling and introduces Negative-Free Sampling for Graph Contrastive Learning (NFS). NFS adopts a two-stage sampling strategy that selectively identifies and utilizes only positive instances during training. By removing reliance on negative samples, it effectively mitigates misclassification bias and improves the semantic alignment between related representations. In addition, a comprehensive theoretical analysis is also provided to establish the robustness of NFS against representation collapse. Experimental results on three benchmarks demonstrate that NFS consistently outperforms or performs state-of-the-art methods, achieving up to a 14.2% relative improvement across evaluated datasets. In addition, a detailed ablation study is also provided to examine how exclusively leveraging positive samples contributes to the efficiency of GCL. The results further demonstrate the plug-and-play nature of the proposed method and its resilience to noisy data.

Graph generation models have shown significant potential across various domains. However, despite their success, these models often inherit societal biases, limiting their adoption in real-world applications. Existing research on fairness in graph generation primarily addresses structural bias, overlooking the critical issue of feature bias. To address this gap, we propose FDGen, a novel approach that defines and mitigates both feature and structural biases in graph generation models. Furthermore, we provide a theoretical analysis of how bias sources in graph data contribute to disparities in graph generation tasks. Experimental results on four real-world datasets demonstrate that FDGen outperforms state-of-the-art methods, achieving notable improvements in fairness while maintaining competitive generation performance.

The Area Under the ROC Curve (AUC) is a key metric for classification, especially under class imbalance, with growing research focus on optimizing AUC over accuracy in applications like medical image analysis and deepfake detection. This leads to fairness in AUC optimization becoming crucial as biases can impact protected groups. While various fairness mitigation techniques exist, fairness considerations in AUC optimization remain in their early stages, with most research focusing on improving AUC fairness under the assumption of clean protected groups. However, these studies often overlook the impact of noisy protected groups, leading to fairness violations in practice. To address this, we propose the first robust AUC fairness approach under noisy protected groups with fairness theoretical guarantees using distributionally robust optimization. Extensive experiments on tabular and image datasets show that our method outperforms state-of-the-art approaches in preserving AUC fairness. The code is in https://github.com/Purdue-M2/AUC_Fairness_with_Noisy_Groups.

Graph Neural Networks (GNNs) have excelled in diverse applications due to their outstanding predictive performance, yet they often overlook fairness considerations, prompting numerous recent efforts to address this societal concern. However, most fair GNNs assume complete demographics by design, which is impractical in most real-world socially sensitive applications due to privacy, legal, or regulatory restrictions. For example, the Consumer Financial Protection Bureau (CFPB) mandates that creditors ensure fairness without requesting or collecting information about an applicant’s race, religion, nationality, sex, or other demographics. To this end, this paper proposes fairGNN-WOD, a first-of-its-kind framework that considers mitigating unfairness in graph learning without using demographic information. In addition, this paper provides a theoretical perspective on analyzing bias in node representations and establishes the relationship between utility and fairness objectives. Experiments on three real-world graph datasets illustrate that fairGNN-WOD outperforms state-of-the-art baselines in achieving fairness but also maintains comparable prediction performance.

Fairness in artificial intelligence has garnered increasing attention due to concerns about discriminatory AI-based decision-making, prompting the development of numerous mitigation approaches. However, most existing methods assume that demographic information is readily available, which may not align with real-world scenarios where such information is often incomplete. To this end, this paper tackles the pervasive yet overlooked challenge of developing fair machine learning algorithms with limited demographics. Specifically, we explore leveraging limited demographic information to accurately infer missing demographics while simultaneously evaluating and optimizing model fairness. We argue that this approach better aligns with common real-world socially sensitive scenarios involving limited demographics. Extensive experiments on three benchmark datasets highlight the effectiveness of the proposed method, surpassing state-of-the-art with significant gains in fairness while maintaining comparable utility.

Graph generation models play pivotal roles in many real-world applications, from data augmentation to privacy-preserving. Despite their deployment successes, existing approaches often exhibit fairness issues, limiting their adoption in high-risk decision-making applications. Most existing fair graph generation works are based on autoregressive models that suffer from ordering sensitivity, while primarily addressing structural bias and overlooking the critical issue of feature bias. To this end, we propose FairGEM, a novel one-shot graph generation framework designed to mitigate both graph structural bias and node feature bias simultaneously. Furthermore, our theoretical analysis establishes that FairGEM delivers substantially stronger fairness guarantees than existing models while preserving generation quality. Extensive experiments across multiple real-world datasets demonstrate that FairGEM achieves superior performance in both generation quality and fairness.

Online learning enables effective predictive modeling on complex data streams. To overcome the negative impact of possibly high-dimensional data, sparse online learning (SOL) has been proposed by imposing various sparse constraints to sheer the resultant model structure. However, most existing SOL studies focused on a fixed feature space, whereas in practice the steaming data observations may increment in both quantity and feature dimensions, leading to varying feature spaces. In this paper, we propose a novel ℓ1,∞-mixed norm-based row sparsity SOL algorithm (SOOFS) to handle data streams in varying feature spaces. We empower SOOFS with a tailored online CUR matrix decomposition method based on the promoted row sparsity to actively and adaptively select informative instances in the sliding windows, facilitating stable online performance over time. Empirical results on ten benchmark datasets substantiate the superiority of SOOFS over three state-of-the-art competitors in terms of classification accuracy and model sparsity.

Autonomous driving platforms encounter diverse driving scenarios, each with varying hardware resources and precision requirements. Given the computational limitations of embedded devices, it is crucial to consider computing costs when deploying on target platforms like the DRIVE PX 2. Our objective is to customize the semantic segmentation network according to the computing power and specific scenarios of autonomous driving hardware. We implement dynamic adaptability through a three-tier control mechanism—width multiplier, classifier depth, and classifier kernel—allowing fine-grained control over model components based on hardware constraints and task requirements. This adaptability facilitates broad model scaling, targeted refinement of the final layers, and scenario-specific optimization of kernel sizes, leading to improved resource allocation and performance. Additionally, we leverage Bayesian Optimization with surrogate modeling to efficiently explore hyperparameter spaces under tight computational budgets. Our approach addresses scenario-specific and task-specific requirements through automatic parameter search, accommodating the unique computational complexity and accuracy needs of autonomous driving. It scales its multiply-accumulate operations (MACs) for task-specific learning adaptation (TSLA), resulting in alternative configurations tailored to diverse self-driving tasks. These TSLA customizations maximize computational capacity and model accuracy, optimizing hardware utilization.

Technical Q&A sites are valuable for software developers seeking knowledge, but the code snippets they provide are often uncompilable and incomplete due to unresolved types and missing libraries. This poses a challenge for users who wish to reuse or analyze these snippets. Existing methods either do not focus on creating compilable code or have low success rates. To address this, we propose ZS4C, a lightweight approach for zero-shot synthesis of compilable code from incomplete snippets using Large Language Models (LLMs). ZS4C operates in two stages: first, it uses an LLM, like GPT-3.5, to identify missing import statements in a snippet; second, it collaborates with a validator (e.g., compiler) to fix compilation errors caused by incorrect imports and syntax issues. We evaluated ZS4C on the StatType-SO benchmark and a new dataset, Python-SO, which includes 539 Python snippets from Stack Overflow across the 20 most popular Python libraries. ZS4C significantly outperforms existing methods, improving the compilation rate from 63% to 95.1% compared to the state-of-the-art SnR, marking a 50.1% improvement. On average, ZS4C can infer more accurate import statements (with an F1 score of 0.98) than SnR, with an improvement of 8.5% in the F1.

Recent works in artificial intelligence fairness attempt to mitigate discrimination by proposing constrained optimization programs that achieve parity for some fairness statistics. Most assume the availability of class label which is impractical in many real-world applications such as precision medicine, actuarial analysis and recidivism prediction. To this end, this talk revisits fairness and reveals idiosyncrasies of existing fairness literature assuming the availability of class label that limits their real-world utility. The primary artifacts are formulating fairness with censorship to account for scenarios where the class label is not guaranteed, and a suite of corresponding new fairness notions, algorithms, and theoretical constructs to bridge the gap between the design of a ``fair'' model in the lab and its deployment in the real-world.

Federated learning (FL), an emerging distributed machine learning paradigm, has been applied to various privacy-preserving scenarios. However, due to its distributed nature, FL faces two key issues: the non-independent and identical distribution (non-IID) of user data and vulnerability to Byzantine threats. To address these challenges, in this paper, we propose FedCAP, a robust FL framework against both data heterogeneity and Byzantine attacks. The core of FedCAP is a model update calibration mechanism to help a server capture the differences in the direction and magnitude of model updates among clients. Furthermore, we design a customized model aggregation rule that facilitates collaborative training among similar clients while accelerating the model deterioration of malicious clients. With a Euclidean norm-based anomaly detection mechanism, the server can quickly identify and permanently remove malicious clients. Moreover, the impact of data heterogeneity and Byzantine attacks can be further mitigated through personalization on the client side. We conduct extensive experiments, comparing multiple state-of-the-art baselines, to demonstrate that FedCAP performs well in several non-IID settings and shows strong robustness under a series of poisoning attacks.

Aiming at learning from a sequence of data instances over time, online learning has attracted increasing attention in the big data era. As two important variants, sparse online learning has been extensively explored by facilitating sparse constraints for online models such as truncated gradient, ℓ1-norm regularization, ℓ1-ball projection, and regularized dual averaging; while online active learning aims to build an online prediction model with a limited number of labeled instances, deploying the so called query strategies to select informative instances over time. However, most existing studies consider sparse online learning or online active learning with fixed feature spaces, whereby in real practice the features may be dynamically evolved over time. To the end, we propose a novel unified one-pass online learning framework named OASF for simultaneously online active learning and sparse online learning tailored for data streams described by open feature spaces, where new features can emerge constantly, and old features may be vanished over various time spans. Specifically, we technically develop an effective online CUR matrix decomposition based on the ℓ1,2mixed norm constraint for simultaneously selecting important up-to-date samples in a sliding window and facilitating stable and meaningful features in open feature spaces over time. If the loss function is simultaneously Lipschitz and convex, a sub-linear regret bound of our proposed algorithm is guaranteed with. Extensive experiments that are conducted with multiple streaming datasets have demonstrated the effectiveness of the proposed OASF compared with state-of-the-art online active learning and sparse online learning methods.

In the pursuit of justice and accountability in the digital age, the integration of Large Language Models (LLMs) with digital forensics holds immense promise. This half-day tutorial provides a comprehensive exploration of the transformative potential of LLMs in automating digital investigations and uncovering hidden insights. Through a combination of real-world case studies, interactive exercises, and hands-on labs, participants will gain a deep understanding of how to harness LLMs for evidence analysis, entity identification, and knowledge graph reconstruction. By fostering a collaborative learning environment, this tutorial aims to empower professionals, researchers, and students with the skills and knowledge needed to drive innovation in digital forensics. As LLMs continue to revolutionize the field, this tutorial will have far-reaching implications for enhancing justice outcomes, promoting accountability, and shaping the future of digital investigations.

The widespread use of Artificial Intelligence (AI) based decision-making systems has raised a lot of concerns regarding potential discrimination, particularly in domains with high societal impact. Most existing fairness research focused on tackling bias relies heavily on the presence of class labels, an assumption that often mismatches real-world scenarios, which ignores the ubiquity of censored data. Further, existing works regard group fairness and individual fairness as two disparate goals, overlooking their inherent interconnection, i.e., addressing one can degrade the other. This paper proposes a novel unified method that aims to mitigate group unfairness under censorship while curbing the amplification of individual unfairness when enforcing group fairness constraints. Specifically, our introduced ranking algorithm optimizes individual fairness within the bounds of group fairness, uniquely accounting for censored information. Evaluation across four benchmark tasks confirms the effectiveness of our method in quantifying and mitigating both fairness dimensions in the face of censored data.

Graph Neural Networks (GNNs) have demonstrated remarkable capabilities across various domains. Despite the successes of GNN deployment, their utilization often reflects societal biases, which critically hinder their adoption in high-stake decision-making scenarios such as online clinical diagnosis, financial crediting, etc. Numerous efforts have been made to develop fair GNNs but they typically concentrate on either individual or group fairness, overlooking the intricate interplay between the two, resulting in the enhancement of one, usually at the cost of the other. In addition, existing individual fairness approaches using a ranking perspective fail to identify discrimination in the ranking. This paper introduces two innovative notions dealing with individual graph fairness and group-aware individual graph fairness, aiming to more accurately measure individual and group biases. Our Group Equality Individual Fairness (GEIF) framework is designed to achieve individual fairness while equalizing the level of individual fairness among subgroups. Preliminary experiments on several real-world graph datasets demonstrate that GEIF outperforms state-of-the-art methods by a significant margin in terms of individual fairness, group fairness, and utility performance.

There has been increasing concern within the machine learning community and beyond that Artificial Intelligence (AI) faces a bias and discrimination crisis which needs AI fairness with urgency. As many have begun to work on this problem, most existing work depends on the availability of class label for the given fairness definition and algorithm which may not align with real-world usage. In this work, we study an AI fairness problem that stems from the gap between the design of a "fair" model in the lab and its deployment in the real-world. Specifically, we consider defining and mitigating individual unfairness amidst censorship, where the availability of class label is not always guaranteed due to censorship, which is broadly applicable in a diversity of real-world socially sensitive applications. We show that our method is able to quantify and mitigate individual unfairness in the presence of censorship across three benchmark tasks, which provides the first known results on individual fairness guarantee in analysis of censored data.

Collocation of measurements from active and passive satellite sensors refers to the combination of data from two sensors that observe the same geographic area at nearly the same time but with differing spatial resolutions and viewing angles. This collocated data, often known as on-track data, comes with precise product labels from the active sensor but comprises only the pixels located directly on the path of an active satellite’s orbit. As a result, its spatial coverage is quite limited, especially when compared to the vast quantities of off-track data. Handling the abundant and information-dense off-track data is crucial for training machine learning models that can effectively integrate the unique features of this data along with on-track data. However, the sheer volume of off-track data presents significant challenges for these models. To address the challenges of large amounts of unlabeled off-track data in remote sensing applications, we introduce a self-supervised representation learning model with VAE and domain adaptation methods to learn a domain invariant classifier for the on-track and off-track data. The model’s performance is enhanced by pre-training off-track data with VAE generative model using off-track data, to learn a good representation that can be transferred to the down-streaming domain adaptation and classification tasks. The classifier is built on these representations to classify different cloud types in passive sensing data, with the goal of achieving higher accuracy in cloud property retrieval. Extensive quantitative and qualitative evaluation demonstrate our method achieves higher accuracy in cloud property retrieval for off-track remote sensing data.

Algorithmic fairness, the research field of making machine learning (ML) algorithms fair, is an established area in ML. As ML technologies expand their application domains, including ones with high societal impact, it becomes essential to take fairness into consideration during the building of ML systems. Yet, despite its wide range of socially sensitive applications, most work treats the issue of algorithmic bias as an intrinsic property of supervised learning, i.e., the class label is given as a precondition. Unlike prior studies in fairness, we propose an individual fairness measure and a corresponding algorithm that deal with the challenges of uncertainty arising from censorship in class labels, while enforcing similar individuals to be treated similarly from a ranking perspective, free of the Lipschitz condition in the conventional individual fairness definition. We argue that this perspective represents a more realistic model of fairness research for real-world application deployment and show how learning with such a relaxed precondition draws new insights that better explains algorithmic fairness. We conducted experiments on four real-world datasets to evaluate our proposed method compared to other fairness models, demonstrating its superiority in minimizing discrimination while maintaining predictive performance with uncertainty present.

Graph neural networks (GNNs) have demonstrated remarkable success in various real-world applications. However, they often inadvertently inherit and amplify existing societal bias. Most existing approaches for fair GNNs tackle this bias issue by assuming that discrimination solely arises from sensitive attributes such as race or gender, while disregarding the prevalent labeling bias that exists in real-world scenarios. Additionally, prior works attempting to address label bias through counterfactual fairness often fail to consider the veracity of counterfactual samples. This paper aims to bridge these gaps by investigating the identification of authentic counterfactual samples within complex graph structures and proposing strategies for mitigating labeling bias guided by causal analysis. Our proposed learning model, known as Real Fair Counterfactual GNNs (RFCGNN), also goes a step further by considering the learning disparity resulting from imbalanced data distribution across different demographic groups in the graph. Extensive experiments conducted on three real-world datasets and a synthetic dataset demonstrate the effectiveness and practicality of the proposed RFCGNN approach.

In the last decade or so, fairness in AI has received widespread attention, both within the scientific community and the general media. Researchers have made significant progress towards fairer AI, with work exploring everything from statistical definitions of fairness for individual and group fairness to fairness constraints and algorithms for debiasing models and datasets. Given the nascent nature of the field, however, progress in the space has been haphazard. For work in fair-AI to have as much real-world impact as possible, we need to take a step back and gauge the gaps and which research questions need urgent attention. This work analyzes where the field is currently and proposes more focused questions and new research areas within fair AI.

Compared with cloud computing-based data storage, distributed data storage in fog computing is more vulnerable to malicious attacks. So, it is very necessary to provide a secure distributed auditing mechanism with protecting the identity privacy of data owners and controlling the identities of auditors under fog computing-based data storage. In this paper, we propose a dual attribute-based auditing scheme for fog computing-based data dynamic storage. Our auditing scheme can protect the identity privacy of data owners, and provide an attribute-based access control for corresponding audits with a distributed collaborative verification between related fog servers. In our scheme, a data owner can securely upload his divided and blinded file blocks with corresponding block authenticators (related with his attribute set) to related fog servers. To prevent malicious auditors from consuming system resources by abusing audit requests, the data owner can provide an attribute-based access control for corresponding audits, where the data owner specifies the attribute set of corresponding auditors who have the right to check the integrity of related data. Further, a distributed collaborative verification mechanism between related fog servers is constructed to reduce the disadvantages of centralized verification, where the Shamir’s secret-sharing method is used to decompose the picked blinding factor as the shared sub-secrets sent to each fog server respectively. Compared with cloud computing-based data storage, our collaborative verification mechanism can implement distributed auditing consent of stored data between multiple fog servers. Our auditing scheme can further audit out specific suspicious fog servers. Additionally, we provide a dynamic data operation mechanism to efficiently support the updating of users’ data under fog computing-based data storage. Furthermore, related theoretical analysis and experimental evaluation show our scheme is secure and efficient.

5G networks enable emerging latency and bandwidth critical applications like industrial IoT, AR/VR, or autonomous vehicles, in addition to supporting traditional voice and data communications. In 5G infrastructure, Radio Access Networks (RANs) consist of radio base stations that communicate over wireless radio links. The communication, however, is prone to environmental changes like the weather and can suffer from radio link failure and interrupt ongoing services. The impact is severe in the above-mentioned applications. One way to mitigate such service interruption is to proactively predict failures and reconfigure the resource allocation accordingly. Existing works like the supervised ensemble learning-based model do not consider the spatial-temporal correlation between radio communication and weather changes. This paper proposes a communication link failure prediction scheme based on the LSTM-autoencoder that considers the spatial-temporal correlation between radio communication and weather forecast. We implement and evaluate the proposed scheme over a huge volume of real radio and weather data. The results confirm that the proposed scheme significantly outperforms the existing solutions.

Recent works in artificial intelligence fairness attempt to mitigate discrimination by proposing constrained optimization programs that achieve parity for some fairness statistic. Most assume availability of the class label, which is impractical in many real-world applications such as precision medicine, actuarial analysis and recidivism prediction. Here we consider fairness in longitudinal right-censored environments, where the time to event might be unknown, resulting in censorship of the class label and inapplicability of existing fairness studies. We devise applicable fairness measures, propose a debiasing algorithm, and provide necessary theoretical constructs to bridge fairness with and without censorship for these important and socially-sensitive tasks. Our experiments on four censored datasets confirm the utility of our approach.

Presently many searchable encryption schemes have been proposed for cloud and fog computing, which use fog nodes (or fog servers) to partly undertake some computational tasks. However, these related schemes still retain cloud servers to undertake most computational tasks, which result in large communication costs between edge devices and cloud servers. Therefore, in this paper we propose a self-verifiable attribute-based keyword search scheme for distributed data storage (SV-KSDS) in full fog computing, where each decryption operation on the data required by a user must meet the negotiated decryption rule between fog servers. Our SV-KSDS scheme first provides attribute-based distributed data storage among fog servers through the$(w, \sigma)$threshold secret-sharing scheme, where fog servers can provide self-verifiable keyword search and data decryption for terminal users. Compared with the data storage in cloud computing, our scheme extends it to the distributed structure while providing fine-grained access control for distributed data storage through attribute-based encryption. The access control policy of our scheme is constructed on linear secret-sharing scheme, whose security is reduced to the decisional bilinear Diffie-Hellman assumption against chosen-keyword attack and the decisional${q}$-parallel bilinear Diffie-Hellman assumption against chosen-plaintext attack in the standard model. Based on theoretical analysis and practical testing, our SV-KSDS scheme generates less computation and communication costs, which further unloads some computational tasks from terminal users to fog servers so as to reduce computing costs of terminal users.

There has been concern within the artificial intelligence (AI) community and the broader society regarding the potential lack of fairness of AI-based decision-making systems. Surprisingly, there is little work quantifying and guaranteeing fairness in the presence of uncertainty which is prevalent in many socially sensitive applications, ranging from marketing analytics to actuarial analysis and recidivism prediction instruments. To this end, we study a longitudinal censored learning problem subject to fairness constraints, where we require that algorithmic decisions made do not affect certain individuals or social groups negatively in the presence of uncertainty on class label due to censorship. We argue that this formulation has a broader applicability to practical scenarios concerning fairness. We show how the newly devised fairness notions involving censored information and the general framework for fair predictions in the presence of censorship allow us to measure and mitigate discrimination under uncertainty that bridges the gap with real-world applications. Empirical evaluations on real-world discriminated datasets with censorship demonstrate the practicality of our approach.

In this paper, we design and implement a generic medical knowledge based system (MKBS) for identifying diseases from several symptoms. In this system, some important aspects like knowledge bases system, knowledge representation, inference engine have been addressed. The system asks users different questions and inference engines will use the certainty factor to prune out low possible solutions. The proposed disease diagnosis system also uses a graphical user interface (GUI) to facilitate users to interact with the expert system. Our expert system is generic and flexible, which can be integrated with any rule bases system in disease diagnosis.

Deep generative models for graphs have exhibited promising performance in ever-increasing domains such as design of molecules (i.e, graph of atoms) and structure prediction of proteins (i.e., graph of amino acids). Existing work typically focuses on static rather than dynamic graphs, which are actually very important in the applications such as protein folding, molecule reactions, and human mobility. Extending existing deep generative models from static to dynamic graphs is a challenging task, which requires to handle the factorization of static and dynamic characteristics as well as mutual interactions among node and edge patterns. Here, this paper proposes a novel framework of factorized deep generative models to achieve interpretable dynamic graph generation. Various generative models are proposed to characterize conditional independence among node, edge, static, and dynamic factors. Then, variational optimization strategies as well as dynamic graph decoders are proposed based on newly designed factorized variational autoencoders and recurrent graph deconvolutions. Extensive experiments on multiple datasets demonstrate the effectiveness of the proposed models.

Breast cancer is the second leading cause of cancer-related death after lung cancer in women. Early detection of breast cancer in X-ray mammography is believed to have effectively reduced the mortality rate since 1989. However, a relatively high false positive rate and a low specificity in mammography technology still exist. In this work, a computer-aided automatic mammogram analysis system is proposed to process the mammogram images and automatically discriminate them as either normal or cancerous, consisting of three consecutive image processing, feature selection, and image classification stages. In designing the system, the discrete wavelet transforms (Daubechies 2, Daubechies 4, and Biorthogonal 6.8) and the Fourier cosine transform were first used to parse the mammogram images and extract statistical features. Then, an entropy-based feature selection method was implemented to reduce the number of features. Finally, different pattern recognition methods (including the Back-propagation Network, the Linear Discriminant Analysis, and the Naive Bayes Classifier) and a voting classification scheme were employed. The performance of each classification strategy was evaluated for sensitivity, specificity, and accuracy and for general performance using the Receiver Operating Curve. Our method is validated on the dataset from the Eastern Health in Newfoundland and Labrador of Canada. The experimental results demonstrated that the proposed automatic mammogram analysis system could effectively improve the classification performances.

With the advent of data mining and business processes automation, outlier detection has evolved into a major problem attracting significant research in relation to several application domains. Further advances in Global Positioning system, tracking of anomalous events based on data enhances effective decision making and pro-active measures to overcome risks and avoid unwarranted outputs. Significant work has been done in trajectory outlier detection although no singular approach fits all the domains. By including position and collective outliers on the same visualizations will enhance understanding of an outlier behavior. As such, we have leveraged Hidden Markov Method for prediction-based point outlier detection and pattern mining to identify points or segments of outliers in trajectory data.

An ideal safe workplace is described as a place where staffs fulfill responsibilities in a well-organized order, potential hazardous events are being monitored in real-time, as well as the number of accidents and relevant damages are minimized. However, occupational-related death and injury are still increasing and have been highly attended in the last decades due to the lack of comprehensive safety management. A smart safety management system is therefore urgently needed, in which the staffs are instructed to fulfill responsibilities as well as automating risk evaluations and alerting staffs and departments when needed. In this paper, a smart system for safety management in the workplace based on responsibility big data analysis and the internet of things (IoT) are proposed. The real world implementation and assessment demonstrate that the proposed systems have superior accountability performance and improve the responsibility fulfillment through real-time supervision and self-reminder.

Predicting workplace injury using automated techniques opens newer possibilities in evidence-based research. This paper presents our preliminary research in a PhD project in predicting workplace incidents using machine learning algorithms. The analysis on the model performance using several mainstream machine learning algorithms including random forest, k-nearest neighbor and decision tree indicated that the general performance of the decision tree model was found to be statistically higher than that of the other two algorithms.

Effectively detecting the fraudulent invitations is valuable for many online Internet enterprises such as iQIYI to promote good products and improve the user experience. However, it remains highly non-trivial to address, which mainly lies in two challenging data characteristics. First, the invitation graph structure is globally large yet locally small, as a large number of invitations usually occur in a very small local graph, making the global and local consistency difficult to achieve simultaneously. Secondly, the user associations are heterogeneous and diverse, as the user associations are from multiple different data resources, making the effects of multiple user associations difficult to use effectively. To this end, this paper proposes a novel heterogeneous graph neural network HmGnn, to detect fraudulent invitations at iQIYI platform. To the best of our knowledge, this is the first attempt to study fraud invitation detection via graph neural networks. HmGnn handles the homogeneity and heterogeneity of networks simultaneously. Specifically, the proposal constructively introduces links between homogenous mini-graphs based on the similarity of mini-graphs, facilitating the impact of local mini-graphs to the global graph structure. In addition, this paper presents a heterogeneous attention convolution network to accurately optimize the contribution of multiple heterogeneous user associations. Extensive experiments conducted on real-world business data validate the excellent effectiveness and improvement on risk management of our method.

Recognizing human activities from multi-channel time series data collected from wearable sensors has become an important practical application of machine learning. A serious challenge comes from the presence of coherent activities or body movements, such as movements of the head while walking or sitting, since signals representing these movements are mixed and interfere with each other. Basic multi-label classification typically assumes independence within the multiple activities. This is oversimplified and reduces modeling power even when using state-of-the-art deep learning methods. In this paper, we investigate this new problem, which we name “Coherent Human Activity Recognition (Co-HAR)”, that keeps complete conditional dependency between the multiple labels. Additionally, we treat Co-HAR as a dense labelling problem that classifies each sample on a time step with multiple coherent labels to provide high-fidelity and duration-sensitive support to high-precision applications. To explicitly model conditional dependency, a novel condition-aware deep architecture “Conditional-UNet” is developed to allow for multiple dense labeling for Co-HAR. We also contribute a first-of-its-kind Co-HAR dataset for head gesture recognition associated with a user's activity, walking or sitting, to the research community. Extensive experiments on this dataset show that our model outperforms state-of-the-art deep learning methods and achieves up to 92% accuracy on context-based head gesture classification.

Artificial intelligence (AI)-based decision-making systems are employed nowadays in an ever growing number of online as well as offline services-some of great importance. Depending on sophisticated learning algorithms and available data, these systems are increasingly becoming automated and data-driven. However, these systems can impact individuals and communities with ethical or legal consequences. Numerous approaches have therefore been proposed to develop decision-making systems that are discrimination-conscious by-design. However, these methods assume the underlying data distribution is stationary without drift, which is counterfactual in many realworld applications. In addition, their focus has been largely on minimizing discrimination while maximizing prediction performance without necessary flexibility in customizing the tradeoff according to different applications. To this end, we propose a learning algorithm for fair classification that also adapts to evolving data streams and further allows for a flexible control on the degree of accuracy and fairness. The positive results on a set of discriminated and non-stationary data streams demonstrate the effectiveness and flexibility of this approach.

Accountability in the workplace is critically important and remains a challenging problem, especially with respect to workplace safety management. In this paper, we introduce a novel notion, the Internet of Responsibilities, for accountability management. Our method sorts through the list of responsibilities with respect to hazardous positions. The positions are interconnected using directed acyclic graphs (DAGs) indicating the hierarchy of responsibilities in the organization. In addition, the system detects and collects responsibilities, and represents risk areas in terms of the positions of the responsibility nodes. Finally, an automatic reminder and assignment system is used to enforce a strict responsibility control without human intervention. Using blockchain technology, we further extend our system with the capability to store, recover and encrypt responsibility data. We show that through the application of the Internet of Responsibility network model driven by Big Data, enterprise and government agencies can attain a highly secured and safe workplace. Therefore, our model offers a combination of interconnected responsibilities, accountability, monitoring, and safety which is crucial for the protection of employees and the success of organizations.

Automated data-driven decision-making systems are ubiquitous across a wide spread of online as well as offline services. These systems, depend on sophisticated learning algorithms and available data, to optimize the service function for decision support assistance. However, there is a growing concern about the accountability and fairness of the employed models by the fact that often the available historic data is intrinsically discriminatory, i.e., the proportion of members sharing one or more sensitive attributes is higher than the proportion in the population as a whole when receiving positive classification, which leads to a lack of fairness in decision support system. A number of fairness-aware learning methods have been proposed to handle this concern. However, these methods tackle fairness as a static problem and do not take the evolution of the underlying stream population into consideration. In this paper, we introduce a learning mechanism to design a fair classifier for online stream based decision-making. Our learning model, FAHT (Fairness-Aware Hoeffding Tree), is an extension of the well-known Hoeffding Tree algorithm for decision tree induction over streams, that also accounts for fairness. Our experiments show that our algorithm is able to deal with discrimination in streaming environments, while maintaining a moderate predictive performance over the stream.

This work stems from the Italian project H-CIM (Health-Care Intelligent Monitoring), aimed at developing a wearable sensor data streams based home-monitoring system to support self-rehabilitation of elderly outpatients. Different from the pervasive data stream applications, which are always accompanied by the evolution of unstable class concepts, this project requires stable standard and personalized rehabilitation exercises patterns be provided to assess outpatient's self-therapy progress at home. In this designed pipeline, the representation sequences of the personal standard rehabilitation exercises in wearable sensor streams is therefore first benchmarked, then an assessment system which integrates multistage data processing and analyzing is proposed to enable elders to manage their own rehabilitation progress properly. The system proved to be an effective tool for supporting compliance monitoring and personalized self-rehabilitation; it is currently under further development within the Italian project Home-IoT, with the aim to become a more general data stream analytics service, not only devoted to rehabilitation exercises assessment.

A self-organizing map (SOM) is a type of competitive artificial neural network, which projects the high-dimensional input space of the training samples into a low-dimensional space with the topology relations preserved. This makes SOMs supportive of organizing and visualizing complex data sets and have been pervasively used among numerous disciplines with different applications. Notwithstanding its wide applications, the self-organizing map is perplexed by its inherent randomness, which produces dissimilar SOM patterns even when being trained on identical training samples with the same parameters every time, and thus causes usability concerns for other domain practitioners and precludes more potential users from exploring SOM based applications in a broader spectrum. Motivated by this practical concern, we propose a deterministic approach as a supplement to the standard self-organizing map. In accordance with the theoretical design, the experimental results with satellite cloud data demonstrate the effective and efficient organization as well as simplification capabilities of the proposed approach.

This work stems from the project with National Institutes of Health on elderly human posture recognition in their real-world wearable sensor data streams. The problem presented several challenges: near real-time posture recognition, skewed class distribution, time-changing data streams and sensor management. To tackle these challenges, in this project, we present our design integrates with resampling, cost-sensitive classifier and incremental learning for time- changing wearable sensor data streams as well as sensor management for the determination of the least possible number of sensors and their best positions to be deployed on human body.

Survival analysis with high-dimensional data deals with the prediction of patient survival based on their gene expression data and clinical data. A crucial task for the accuracy of survival analysis in this context is to select the features highly correlated with the patient's survival time. Since the information about class labels is hidden, existing feature selection methods in machine learning are not applicable. In contrast to classical statistical methods which address this issue with the Cox score, we propose to tackle this problem by discretizing the survival time of patients into a suitable number of subgroups via silhouettes clustering validity. To cope with patients' censoring, we use “k-nearest neighbor” based on clinical parameters. Feature selection is then accomplished using Fast Correlation-Based Filtering approach from machine learning community. The effectiveness and efficiency of the proposed method are demonstrated through comparisons with classical statistical methods on real-world datasets and simulation datasets.

Human posture recognition has a wide range of applications including elderly care and video surveillance. This paper discusses how to recognize human postures using wearable devices. From real-world data, we analyze the challenges in terms of result performance, recognition efficiency and sensor selection. To deal with the challenges, we present our design with five techniques: i) oversampling and undersampling methods, ii) ensemble learning, iii) sensor selection, iv) stream data classification and v) post-processing techniques. We verify our design and show our findings through extensive experiments on real-world data, which shows our approach can achieve up to 91.5% overall weighted average accuracy for all three postures. We also discuss possible extensions of our work.