Survival analysis models have evolved significantly with deep learning approaches, yet often lack interpretability and meaningful risk stratification capabilities. We present Interpretable Risk Clustering Intelligence for Survival Analysis (IRIS), a novel framework that addresses the critical task of risk clustering while enhancing both input-level and model-body interpretability. Unlike traditional survival models that perform post-hoc risk clustering, IRIS learns to cluster patients into meaningful risk groups directly from data while providing transparent feature importance estimation through feature contribution functions. We validate IRIS on several benchmark datasets, a real-world Alzheimer's disease dataset, and an electronic health record dataset, showing superior performance in risk clustering and predictive reliability with only a modest decrease in time-to-event prediction accuracy compared to state-of-the-art methods. Our results show that IRIS successfully balances the trade-off between interpretability and prediction performance in risk-based survival analysis, offering clinicians actionable insights for treatment planning and resource allocation.

In recent years, *task arithmetic* has garnered increasing attention. This approach edits pre-trained models directly in weight space by combining the fine-tuned weights of various tasks into a *unified model*. Its efficiency and cost-effectiveness stem from its training-free combination, contrasting with traditional methods that require model training on large datasets for multiple tasks. However, applying such a unified model to individual tasks can lead to interference from other tasks (lack of *weight disentanglement*). To address this issue, Neural Tangent Kernel (NTK) linearization has been employed to leverage a ''kernel behavior'', facilitating weight disentanglement and mitigating adverse effects from unrelated tasks. Despite its benefits, NTK linearization presents drawbacks, including doubled training costs, as well as reduced performance of individual models. To tackle this problem, we propose a simple yet effective and efficient method that is to finetune the attention modules only in the Transformer. Our study reveals that the attention modules exhibit kernel behavior, and fine-tuning the attention modules only significantly improves weight disentanglement. To further understand how our method improves the weight disentanglement of task arithmetic, we present a comprehensive study of task arithmetic by differentiating the role of the representation module and task-specific module. In particular, we find that the representation module plays an important role in improving weight disentanglement whereas the task-specific modules such as the classification heads can degenerate the weight disentanglement performance.

One of the key technologies for the success of Large Language Models (LLMs) is preference alignment. However, a notable side effect of preference alignment is poor calibration: while the pre-trained models are typically well-calibrated, LLMs tend to become poorly calibrated after alignment with human preferences. In this paper, we investigate why preference alignment affects calibration and how to address this issue. For the first question, we observe that the preference collapse issue in alignment undesirably generalizes to the calibration scenario, causing LLMs to exhibit overconfidence and poor calibration. To address this, we demonstrate the importance of fine-tuning with domain-specific knowledge to alleviate the overconfidence issue. To further analyze whether this affects the model’s performance, we categorize models into two regimes: calibratable and non-calibratable, defined by bounds of Expected Calibration Error (ECE). In the calibratable regime, we propose a calibration-aware fine-tuning approach to achieve proper calibration without compromising LLMs’ performance. However, as models are further fine-tuned for better performance, they enter the non-calibratable regime. For this case, we develop an EM-algorithm-based ECE regularization for the fine-tuning loss to maintain low calibration error. Extensive experiments validate the effectiveness of the proposed methods.

We introduce MentalChat16K, an English benchmark dataset combining a synthetic mental health counseling dataset and a dataset of anonymized transcripts from interventions between Behavioral Health Coaches and Caregivers of patients in palliative or hospice care. Covering a diverse range of conditions like depression, anxiety, and grief, this curated dataset is designed to facilitate the development and evaluation of large language models for conversational mental health assistance. By providing a high-quality resource tailored to this critical domain, MentalChat16K aims to advance research on empathetic, personalized AI solutions to improve access to mental health support services. The dataset prioritizes patient privacy, ethical considerations, and responsible data usage. MentalChat16K presents a valuable opportunity for the research community to innovate AI technologies that can positively impact mental well-being. The dataset is available at https://huggingface.co/datasets/ShenLab/MentalChat16K and the code and documentation are hosted on GitHub at https://github.com/PennShenLab/MentalChat16K.

Online bilevel optimization (OBO) is a powerful framework for machine learning problems where both outer and inner objectives evolve over time, requiring dynamic updates. Current OBO approaches rely on deterministic \textit{window-smoothed} regret minimization, which may not accurately reflect system performance when functions change rapidly. In this work, we introduce a novel search direction and show that both first- and zeroth-order (ZO) stochastic OBO algorithms leveraging this direction achieve sublinear {stochastic bilevel regret without window smoothing}. Beyond these guarantees, our framework enhances efficiency by: (i) reducing oracle dependence in hypergradient estimation, (ii) updating inner and outer variables alongside the linear system solution, and (iii) employing ZO-based estimation of Hessians, Jacobians, and gradients. Experiments on online parametric loss tuning and black-box adversarial attacks validate our approach.

Tensor Canonical Correlation Analysis (TCCA) is a commonly employed statistical method utilized to examine linear associations between two sets of tensor datasets. However, the existing TCCA models fail to adequately address the heterogeneity present in real-world tensor data, such as brain imaging data collected from diverse groups characterized by factors like sex and race. Consequently, these models may yield biased outcomes. In order to surmount this constraint, we propose a novel approach called Multi-Group TCCA (MG-TCCA), which enables the joint analysis of multiple subgroups. By incorporating a dual sparsity structure and a block coordinate ascent algorithm, our MG-TCCA method effectively addresses heterogeneity and leverages information across different groups to identify consistent signals. This novel approach facilitates the quantification of shared and individual structures, reduces data dimensionality, and enables visual exploration. To empirically validate our approach, we conduct a study focused on investigating correlations between two brain positron emission tomography (PET) modalities (AV-45 and FDG) within an Alzheimer's disease (AD) cohort. Our results demonstrate that MG-TCCA surpasses traditional TCCA and Sparse TCCA (STCCA) in identifying sex-specific cross-modality imaging correlations. This heightened performance of MG-TCCA provides valuable insights for the characterization of multimodal imaging biomarkers in AD.

A neural network (NN) with the widely-used ReLU activation has been shown to partition the sample space into many convex polytopes for prediction. However, the parametric way a NN and other machine learning models use to partition the space has imperfections, e.g., the compromised interpretability for complex models, the inflexibility in decision boundary construction due to the generic character of the model, and the risk of being trapped into shortcut solutions. In contrast, although the nonparameterized models can adorably avoid or downplay these issues, they are usually insufficiently powerful either due to over-simplification or the failure to accommodate the manifold structures of data. In this context, we first propose a new type of machine learning models referred to as Manifoldron that directly derives decision boundaries from data and partitions the space via manifold structure discovery. Then, we systematically analyze the key characteristics of the Manifoldron such as manifold characterization capability and its link to NNs. The experimental results on four synthetic examples, 20 public benchmark datasets, and one real-world application demonstrate that the proposed Manifoldron performs competitively compared to the mainstream machine learning models. We have shared our code in https://github.com/wdayang/Manifoldron for free download and evaluation.

This paper introduces \textit{online bilevel optimization} in which a sequence of time-varying bilevel problems is revealed one after the other. We extend the known regret bounds for single-level online algorithms to the bilevel setting. Specifically, we provide new notions of \textit{bilevel regret}, develop an online alternating time-averaged gradient method that is capable of leveraging smoothness, and give regret bounds in terms of the path-length of the inner and outer minimizer sequences.

techniques that often evade existing detection methods. To address this challenge, we present a novel semantic-enhanced framework for detecting LLM-generated text (SEFD) that leverages a retrieval-based mechanism to fully utilize text semantics. Our framework improves upon existing detection methods by systematically integrating retrieval-based techniques with traditional detectors, employing a carefully curated retrieval mechanism that strikes a balance between comprehensive coverage and computational efficiency. We showcase the effectiveness of our approach in sequential text scenarios common in real-world applications, such as online forums and Q&A platforms. Through comprehensive experiments across various LLM-generated texts and detection methods, we demonstrate that our framework substantially enhances detection accuracy in paraphrasing scenarios while maintaining robustness for standard LLM-generated content. This work contributes significantly to ongoing efforts to safeguard information integrity in an era where AI-generated content is increasingly prevalent.

This paper examines the issue of fairness in the estimation of graphical models (GMs), particularly Gaussian, Covariance, and Ising models. These models play a vital role in understanding complex relationships in high-dimensional data. However, standard GMs can result in biased outcomes, especially when the underlying data involves sensitive characteristics or protected groups. To address this, we introduce a comprehensive framework designed to reduce bias in the estimation of GMs related to protected attributes. Our approach involves the integration of the pairwise graph disparity error and a tailored loss function into a nonsmooth multi-objective optimization problem, striving to achieve fairness across different sensitive groups while maintaining the effectiveness of the GMs. Experimental evaluations on synthetic and real-world datasets demonstrate that our framework effectively mitigates bias without undermining GMs' performance.

This paper investigates fairness and bias in Canonical Correlation Analysis (CCA), a widely used statistical technique for examining the relationship between two sets of variables. We present a framework that alleviates unfairness by minimizing the correlation disparity error associated with protected attributes. Our approach enables CCA to learn global projection matrices from all data points while ensuring that these matrices yield comparable correlation levels to group-specific projection matrices. Experimental evaluation on both synthetic and real-world datasets demonstrates the efficacy of our method in reducing correlation disparity error without compromising CCA accuracy.

We present a novel Bayesian-based optimization framework that addresses the challenge of generalization in overparameterized models when dealing with imbalanced subgroups and limited samples per subgroup. Our proposed tri-level optimization framework utilizes local predictors, which are trained on a small amount of data, as well as a fair and class-balanced predictor at the middle and lower levels. To effectively overcome saddle points for minority classes, our lower-level formulation incorporates sharpness-aware minimization. Meanwhile, at the upper level, the framework dynamically adjusts the loss function based on validation loss, ensuring a close alignment between the global predictor and local predictors. Theoretical analysis demonstrates the framework’s ability to enhance classification and fairness generalization, potentially resulting in improvements in the generalization bound. Empirical results validate the superior performance of our tri-level framework compared to existing state-of-the-art approaches. The source code can be found at \url{https://github.com/PennShenLab/FACIMS}.

This paper investigates a new online learning problem with doubly-streaming data, where the data streams are described by feature spaces that constantly evolve, with new features emerging and old features fading away. A plausible idea to deal with such data streams is to establish a relationship between the old and new feature spaces, so that an online learner can leverage the knowledge learned from the old features to better the learning performance on the new features. Unfortunately, this idea does not scale up to high-dimensional multimedia data with complex feature interplay, which suffers a tradeoff between onlineness, which biases shallow learners, and expressiveness, which requires deep models. Motivated by this, we propose a novel OLD3S paradigm, where a shared latent subspace is discovered to summarize information from the old and new feature spaces, building an intermediate feature mapping relationship. A key trait of OLD3S is to treat the model capacity as a learnable semantics, aiming to yield optimal model depth and parameters jointly in accordance with the complexity and non-linearity of the input data streams in an online fashion. Both theoretical analysis and empirical studies substantiate the viability and effectiveness of our proposed approach. The code is available online at https://github.com/X1aoLian/OLD3S.