There has been increasing research attention on community detection in directed and bipartite networks. However, these studies often fail to consider the popularity of nodes in different communities, which is a common phenomenon in real-world networks. To address this issue, we propose a new probabilistic framework called the Two-Way Node Popularity Model (TNPM). The TNPM also accommodates edges from different distributions within a general sub-Gaussian family. We introduce the Delete-One-Method (DOM) for model fitting and community structure identification, and provide a comprehensive theoretical analysis with novel technical skills dealing with sub-Gaussian generalization. Additionally, we propose the Two-Stage Divided Cosine Algorithm (TSDC) to handle large-scale networks more efficiently. Our proposed methods offer multi-folded advantages in terms of estimation accuracy and computational efficiency, as demonstrated through extensive numerical studies. We apply our methods to two real-world applications, uncovering interesting findings.

In offline reinforcement learning, it is necessary to manage out-of-distribution actions to prevent overestimation of value functions. One class of methods, the policy-regularized method, addresses this problem by constraining the target policy to stay close to the behavior policy. Although several approaches suggest representing the behavior policy as an expressive diffusion model to boost performance, it remains unclear how to regularize the target policy given a diffusion-modeled behavior sampler. In this paper, we propose Diffusion Actor-Critic (DAC) that formulates the Kullback-Leibler (KL) constraint policy iteration as a diffusion noise regression problem, enabling direct representation of target policies as diffusion models. Our approach follows the actor-critic learning paradigm in which we alternatively train a diffusion-modeled target policy and a critic network. The actor training loss includes a soft Q-guidance term from the Q-gradient. The soft Q-guidance is based on the theoretical solution of the KL constraint policy iteration, which prevents the learned policy from taking out-of-distribution actions. We demonstrate that such diffusion-based policy constraint, along with the coupling of the lower confidence bound of the Q-ensemble as value targets, not only preserves the multi-modality of target policies, but also contributes to stable convergence and strong performance in DAC. Our approach is evaluated on D4RL benchmarks and outperforms the state-of-the-art in nearly all environments.

The ever-increasing fine-tuning cost of large-scale pre-trained models gives rise to the importance of dataset pruning, which aims to reduce dataset size while maintaining task performance. However, existing dataset pruning methods require training on the entire dataset, which is impractical for large-scale pre-trained models. In this paper, we propose a straightforward, novel, and training-free hardness score named Distorting-based Learning Complexity (DLC), to identify informative images and instructions from the downstream dataset efficiently. Our method is motivated by the observation that easy samples learned faster can also be learned with fewer parameters. Specifically, we define the Learning Complexity to quantify sample hardness and utilize a lightweight weights masking process for fast estimation, instead of the costly SGD optimization. Based on DLC, we further design a flexible under-sampling strategy with randomness (dubbed FlexRand), replacing the top-K strategy, to alleviate the severe subset distribution shift. Extensive experiments with downstream image and instructions dataset pruning benchmarks demonstrate the effectiveness and efficiency of the proposed approach. In the images pruning benchmark, DLC significantly reduces the pruning time by 35$\times$ while establishing state-of-the-art performance with FlexRand.

Knowledge distillation (KD) is a promising yet challenging model compression approach that transmits rich learning representations from robust but resource-demanding teacher models to efficient student models. Previous methods for image super-resolution (SR) are often tailored to specific teacher-student architectures, limiting their potential for improvement and hindering broader applications. This work presents a novel KD framework for SR models, the multi-granularity Mixture of Priors Knowledge Distillation (MiPKD), which can be universally applied to a wide range of architectures at both feature and block levels. The teacher’s knowledge is effectively integrated with the student's feature via the Feature Prior Mixer, and the reconstructed feature propagates dynamically in the training phase with the Block Prior Mixer. Extensive experiments illustrate the significance of the proposed MiPKD technique.

Knowledge distillation (KD) compresses deep neural networks by transferring task-related knowledge from cumbersome pre-trained teacher models to more compact student models. However, vanilla KD for image super-resolution (SR) networks yields only limited improvements due to the inherent nature of SR tasks, where the outputs of teacher models are noisy approximations of high-quality label images. In this work, we show that the potential of vanilla KD has been underestimated and demonstrate that the ingenious application of data augmentation methods can close the gap between it and more complex, well-designed methods. Unlike conventional training processes typically applying image augmentations simultaneously to both low-quality inputs and high-quality labels, we propose AugKD utilizing unpaired data augmentations to 1) generate auxiliary distillation samples and 2) impose label consistency regularization. Comprehensive experiments show that the AugKD significantly outperforms existing state-of-the-art KD methods across a range of SR tasks.

In the era of large language models (LLMs), detecting pretraining data has been increasingly important due to concerns about fair evaluation and ethical risks. Current methods differentiate members and non-members by designing scoring functions, like Perplexity and Min-k%. However, the diversity and complexity of training data magnifies the difficulty of distinguishing, leading to suboptimal performance in detecting pretraining data. In this paper, we first explore the benefits of unseen data, which can be easily collected after the release of the LLM. We find that the perplexities of LLMs shift differently for members and non-members, after fine-tuning with a small amount of previously unseen data. In light of this, we introduce a novel and effective method termed Fine-tuned Score Deviation (FSD), which improves the performance of current scoring functions for pretraining data detection. In particular, we propose to measure the deviation distance of current scores after fine-tuning on a small amount of unseen data within the same domain. In effect, using a few unseen data can largely decrease the scores of all non-members, leading to a larger deviation distance than members. Extensive experiments demonstrate the effectiveness of our method, significantly improving the AUC score on common benchmark datasets across various models.

Conformal prediction is a popular framework of uncertainty quantification that constructs prediction sets with coverage guarantees. To uphold the exchangeability assumption, many conformal prediction methods necessitate an additional hold-out set for parameter tuning. Yet, the impact of violating this principle on coverage remains underexplored, making it ambiguous in practical applications. In this work, we empirically find that the tuning bias - the coverage gap introduced by leveraging the same dataset for tuning and calibration, is negligible for simple parameter tuning in many conformal prediction methods. In particular, we observe the scaling law of the tuning bias: this bias increases with parameter space complexity and decreases with calibration set size. Formally, we establish a theoretical framework to quantify the tuning bias and provide rigorous proof for the scaling law of the tuning bias by deriving its upper bound. In the end, we discuss how to reduce the tuning bias, guided by the theories we developed.

Molecular docking is a fundamental technique in structure-based drug discovery, playing a critical role in predicting the binding poses of protein-ligand complexes. While traditional docking methods are generally reliable, they are often computationally expensive. Recent deep learning (DL) approaches have substantially accelerated docking and improved prediction accuracy; however, they frequently generate conformations that lack physical plausibility due to insufficient integration of physical priors. To deal with these challenges, we propose ForceFM, a novel force-guided model that integrates a force-guided network into the generation process, steering ligand poses toward low-energy, physically realistic conformations. Force guidance also halves inference cost compared with the unguided approaches. Importantly, replacing the guiding potential with diverse energy functions-including Vina, Glide, Gnina, and Confscore-preserves or improves performance, underscoring the method's generality and robustness. These results highlight ForceFM's ability to set new standards in docking accuracy and physical consistency, surpassing the limitations of previous methods. Code is available at \url{https://github.com/Guhuary/ForceFM}.

Conformal prediction (CP) is a powerful statistical framework that generates prediction intervals or sets with guaranteed coverage probability. While CP algorithms have evolved beyond traditional classifiers and regressors to sophisticated deep learning models like deep neural networks (DNNs), graph neural networks (GNNs), and large language models (LLMs), existing CP libraries often lack the model support and scalability for large-scale deep learning (DL) scenarios. This paper introduces TorchCP, a PyTorch-native library designed to integrate state-of-the-art CP algorithms into DL techniques, including DNN-based classifiers/regressors, GNNs, and LLMs. Released under the LGPL-3.0 license, TorchCP comprises about 16k lines of code, validated with 100% unit test coverage and detailed documentation. Notably, TorchCP enables CP-specific training algorithms, online prediction, and GPU-accelerated batch processing, achieving up to 90% reduction in inference time on large datasets. With its low-coupling design, comprehensive suite of advanced methods, and full GPU scalability, TorchCP empowers researchers and practitioners to enhance uncertainty quantification across cutting-edge applications.

Industrial scene text detection is challenging due to cluttered backgrounds, rust occlusions, and arbitrary orientations. We introduce ISTD-DLA, a dynamic local-aware aggregation network for industrial text detection. The framework integrates two synergistic components: (i) a dynamic local-aware feature learner that fuses shape-aware and Bayar convolutions to enrich fine-grained structural cues; and (ii) a local feature aggregation module that forms superpixel-based proposals and uses cross-attention to iteratively exchange context between pixels and superpixels, enabling more precise localization in complex scenes. To maintain efficiency, we prune implicit-mapping submodules at inference, reducing complexity without degrading accuracy. On the MPSC benchmark, ISTD-DLA attains an F-measure of 86.2% at 32 FPS, demonstrating a favorable accuracy–efficiency trade-off and robust practicality for industrial applications.

Tabular data is widely utilized in a wide range of real-world applications. The challenge of few-shot learning with tabular data stands as a crucial problem in both industry and academia, due to the high cost or even impossibility of annotating additional samples. However, the inherent heterogeneity of tabular features, combined with the scarcity of labeled data, presents a significant challenge in tabular few-shot classification. In this paper, we propose a novel approach named Diffusion-based Representation with Random Distance matching (D2R2) for tabular few-shot learning. D2R2 leverages the powerful expression ability of diffusion models to extract essential semantic knowledge crucial for denoising process. This semantic knowledge proves beneficial in few-shot downstream tasks. During the training process of our designed diffusion model, we introduce a random distance matching to preserve distance information in the embeddings, thereby improving effectiveness for classification. During the classification stage, we introduce an instance-wise iterative prototype scheme to improve performance by accommodating the multimodality of embeddings and increasing clustering robustness. Our experiments reveal the significant efficacy of D2R2 across various tabular few-shot learning benchmarks, demonstrating its state-of-the-art performance in this field.

``Distribution shift'' is the primary obstacle to the success of offline reinforcement learning. As a learning policy may take actions beyond the knowledge of the behavior policy (referred to as Out-of-Distribution (OOD) actions), the Q-values of these OOD actions can be easily overestimated. Consequently, the learning policy becomes biasedly optimized using the incorrect recovered Q-value function. One commonly used idea to avoid the overestimation of Q-value is to make a pessimistic adjustment. Our key idea is to penalize the Q-values of OOD actions that correspond to high uncertainty. In this work, we propose Q-Distribution guided Q-learning (QDQ) which pessimistic Q-value on OOD regions based on uncertainty estimation. The uncertainty measure is based on the conditional Q-value distribution, which is learned via a high-fidelity and efficient consistency model. On the other hand, to avoid the overly conservative problem, we introduce an uncertainty-aware optimization objective to update the Q-value function. The proposed QDQ demonstrates solid theoretical guarantees for the accuracy of Q-value distribution learning and uncertainty measurement, as well as the performance of the learning policy. QDQ consistently exhibits strong performance in the D4RL benchmark and shows significant improvements for many tasks. Our code can be found at <code link>.

MOTIVATION: Effective drug delivery systems are paramount in enhancing pharmaceutical outcomes, particularly through the use of cell-penetrating peptides (CPPs). These peptides are gaining prominence due to their ability to penetrate eukaryotic cells efficiently without inflicting significant damage to the cellular membrane, thereby ensuring optimal drug delivery. However, the identification and characterization of CPPs remain a challenge due to the laborious and time-consuming nature of conventional methods, despite advances in proteomics. Current computational models, however, are predominantly tailored for balanced datasets, an approach that falls short in real-world applications characterized by a scarcity of known positive CPP instances. RESULTS: To navigate this shortfall, we introduce PractiCPP, a novel deep-learning framework tailored for CPP prediction in highly imbalanced data scenarios. Uniquely designed with the integration of hard negative sampling and a sophisticated feature extraction and prediction module, PractiCPP facilitates an intricate understanding and learning from imbalanced data. Our extensive computational validations highlight PractiCPP's exceptional ability to outperform existing state-of-the-art methods, demonstrating remarkable accuracy, even in datasets with an extreme positive-to-negative ratio of 1:1000. Furthermore, through methodical embedding visualizations, we have established that models trained on balanced datasets are not conducive to practical, large-scale CPP identification, as they do not accurately reflect real-world complexities. In summary, PractiCPP potentially offers new perspectives in CPP prediction methodologies. Its design and validation, informed by real-world dataset constraints, suggest its utility as a valuable tool in supporting the acceleration of drug delivery advancements. AVAILABILITY AND IMPLEMENTATION: The source code of PractiCPP is available on Figshare at https://doi.org/10.6084/m9.figshare.25053878.v1.

Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points. Existing methods for addressing this issue either control policy to exclude the OOD action or make the $Q$ function pessimistic. However, these methods can be overly conservative or fail to identify OOD areas accurately. To overcome this problem, we propose a Constrained Policy optimization with Explicit Behavior density (CPED) method that utilizes a flow-GAN model to explicitly estimate the density of behavior policy. By estimating the explicit density, CPED can accurately identify the safe region and enable exploration within the region, resulting in less conservative learning policies. We further provide theoretical results for both the flow-GAN estimator and performance guarantee for CPED by showing that CPED can find the optimal $Q$-function value. Empirically, CPED outperforms existing alternatives on various standard offline reinforcement learning tasks, yielding higher expected returns.

Gaussian process regression is widely used in many fields, for example, machine learning, reinforcement learning and uncertainty quantification. One key component of Gaussian process regression is the unknown correlation function, which needs to be specified. In this paper, we investigate what would happen if the correlation function is misspecified. We derive upper and lower error bounds for Gaussian process regression with possibly misspecified correlation functions. We find that when the sampling scheme is quasi-uniform, the optimal convergence rate can be attained even if the smoothness of the imposed correlation function exceeds that of the true correlation function. We also obtain convergence rates of kernel ridge regression with misspecified kernel function, where the underlying truth is a deterministic function. Our study reveals a close connection between the convergence rates of Gaussian process regression and kernel ridge regression, which is aligned with the relationship between sample paths of Gaussian process and the corresponding reproducing kernel Hilbert space. This work establishes a bridge between Bayesian learning based on Gaussian process and frequentist kernel methods with reproducing kernel Hilbert space.

MOTIVATION: Nuclear magnetic resonance (NMR) has been widely used as a powerful tool to determine the 3D structures of proteins in vivo. However, the post-spectra processing stage of NMR structure determination usually involves a tremendous amount of time and expert knowledge, which includes peak picking, chemical shift assignment and structure calculation steps. Detecting accurate peaks from the NMR spectra is a prerequisite for all following steps, and thus remains a key problem in automatic NMR structure determination. RESULTS: We introduce WaVPeak, a fully automatic peak detection method. WaVPeak first smoothes the given NMR spectrum by wavelets. The peaks are then identified as the local maxima. The false positive peaks are filtered out efficiently by considering the volume of the peaks. WaVPeak has two major advantages over the state-of-the-art peak-picking methods. First, through wavelet-based smoothing, WaVPeak does not eliminate any data point in the spectra. Therefore, WaVPeak is able to detect weak peaks that are embedded in the noise level. NMR spectroscopists need the most help isolating these weak peaks. Second, WaVPeak estimates the volume of the peaks to filter the false positives. This is more reliable than intensity-based filters that are widely used in existing methods. We evaluate the performance of WaVPeak on the benchmark set proposed by PICKY (Alipanahi et al., 2009), one of the most accurate methods in the literature. The dataset comprises 32 2D and 3D spectra from eight different proteins. Experimental results demonstrate that WaVPeak achieves an average of 96%, 91%, 88%, 76% and 85% recall on (15)N-HSQC, HNCO, HNCA, HNCACB and CBCA(CO)NH, respectively. When the same number of peaks are considered, WaVPeak significantly outperforms PICKY. AVAILABILITY: WaVPeak is an open source program. The source code and two test spectra of WaVPeak are available at http://faculty.kaust.edu.sa/sites/xingao/Pages/Publications.aspx. The online server is under construction. CONTACT: [email protected]; [email protected]; [email protected]; [email protected].