Federated graph learning (FGL) has emerged as a promising paradigm for collaborative machine learning, enabling multiple parties to jointly train models while preserving the privacy of raw graph data. However, existing FGL methods often overlook the model-centric heterogeneous FGL (MHtFGL) problem, which arises in real-world applications, such as the aggregation of models from different companies with varying scales and architectures. MHtFGL presents an additional challenge: the diversity of client model architectures hampers common learning and integration of graph representations. To address this issue, we propose the Federated Graph Knowledge Collaboration (FedGKC) framework, comprising two key components: Client-side Self-Mutual Knowledge Distillation, which fosters effective knowledge sharing among clients through copilot models; and Server-side Knowledge-Aware Model Aggregation, which enhances model integration by accounting for the knowledge acquired by clients. Experiments on eight benchmark datasets demonstrate that FedGKC achieves an average accuracy improvement of 3.74% over baseline models in MHtFGL scenarios, while also maintaining excellent performance in homogeneous settings.
With the advent of the COVID-19 pandemic, ultrasound imaging has emerged as a promising technique for COVID-19 detection, due to its non-invasive nature, affordability, and portability. In response, researchers have focused on developing AI-based scoring systems to provide real-time diagnostic support. However, the limited size and lack of proper annotation in publicly available ultrasound datasets pose significant challenges for training a robust AI model. This paper proposes MeDiVLAD, a novel pipeline to address the above issue for multi-level lung-ultrasound (LUS) severity scoring. In particular, we leverage self-knowledge distillation to pretrain a vision transformer (ViT) without label and aggregate frame-level features via dual-level VLAD aggregation. We show that with minimal finetuning, MeDiVLAD outperforms conventional fully-supervised methods in both frame- and video-level scoring, while offering classification reasoning with exceptional quality. This superior performance enables key applications such as the automatic identification of critical lung pathology areas and provides a robust solution for broader medical video classification tasks.
In this report, we present DNA 1.0 8B Instruct, a state-of-the-art bilingual language model optimized for Korean and English language tasks. By applying continual pre-training (CPT) with high-quality Korean datasets to Llama 3.1 8B and subsequent supervised fine-tuning (SFT), we create an instruction-following model with enhanced Korean language capabilities. This model is then merged with Llama 3.1 8B Instruct via spherical linear interpolation (SLERP) and undergoes further optimization through direct preference optimization (DPO) and knowledge distillation (KD). DNA 1.0 8B Instruct achieves state-of-the-art results on Korean-specific tasks, including KMMLU (53.26%), KoBEST (83.40%), and BELEBELE (57.99%), while maintaining strong English capabilities on MMLU (66.64%), MMLU-Pro (43.05%) and GSM8K (80.52%). As an open model, DNA 1.0 8B Instruct represents a significant advancement in bilingual language modeling. As an open model, DNA 1.0 8B Instruct is freely available through https://huggingface.co/dnotitia/Llama-DNA-1.0-8B-Instruct . For commercial licensing inquiries or feedback, please contact us at https://www.dnotitia.com/contact/post-form
Self-supervised speech representation models, particularly those leveraging transformer architectures, have demonstrated remarkable performance across various tasks such as speech recognition, speaker identification, and emotion detection. Recent studies on transformer models revealed a high redundancy between layers and the potential for significant pruning, which we will investigate here for transformer-based speech representation models. We perform a detailed analysis of layer similarity in speech representation models using three similarity metrics: cosine similarity, centered kernel alignment, and mutual nearest-neighbor alignment. Our findings reveal a block-like structure of high similarity, suggesting two main processing steps and significant redundancy of layers. We demonstrate the effectiveness of pruning transformer-based speech representation models without the need for post-training, achieving up to 40% reduction in transformer layers while maintaining over 95% of the model's predictive capacity. Furthermore, we employ a knowledge distillation method to substitute the entire transformer stack with mimicking layers, reducing the network size 95-98% and the inference time by up to 94%. This substantial decrease in computational load occurs without considerable performance loss, suggesting that the transformer stack is almost completely redundant for downstream applications of speech representation models.
Chain-of-Thought (CoT) reasoning in smaller language models is a challenging natural language process problem yet highly desirable in many real-life applications. Existing CoT knowledge distillation methods often suffer from overly conservative memorization in smaller LLMs, leading to low generalization confidence. As fully preserving the CoT ability of teacher model is impossible, we hypothesize that adversarial CoT fine-tuning is crucial for developing smaller LLM with robust CoT generalization. To this end, we propose \textit{PRompt-Assisted Domain-Adversarial fine-tuning} (PRADA), a principled fine-tuning framework that integrates diverse CoT domains. Specifically, PRADA pioneers two CoT improvements in smaller LLM: (1) Recovering the domain-invariant feature insight which typically lost during distillation with domain adversarial fine-tuning; (2) Enhancing the domain adaptability of CoT prompt engineering by employing domain-adversarial approaches. We theoretically demonstrate the effectiveness of our approach and empirically show that it significantly outperforms the state of the arts in a wide range of tasks. Moreover, our empirical findings reveal that the smaller LLM, when leveraging PRADA, aligns closely with domain knowledge, thereby improving the explainability of our approach.
Transformer-based encoder-decoder models have achieved remarkable success in image-to-image transfer tasks, particularly in image restoration. However, their high computational complexity-manifested in elevated FLOPs and parameter counts-limits their application in real-world scenarios. Existing knowledge distillation methods in image restoration typically employ lightweight student models that directly mimic the intermediate features and reconstruction results of the teacher, overlooking the implicit attention relationships between them. To address this, we propose a Soft Knowledge Distillation (SKD) strategy that incorporates a Multi-dimensional Cross-net Attention (MCA) mechanism for compressing image restoration models. This mechanism facilitates interaction between the student and teacher across both channel and spatial dimensions, enabling the student to implicitly learn the attention matrices. Additionally, we employ a Gaussian kernel function to measure the distance between student and teacher features in kernel space, ensuring stable and efficient feature learning. To further enhance the quality of reconstructed images, we replace the commonly used L1 or KL divergence loss with a contrastive learning loss at the image level. Experiments on three tasks-image deraining, deblurring, and denoising-demonstrate that our SKD strategy significantly reduces computational complexity while maintaining strong image restoration capabilities.
Model compression through knowledge distillation has seen extensive application in classification and segmentation tasks. However, its potential in image-to-image translation, particularly in image restoration, remains underexplored. To address this gap, we propose a Simultaneous Learning Knowledge Distillation (SLKD) framework tailored for model compression in image restoration tasks. SLKD employs a dual-teacher, single-student architecture with two distinct learning strategies: Degradation Removal Learning (DRL) and Image Reconstruction Learning (IRL), simultaneously. In DRL, the student encoder learns from Teacher A to focus on removing degradation factors, guided by a novel BRISQUE extractor. In IRL, the student decoder learns from Teacher B to reconstruct clean images, with the assistance of a proposed PIQE extractor. These strategies enable the student to learn from degraded and clean images simultaneously, ensuring high-quality compression of image restoration models. Experimental results across five datasets and three tasks demonstrate that SLKD achieves substantial reductions in FLOPs and parameters, exceeding 80\%, while maintaining strong image restoration performance.
Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot fault data is challenging, and adding new fault classes often demands costly model retraining. Moreover, incremental training of existing methods risks catastrophic forgetting, and severe class imbalance can bias the model's decisions toward normal classes. To tackle these issues, we introduce a Supervised Contrastive knowledge distiLlation for class Incremental Fault Diagnosis (SCLIFD) framework proposing supervised contrastive knowledge distillation for improved representation learning capability and less forgetting, a novel prioritized exemplar selection method for sample replay to alleviate catastrophic forgetting, and the Random Forest Classifier to address the class imbalance. Extensive experimentation on simulated and real-world industrial datasets across various imbalance ratios demonstrates the superiority of SCLIFD over existing approaches. Our code can be found at https://github.com/Zhang-Henry/SCLIFD_TII.
Data scarcity in pharmaceutical research has led to reliance on labour-intensive trial-and-error approaches for development rather than data-driven methods. While Machine Learning offers a solution, existing datasets are often small and noisy, limiting their utility. To address this, we developed a Variationally Encoded Conditional Tabular Generative Adversarial Network (VECT-GAN), a novel generative model specifically designed for augmenting small, noisy datasets. We introduce a pipeline where data is augmented before regression model development and demonstrate that this consistently and significantly improves performance over other state-of-the-art tabular generative models. We apply this pipeline across six pharmaceutical datasets, and highlight its real-world applicability by developing novel polymers with medically desirable mucoadhesive properties, which we made and experimentally characterised. Additionally, we pre-train the model on the ChEMBL database of drug-like molecules, leveraging knowledge distillation to enhance its generalisability, making it readily available for use on pharmaceutical datasets containing small molecules, an extremely common pharmaceutical task. We demonstrate the power of synthetic data for regularising small tabular datasets, highlighting its potential to become standard practice in pharmaceutical model development, and make our method, including VECT-GAN pre-trained on ChEMBL available as a pip package.
Knowledge distillation (KD) involves transferring knowledge from a pre-trained heavy teacher model to a lighter student model, thereby reducing the inference cost while maintaining comparable effectiveness. Prior KD techniques typically assume homogeneity between the teacher and student models. However, as technology advances, a wide variety of architectures have emerged, ranging from initial Convolutional Neural Networks (CNNs) to Vision Transformers (ViTs), and Multi-Level Perceptrons (MLPs). Consequently, developing a universal KD framework compatible with any architecture has become an important research topic. In this paper, we introduce a feature-based one-for-all (FOFA) KD framework to enable feature distillation across diverse architecture. Our framework comprises two key components. First, we design prompt tuning blocks that incorporate student feedback, allowing teacher features to adapt to the student model's learning process. Second, we propose region-aware attention to mitigate the view mismatch problem between heterogeneous architecture. By leveraging these two modules, effective distillation of intermediate features can be achieved across heterogeneous architectures. Extensive experiments on CIFAR, ImageNet, and COCO demonstrate the superiority of the proposed method.
Text-to-image diffusion models have shown an impressive ability to generate high-quality images from input textual descriptions. However, concerns have been raised about the potential for these models to create content that infringes on copyrights or depicts disturbing subject matter. Removing specific concepts from these models is a promising potential solution to this problem. However, existing methods for concept removal do not work well in practical but challenging scenarios where concepts need to be continuously removed. Specifically, these methods lead to poor alignment between the text prompts and the generated image after the continuous removal process. To address this issue, we propose a novel approach called CCRT that includes a designed knowledge distillation paradigm. It constrains the text-image alignment behavior during the continuous concept removal process by using a set of text prompts generated through our genetic algorithm, which employs a designed fuzzing strategy. We conduct extensive experiments involving the removal of various concepts. The results evaluated through both algorithmic metrics and human studies demonstrate that our CCRT can effectively remove the targeted concepts in a continuous manner while maintaining the high generation quality (e.g., text-image alignment) of the model.
The foundation model (FM) paradigm is transforming Machine Learning Force Fields (MLFFs), leveraging general-purpose representations and scalable training to perform a variety of computational chemistry tasks. Although MLFF FMs have begun to close the accuracy gap relative to first-principles methods, there is still a strong need for faster inference speed. Additionally, while research is increasingly focused on general-purpose models which transfer across chemical space, practitioners typically only study a small subset of systems at a given time. This underscores the need for fast, specialized MLFFs relevant to specific downstream applications, which preserve test-time physical soundness while maintaining train-time scalability. In this work, we introduce a method for transferring general-purpose representations from MLFF foundation models to smaller, faster MLFFs specialized to specific regions of chemical space. We formulate our approach as a knowledge distillation procedure, where the smaller "student" MLFF is trained to match the Hessians of the energy predictions of the "teacher" foundation model. Our specialized MLFFs can be up to 20 $\times$ faster than the original foundation model, while retaining, and in some cases exceeding, its performance and that of undistilled models. We also show that distilling from a teacher model with a direct force parameterization into a student model trained with conservative forces (i.e., computed as derivatives of the potential energy) successfully leverages the representations from the large-scale teacher for improved accuracy, while maintaining energy conservation during test-time molecular dynamics simulations. More broadly, our work suggests a new paradigm for MLFF development, in which foundation models are released along with smaller, specialized simulation "engines" for common chemical subsets.
Knowledge distillation has been widely adopted in computer vision task processing, since it can effectively enhance the performance of lightweight student networks by leveraging the knowledge transferred from cumbersome teacher networks. Most existing knowledge distillation methods utilize Kullback-Leibler divergence to mimic the logit output probabilities between the teacher network and the student network. Nonetheless, these methods may neglect the negative parts of the teacher's ''dark knowledge'' because the divergence calculations may ignore the effect of the minute probabilities from the teacher's logit output. This deficiency may lead to suboptimal performance in logit mimicry during the distillation process and result in an imbalance of information acquired by the student network. In this paper, we investigate the impact of this imbalance and propose a novel method, named Balance Divergence Distillation. By introducing a compensatory operation using reverse Kullback-Leibler divergence, our method can improve the modeling of the extremely small values in the negative from the teacher and preserve the learning capacity for the positive. Furthermore, we test the impact of different temperature coefficients adjustments, which may conducted to further balance for knowledge transferring. We evaluate the proposed method on several computer vision tasks, including image classification and semantic segmentation. The evaluation results show that our method achieves an accuracy improvement of 1%~3% for lightweight students on both CIFAR-100 and ImageNet dataset, and a 4.55% improvement in mIoU for PSP-ResNet18 on the Cityscapes dataset. The experiments show that our method is a simple yet highly effective solution that can be smoothly applied to different knowledge distillation methods.
Spiking Neural Networks (SNNs) are promising for low-power computation due to their event-driven mechanism but often suffer from lower accuracy compared to Artificial Neural Networks (ANNs). ANN-to-SNN knowledge distillation can improve SNN performance, but previous methods either focus solely on label information, missing valuable intermediate layer features, or use a layer-wise approach that neglects spatial and temporal semantic inconsistencies, leading to performance degradation.To address these limitations, we propose a novel method called self-attentive spatio-temporal calibration (SASTC). SASTC uses self-attention to identify semantically aligned layer pairs between ANN and SNN, both spatially and temporally. This enables the autonomous transfer of relevant semantic information. Extensive experiments show that SASTC outperforms existing methods, effectively solving the mismatching problem. Superior accuracy results include 95.12% on CIFAR-10, 79.40% on CIFAR-100 with 2 time steps, and 68.69% on ImageNet with 4 time steps for static datasets, and 97.92% on DVS-Gesture and 83.60% on DVS-CIFAR10 for neuromorphic datasets. This marks the first time SNNs have outperformed ANNs on both CIFAR-10 and CIFAR-100, shedding the new light on the potential applications of SNNs.
Bearing fault diagnosis under varying working conditions faces challenges, including a lack of labeled data, distribution discrepancies, and resource constraints. To address these issues, we propose a progressive knowledge distillation framework that transfers knowledge from a complex teacher model, utilizing a Graph Convolutional Network (GCN) with Autoregressive moving average (ARMA) filters, to a compact and efficient student model. To mitigate distribution discrepancies and labeling uncertainty, we introduce Enhanced Local Maximum Mean Squared Discrepancy (ELMMSD), which leverages mean and variance statistics in the Reproducing Kernel Hilbert Space (RKHS) and incorporates a priori probability distributions between labels. This approach increases the distance between clustering centers, bridges subdomain gaps, and enhances subdomain alignment reliability. Experimental results on benchmark datasets (CWRU and JNU) demonstrate that the proposed method achieves superior diagnostic accuracy while significantly reducing computational costs. Comprehensive ablation studies validate the effectiveness of each component, highlighting the robustness and adaptability of the approach across diverse working conditions.
In the contemporary context of rapid advancements in information technology and the exponential growth of data volume, language models are confronted with significant challenges in effectively navigating the dynamic and ever-evolving information landscape to update and adapt to novel knowledge in real time. In this work, an online update method is proposed, which is based on the existing Retrieval Enhanced Generation (RAG) model with multiple innovation mechanisms. Firstly, the dynamic memory is used to capture the emerging data samples, and then gradually integrate them into the core model through a tunable knowledge distillation strategy. At the same time, hierarchical indexing and multi-layer gating mechanism are introduced into the retrieval module to ensure that the retrieved content is more targeted and accurate. Finally, a multi-stage network structure is established for different types of inputs in the generation stage, and cross-attention matching and screening are carried out on the intermediate representations of each stage to ensure the effective integration and iterative update of new and old knowledge. Experimental results show that the proposed method is better than the existing mainstream comparison models in terms of knowledge retention and inference accuracy.
Recent feature masking knowledge distillation methods make use of attention mechanisms to identify either important spatial regions or channel clues for discriminative feature reconstruction. However, most of existing strategies perform global attention-guided feature masking distillation without delving into fine-grained visual clues in feature maps. In particular, uncovering locality-aware clues across different scales are conducive to reconstructing region-aware features, thereby significantly benefiting distillation performance. In this study, we propose a fine-grained adaptive feature masking distillation framework for accurate object detection. Different from previous methods in which global masking is performed on single-scale feature maps, we explore the scale-aware feature masking by performing feature distillation across various scales, such that the object-aware locality is encoded for improved feature reconstruction. In addition, our fine-grained feature distillation strategy is combined with a masking logits distillation scheme in which logits difference between teacher and student networks is utilized to guide the distillation process. Thus, it can help the student model to better learn from the teacher counterpart with improved knowledge transfer. Extensive experiments for detection task demonstrate the superiority of our method. For example, when RetinaNet, RepPoints and Cascade Mask RCNN are used as teacher detectors, the student network achieves mAP scores of 41.5\%, 42.9\%, and 42.6\%, respectively, outperforming state-of-the-art methods such as DMKD and FreeKD.
Conventional knowledge distillation (KD) approaches are designed for the student model to predict similar output as the teacher model for each sample. Unfortunately, the relationship across samples with same class is often neglected. In this paper, we explore to redefine the knowledge in distillation, capturing the relationship between each sample and its corresponding in-context samples (a group of similar samples with the same or different classes), and perform KD from an in-context sample retrieval perspective. As KD is a type of learned label smoothing regularization (LSR), we first conduct a theoretical analysis showing that the teacher's knowledge from the in-context samples is a crucial contributor to regularize the student training with the corresponding samples. Buttressed by the analysis, we propose a novel in-context knowledge distillation (IC-KD) framework that shows its superiority across diverse KD paradigms (offline, online, and teacher-free KD). Firstly, we construct a feature memory bank from the teacher model and retrieve in-context samples for each corresponding sample through retrieval-based learning. We then introduce Positive In-Context Distillation (PICD) to reduce the discrepancy between a sample from the student and the aggregated in-context samples with the same class from the teacher in the logit space. Moreover, Negative In-Context Distillation (NICD) is introduced to separate a sample from the student and the in-context samples with different classes from the teacher in the logit space. Extensive experiments demonstrate that IC-KD is effective across various types of KD, and consistently achieves state-of-the-art performance on CIFAR-100 and ImageNet datasets.
Autonomous driving (AD) has experienced significant improvements in recent years and achieved promising 3D detection, classification, and localization results. However, many challenges remain, e.g. semantic understanding of pedestrians' behaviors, and downstream handling for pedestrian interactions. Recent studies in applications of Large Language Models (LLM) and Vision-Language Models (VLM) have achieved promising results in scene understanding and high-level maneuver planning in diverse traffic scenarios. However, deploying the billion-parameter LLMs to vehicles requires significant computation and memory resources. In this paper, we analyzed effective knowledge distillation of semantic labels to smaller Vision networks, which can be used for the semantic representation of complex scenes for downstream decision-making for planning and control.
Large Vision Language Models (LVLMs) have demonstrated impressive capabilities in video understanding, yet their adoption for Activities of Daily Living (ADL) remains limited by their inability to capture fine-grained interactions and spatial relationships. To address this, we aim to leverage the complementary nature of egocentric views to enhance LVLM's understanding of exocentric ADL videos. Consequently, we propose ego2exo knowledge distillation to learn ego-augmented exp representations. While effective, this approach requires paired ego-exo videos, which are impractical to collect at scale. To address this, we propose Skeleton-guided Synthetic Ego Generation (SK-EGO), which leverages human skeleton motion to generate synthetic ego views from exocentric videos. To enhance the ego representation of LVLMs trained on synthetic data, we develop a domain-agnostic bootstrapped ego2exo strategy that effectively transfers knowledge from real ego-exo pairs to synthetic ego-exo pairs, while mitigating domain misalignment. We find that the exo representations of our ego-augmented LVLMs successfully learn to extract ego-perspective cues, demonstrated through comprehensive evaluation on six ADL benchmarks and our proposed Ego-in-Exo PerceptionMCQ benchmark designed specifically to assess egocentric understanding from exocentric videos. Code, models, and data will be open-sourced at https://github.com/dominickrei/EgoExo4ADL.