Previous studies have pointed out that visual question answering (VQA) models are prone to relying on language priors for answer predictions. In this context, predictions often depend on linguistic shortcuts rather than a comprehensive grasp of multimodal knowledge, which diminishes their generalization ability. In this paper, we propose a novel method, namely, KDAR, leveraging knowledge distillation to address the prior-dependency dilemmas within the VQA task. Specifically, the regularization effect facilitated by soft labels from a well-trained teacher is employed to penalize overfitting to the most common answers. The soft labels, which serve a regularization role, also provide semantic guidance that narrows the range of candidate answers. Additionally, we design an adaptive sample-wise reweighting learning strategy to further mitigate bias by dynamically adjusting the importance of each sample. Experimental results demonstrate that our method enhances performance in both OOD and IID settings. Our method achieves state-of-the-art performance on the VQA-CPv2 out-of-distribution (OOD) benchmark, significantly outperforming previous state-of-the-art approaches.
We introduce LLMQuoter, a lightweight, distillation-based model designed to enhance Retrieval Augmented Generation (RAG) by extracting the most relevant textual evidence for downstream reasoning tasks. Built on the LLaMA-3B architecture and fine-tuned with Low-Rank Adaptation (LoRA) on a 15,000-sample subset of HotpotQA, LLMQuoter adopts a "quote-first-then-answer" strategy, efficiently identifying key quotes before passing curated snippets to reasoning models. This workflow reduces cognitive overhead and outperforms full-context approaches like Retrieval-Augmented Fine-Tuning (RAFT), achieving over 20-point accuracy gains across both small and large language models. By leveraging knowledge distillation from a high-performing teacher model, LLMQuoter achieves competitive results in a resource-efficient fine-tuning setup. It democratizes advanced RAG capabilities, delivering significant performance improvements without requiring extensive model retraining. Our results highlight the potential of distilled quote-based reasoning to streamline complex workflows, offering a scalable and practical solution for researchers and practitioners alike.
Federated Learning (FL) provides novel solutions for machine learning (ML)-based lithography hotspot detection (LHD) under distributed privacy-preserving settings. Currently, two research pipelines have been investigated to aggregate local models and achieve global consensus, including parameter/nonparameter based (also known as knowledge distillation, namely KD). While these two kinds of methods show effectiveness in specific scenarios, we note they have not fully utilized and transferred the information learned, leaving the potential of FL-based LDH remains unexplored. Thus, we propose FedKDhybrid in this study to mitigate the research gap. Specifically, FedKD-hybrid clients agree on several identical layers across all participants and a public dataset for achieving global consensus. During training, the trained local model will be evaluated on the public dataset, and the generated logits will be uploaded along with the identical layer parameters. The aggregated information is consequently used to update local models via the public dataset as a medium. We compare our proposed FedKD-hybrid with several state-of-the-art (SOTA) FL methods under ICCAD-2012 and FAB (real-world collected) datasets with different settings; the experimental results demonstrate the superior performance of the FedKD-hybrid algorithm. Our code is available at https://github.com/itsnotacie/NN-FedKD-hybrid
Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets, enabling task-specific adaptation while preserving data privacy. However, fine-tuning the extensive parameters in LLMs is particularly challenging in resource-constrained federated scenarios due to the significant communication and computational costs. To gain a deeper understanding of how these challenges can be addressed, this article conducts a comparative analysis three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues: 1) FedLLMs, where clients upload model parameters or gradients to enable straightforward and effective fine-tuning; 2) KD-FedLLMs, which leverage KD for efficient knowledge sharing via logits; and 3) Split-FedLLMs, which split the LLMs into two parts, with one part executed on the client and the other one on the server, to balance the computational load. Each framework is evaluated based on key performance metrics, including model accuracy, communication overhead, and client-side computational load, offering insights into their effectiveness for various federated fine-tuning scenarios. Through this analysis, we identify framework-specific optimization opportunities to enhance the efficiency of FedLLMs and discuss broader research directions, highlighting open opportunities to better adapt FedLLMs for real-world applications. A use case is presented to demonstrate the performance comparison of these three frameworks under varying configurations and settings.
In remote sensing scene classification, leveraging the transfer methods with well-trained optical models is an efficient way to overcome label scarcity. However, cloud contamination leads to optical information loss and significant impacts on feature distribution, challenging the reliability and stability of transferred target models. Common solutions include cloud removal for optical data or directly using Synthetic aperture radar (SAR) data in the target domain. However, cloud removal requires substantial auxiliary data for support and pre-training, while directly using SAR disregards the unobstructed portions of optical data. This study presents a scene classification transfer method that synergistically combines multi-modality data, which aims to transfer the source domain model trained on cloudfree optical data to the target domain that includes both cloudy optical and SAR data at low cost. Specifically, the framework incorporates two parts: (1) the collaborative transfer strategy, based on knowledge distillation, enables the efficient prior knowledge transfer across heterogeneous data; (2) the information regulation mechanism (IRM) is proposed to address the modality imbalance issue during transfer. It employs auxiliary models to measure the contribution discrepancy of each modality, and automatically balances the information utilization of modalities during the target model learning process at the sample-level. The transfer experiments were conducted on simulated and real cloud datasets, demonstrating the superior performance of the proposed method compared to other solutions in cloud-covered scenarios. We also verified the importance and limitations of IRM, and further discussed and visualized the modality imbalance problem during the model transfer. Codes are available at https://github.com/wangyuze-csu/ESCCS
Dataset distillation is an effective technique for reducing the cost and complexity of model training while maintaining performance by compressing large datasets into smaller, more efficient versions. In this paper, we present a novel generative dataset distillation method that can improve the accuracy of aligning prediction logits. Our approach integrates self-knowledge distillation to achieve more precise distribution matching between the synthetic and original data, thereby capturing the overall structure and relationships within the data. To further improve the accuracy of alignment, we introduce a standardization step on the logits before performing distribution matching, ensuring consistency in the range of logits. Through extensive experiments, we demonstrate that our method outperforms existing state-of-the-art methods, resulting in superior distillation performance.
With the rapid development of 3D reconstruction technology, the widespread distribution of 3D data has become a future trend. While traditional visual data (such as images and videos) and NeRF-based formats already have mature techniques for copyright protection, steganographic techniques for the emerging 3D Gaussian Splatting (3D-GS) format have yet to be fully explored. To address this, we propose ConcealGS, an innovative method for embedding implicit information into 3D-GS. By introducing the knowledge distillation and gradient optimization strategy based on 3D-GS, ConcealGS overcomes the limitations of NeRF-based models and enhances the robustness of implicit information and the quality of 3D reconstruction. We evaluate ConcealGS in various potential application scenarios, and experimental results have demonstrated that ConcealGS not only successfully recovers implicit information but also has almost no impact on rendering quality, providing a new approach for embedding invisible and recoverable information into 3D models in the future.
Math Word Problem (MWP) solving is a critical task in natural language processing, has garnered significant research interest in recent years. Various recent studies heavily rely on Seq2Seq models and their extensions (e.g., Seq2Tree and Graph2Tree) to generate mathematical equations. While effective, these models struggle to generate diverse but counterpart solution equations, limiting their generalization across various math problem scenarios. In this paper, we introduce a novel Diversity-enhanced Knowledge Distillation (DivKD) model for practical MWP solving. Our approach proposes an adaptive diversity distillation method, in which a student model learns diverse equations by selectively transferring high-quality knowledge from a teacher model. Additionally, we design a diversity prior-enhanced student model to better capture the diversity distribution of equations by incorporating a conditional variational auto-encoder. Extensive experiments on {four} MWP benchmark datasets demonstrate that our approach achieves higher answer accuracy than strong baselines while maintaining high efficiency for practical applications.
This study investigates transformer model compression by systematically pruning its layers. We evaluated 14 pruning strategies across nine diverse datasets, including 12 strategies based on different signals obtained from layer activations, mutual information, gradients, weights, and attention. To address the limitations of single-signal strategies, we introduced two fusion strategies, linear regression and random forest, which combine individual strategies (i.e., strategic fusion), for more informed pruning decisions. Additionally, we applied knowledge distillation to mitigate any accuracy loss during layer pruning. Our results reveal that random forest strategic fusion outperforms individual strategies in seven out of nine datasets and achieves near-optimal performance in the other two. The distilled random forest surpasses the original accuracy in six datasets and mitigates accuracy drops in the remaining three. Knowledge distillation also improves the accuracy-to-size ratio by an average factor of 18.84 across all datasets. Supported by mathematical foundations and biological analogies, our findings suggest that strategically combining multiple signals can lead to efficient, high-performing transformer models for resource-constrained applications.
The emergence of 5G and edge computing hardware has brought about a significant shift in artificial intelligence, with edge AI becoming a crucial technology for enabling intelligent applications. With the growing amount of data generated and stored on edge devices, deploying AI models for local processing and inference has become increasingly necessary. However, deploying state-of-the-art AI models on resource-constrained edge devices faces significant challenges that must be addressed. This paper presents an optimization triad for efficient and reliable edge AI deployment, including data, model, and system optimization. First, we discuss optimizing data through data cleaning, compression, and augmentation to make it more suitable for edge deployment. Second, we explore model design and compression methods at the model level, such as pruning, quantization, and knowledge distillation. Finally, we introduce system optimization techniques like framework support and hardware acceleration to accelerate edge AI workflows. Based on an in-depth analysis of various application scenarios and deployment challenges of edge AI, this paper proposes an optimization paradigm based on the data-model-system triad to enable a whole set of solutions to effectively transfer ML models, which are initially trained in the cloud, to various edge devices for supporting multiple scenarios.
Photoplethsmography (PPG)-based individual identification aiming at recognizing humans via intrinsic cardiovascular activities has raised extensive attention due to its high security and resistance to mimicry. However, this kind of technology witnesses unpromising results due to the limitation of low information density. To this end, electrocardiogram (ECG) signals have been introduced as a novel modality to enhance the density of input information. Specifically, a novel cross-modal knowledge distillation framework is implemented to propagate discriminate knowledge from ECG modality to PPG modality without incurring additional computational demands at the inference phase. Furthermore, to ensure efficient knowledge propagation, Contrastive Language-Image Pre-training (CLIP)-based knowledge alignment and cross-knowledge assessment modules are proposed respectively. Comprehensive experiments are conducted and results show our framework outperforms the baseline model with the improvement of 2.8% and 3.0% in terms of overall accuracy on seen- and unseen individual recognitions.
Following the remarkable success of Large Language Models (LLMs) in NLP tasks, there is increasing interest in extending their capabilities to speech -- the most common form of communication. The most widespread approach to integrating speech into LLMs is dense feature prepending (DFP), which prepends the projected speech representations to the textual representations, allowing end-to-end training with a speech encoder. This raises questions about the need for a sophisticated speech encoder for DFP and how its performance compares with a standard encoder-decoder (i.e., cross-attention) architecture. We compare DFP and cross-attention under a variety of configurations, such as CTC compression, sequence-level knowledge distillation, on monolingual, bilingual, and multilingual models. To perform a controlled architectural comparison, we train all models from scratch rather than using large pretrained models and use comparable data and parameter settings, testing speech-to-text recognition (ASR) and translation (ST) on MuST-C v1.0 and CoVoST2 datasets. Despite the wide adoption of DFP, our results do not indicate a clear advantage of DFP over cross-attention.
Although large models have shown a strong capacity to solve large-scale problems in many areas including natural language and computer vision, their voluminous parameters are hard to deploy in a real-time system due to computational and energy constraints. Addressing this, knowledge distillation through Teacher-Student architecture offers a sustainable pathway to compress the knowledge of large models into more manageable sizes without significantly compromising performance. To enhance the robustness and interpretability of this framework, it is critical to understand how individual training data impact model performance, which is an area that remains underexplored. We propose the \textbf{Knowledge Distillation with Adaptive Influence Weight (KD-AIF)} framework which leverages influence functions from robust statistics to assign weights to training data, grounded in the four key SAFE principles: Sustainability, Accuracy, Fairness, and Explainability. This novel approach not only optimizes distillation but also increases transparency by revealing the significance of different data. The exploration of various update mechanisms within the KD-AIF framework further elucidates its potential to significantly improve learning efficiency and generalization in student models, marking a step toward more explainable and deployable Large Models. KD-AIF is effective in knowledge distillation while also showing exceptional performance in semi-supervised learning with outperforms existing baselines and methods in multiple benchmarks (CIFAR-100, CIFAR-10-4k, SVHN-1k, and GLUE).
The study of physical adversarial patches is crucial for identifying vulnerabilities in AI-based recognition systems and developing more robust deep learning models. While recent research has focused on improving patch stealthiness for greater practical applicability, achieving an effective balance between stealth and attack performance remains a significant challenge. To address this issue, we propose a novel physical adversarial attack method that leverages knowledge distillation. Specifically, we first define a stealthy color space tailored to the target environment to ensure smooth blending. Then, we optimize an adversarial patch in an unconstrained color space, which serves as the 'teacher' patch. Finally, we use an adversarial knowledge distillation module to transfer the teacher patch's knowledge to the 'student' patch, guiding the optimization of the stealthy patch. Experimental results show that our approach improves attack performance by 20%, while maintaining stealth, highlighting its practical value.
The tumor microenvironment (TME) plays a crucial role in cancer progression and treatment response, yet current methods for its comprehensive analysis in H&E-stained tissue slides face significant limitations in the diversity of tissue cell types and accuracy. Here, we present PAGET (Pathological image segmentation via AGgrEgated Teachers), a new knowledge distillation approach that integrates multiple segmentation models while considering the hierarchical nature of cell types in the TME. By leveraging a unique dataset created through immunohistochemical restaining techniques and existing segmentation models, PAGET enables simultaneous identification and classification of 14 key TME components. We demonstrate PAGET's ability to perform rapid, comprehensive TME segmentation across various tissue types and medical institutions, advancing the quantitative analysis of tumor microenvironments. This method represents a significant step forward in enhancing our understanding of cancer biology and supporting precise clinical decision-making from large-scale histopathology images.
Graph neural networks (GNNs) have demonstrated superior performance in collaborative recommendation through their ability to conduct high-order representation smoothing, effectively capturing structural information within users' interaction patterns. However, existing GNN paradigms face significant challenges in scalability and robustness when handling large-scale, noisy, and real-world datasets. To address these challenges, we present LightGNN, a lightweight and distillation-based GNN pruning framework designed to substantially reduce model complexity while preserving essential collaboration modeling capabilities. Our LightGNN framework introduces a computationally efficient pruning module that adaptively identifies and removes redundant edges and embedding entries for model compression. The framework is guided by a resource-friendly hierarchical knowledge distillation objective, whose intermediate layer augments the observed graph to maintain performance, particularly in high-rate compression scenarios. Extensive experiments on public datasets demonstrate LightGNN's effectiveness, significantly improving both computational efficiency and recommendation accuracy. Notably, LightGNN achieves an 80% reduction in edge count and 90% reduction in embedding entries while maintaining performance comparable to more complex state-of-the-art baselines. The implementation of our LightGNN framework is available at the github repository: https://github.com/HKUDS/LightGNN.
In V2X collaborative perception, the domain gaps between heterogeneous nodes pose a significant challenge for effective information fusion. Pose errors arising from latency and GPS localization noise further exacerbate the issue by leading to feature misalignment. To overcome these challenges, we propose V2X-DGPE, a high-accuracy and robust V2X feature-level collaborative perception framework. V2X-DGPE employs a Knowledge Distillation Framework and a Feature Compensation Module to learn domain-invariant representations from multi-source data, effectively reducing the feature distribution gap between vehicles and roadside infrastructure. Historical information is utilized to provide the model with a more comprehensive understanding of the current scene. Furthermore, a Collaborative Fusion Module leverages a heterogeneous self-attention mechanism to extract and integrate heterogeneous representations from vehicles and infrastructure. To address pose errors, V2X-DGPE introduces a deformable attention mechanism, enabling the model to adaptively focus on critical parts of the input features by dynamically offsetting sampling points. Extensive experiments on the real-world DAIR-V2X dataset demonstrate that the proposed method outperforms existing approaches, achieving state-of-the-art detection performance. The code is available at https://github.com/wangsch10/V2X-DGPE.
Visual encoders are fundamental components in vision-language models (VLMs), each showcasing unique strengths derived from various pre-trained visual foundation models. To leverage the various capabilities of these encoders, recent studies incorporate multiple encoders within a single VLM, leading to a considerable increase in computational cost. In this paper, we present Mixture-of-Visual-Encoder Knowledge Distillation (MoVE-KD), a novel framework that distills the unique proficiencies of multiple vision encoders into a single, efficient encoder model. Specifically, to mitigate conflicts and retain the unique characteristics of each teacher encoder, we employ low-rank adaptation (LoRA) and mixture-of-experts (MoEs) to selectively activate specialized knowledge based on input features, enhancing both adaptability and efficiency. To regularize the KD process and enhance performance, we propose an attention-based distillation strategy that adaptively weighs the different visual encoders and emphasizes valuable visual tokens, reducing the burden of replicating comprehensive but distinct features from multiple teachers. Comprehensive experiments on popular VLMs, such as LLaVA and LLaVA-NeXT, validate the effectiveness of our method. The code will be released.
Motivated by deep learning regimes with multiple interacting yet distinct model components, we introduce learning diagrams, graphical depictions of training setups that capture parameterized learning as data rather than code. A learning diagram compiles to a unique loss function on which component models are trained. The result of training on this loss is a collection of models whose predictions ``agree" with one another. We show that a number of popular learning setups such as few-shot multi-task learning, knowledge distillation, and multi-modal learning can be depicted as learning diagrams. We further implement learning diagrams in a library that allows users to build diagrams of PyTorch and Flux.jl models. By implementing some classic machine learning use cases, we demonstrate how learning diagrams allow practitioners to build complicated models as compositions of smaller components, identify relationships between workflows, and manipulate models during or after training. Leveraging a category theoretic framework, we introduce a rigorous semantics for learning diagrams that puts such operations on a firm mathematical foundation.
Host-response-based diagnostics can improve the accuracy of diagnosing bacterial and viral infections, thereby reducing inappropriate antibiotic prescriptions. However, the existing cohorts with limited sample size and coarse infections types are unable to support the exploration of an accurate and generalizable diagnostic model. Here, we curate the largest infection host-response transcriptome data, including 11,247 samples across 89 blood transcriptome datasets from 13 countries and 21 platforms. We build a diagnostic model for pathogen prediction starting from a pan-infection model as foundation (AUC = 0.97) based on the pan-infection dataset. Then, we utilize knowledge distillation to efficiently transfer the insights from this "teacher" model to four lightweight pathogen "student" models, i.e., staphylococcal infection (AUC = 0.99), streptococcal infection (AUC = 0.94), HIV infection (AUC = 0.93), and RSV infection (AUC = 0.94), as well as a sepsis "student" model (AUC = 0.99). The proposed knowledge distillation framework not only facilitates the diagnosis of pathogens using pan-infection data, but also enables an across-disease study from pan-infection to sepsis. Moreover, the framework enables high-degree lightweight design of diagnostic models, which is expected to be adaptively deployed in clinical settings.