Graph neural networks (GNNs) are being increasingly used in many high-stakes tasks, and as a result, there is growing attention on their fairness recently. GNNs have been shown to be unfair as they tend to make discriminatory decisions toward certain demographic groups, divided by sensitive attributes such as gender and race. While recent works have been devoted to improving their fairness performance, they often require accessible demographic information. This greatly limits their applicability in real-world scenarios due to legal restrictions. To address this problem, we present a demographic-agnostic method to learn fair GNNs via knowledge distillation, namely FairGKD. Our work is motivated by the empirical observation that training GNNs on partial data (i.e., only node attributes or topology data) can improve their fairness, albeit at the cost of utility. To make a balanced trade-off between fairness and utility performance, we employ a set of fairness experts (i.e., GNNs trained on different partial data) to construct the synthetic teacher, which distills fairer and informative knowledge to guide the learning of the GNN student. Experiments on several benchmark datasets demonstrate that FairGKD, which does not require access to demographic information, significantly improves the fairness of GNNs by a large margin while maintaining their utility.
Image segmentation based on continual learning exhibits a critical drop of performance, mainly due to catastrophic forgetting and background shift, as they are required to incorporate new classes continually. In this paper, we propose a simple, yet effective Continual Image Segmentation method with incremental Dynamic Query (CISDQ), which decouples the representation learning of both old and new knowledge with lightweight query embedding. CISDQ mainly includes three contributions: 1) We define dynamic queries with adaptive background class to exploit past knowledge and learn future classes naturally. 2) CISDQ proposes a class/instance-aware Query Guided Knowledge Distillation strategy to overcome catastrophic forgetting by capturing the inter-class diversity and intra-class identity. 3) Apart from semantic segmentation, CISDQ introduce the continual learning for instance segmentation in which instance-wise labeling and supervision are considered. Extensive experiments on three datasets for two tasks (i.e., continual semantic and instance segmentation are conducted to demonstrate that CISDQ achieves the state-of-the-art performance, specifically, obtaining 4.4% and 2.9% mIoU improvements for the ADE 100-10 (6 steps) setting and ADE 100-5 (11 steps) setting.
Recent advances in real-time neural rendering using point-based techniques have enabled broader adoption of 3D representations. However, foundational approaches like 3D Gaussian Splatting impose substantial storage overhead, as Structure-from-Motion (SfM) points can grow to millions, often requiring gigabyte-level disk space for a single unbounded scene. This growth presents scalability challenges and hinders splatting efficiency. To address this, we introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction, and applies a pruning and recovery process to reduce redundancy while preserving visual quality. Knowledge distillation and pseudo-view augmentation then transfer spherical harmonic coefficients to a lower degree, yielding compact representations. Gaussian Vector Quantization, based on each Gaussian's global significance, further lowers bitwidth with minimal accuracy loss. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework, enabling efficient complex scene representation on the Mip-NeRF 360 and Tank & Temple datasets. The proposed Gaussian pruning approach is also adaptable to other 3D representations (e.g., Scaffold-GS), demonstrating strong generalization capabilities.
Recent studies attempted to utilize multilayer perceptrons (MLPs) to solve semisupervised node classification on graphs, by training a student MLP by knowledge distillation from a teacher graph neural network (GNN). While previous studies have focused mostly on training the student MLP by matching the output probability distributions between the teacher and student models during distillation, it has not been systematically studied how to inject the structural information in an explicit and interpretable manner. Inspired by GNNs that separate feature transformation $T$ and propagation $\Pi$, we re-frame the distillation process as making the student MLP learn both $T$ and $\Pi$. Although this can be achieved by applying the inverse propagation $\Pi^{-1}$ before distillation from the teacher, it still comes with a high computational cost from large matrix multiplications during training. To solve this problem, we propose Propagate & Distill (P&D), which propagates the output of the teacher before distillation, which can be interpreted as an approximate process of the inverse propagation. We demonstrate that P&D can readily improve the performance of the student MLP.
Text-to-image diffusion models are well-known for their ability to generate realistic images based on textual prompts. However, the existing works have predominantly focused on English, lacking support for non-English text-to-image models. The most commonly used translation methods cannot solve the generation problem related to language culture, while training from scratch on a specific language dataset is prohibitively expensive. In this paper, we are inspired to propose a simple plug-and-play language transfer method based on knowledge distillation. All we need to do is train a lightweight MLP-like parameter-efficient adapter (PEA) with only 6M parameters under teacher knowledge distillation along with a small parallel data corpus. We are surprised to find that freezing the parameters of UNet can still achieve remarkable performance on the language-specific prompt evaluation set, demonstrating that PEA can stimulate the potential generation ability of the original UNet. Additionally, it closely approaches the performance of the English text-to-image model on a general prompt evaluation set. Furthermore, our adapter can be used as a plugin to achieve significant results in downstream tasks in cross-lingual text-to-image generation. Code will be available at: https://github.com/OPPO-Mente-Lab/PEA-Diffusion
This paper presents an approach for detecting unilateral arm paralysis/weakness using kinematic data. Our method employs temporal convolution networks and recurrent neural networks, guided by knowledge distillation, where we use inertial measurement units attached to the body to capture kinematic information such as acceleration, rotation, and flexion of body joints during an action. This information is then analyzed to recognize body actions and patterns. Our proposed network achieves a high paretic detection accuracy of 97.99\%, with an action classification accuracy of 77.69\%, through knowledge sharing. Furthermore, by incorporating causal reasoning, we can gain additional insights into the patient's condition, such as their Fugl-Meyer assessment score or impairment level based on the machine learning result. Overall, our approach demonstrates the potential of using kinematic data and machine learning for detecting arm paralysis/weakness. The results suggest that our method could be a useful tool for clinicians and healthcare professionals working with patients with this condition.
Foundation models have achieved remarkable results in 2D and language tasks like image segmentation, object detection, and visual-language understanding. However, their potential to enrich 3D scene representation learning is largely untapped due to the existence of the domain gap. In this work, we propose an innovative methodology called Bridge3D to address this gap by pre-training 3D models using features, semantic masks, and captions sourced from foundation models. Specifically, our method employs semantic masks from foundation models to guide the masking and reconstruction process for the masked autoencoder, enabling more focused attention on foreground representations. Moreover, we bridge the 3D-text gap at the scene level using image captioning foundation models, thereby facilitating scene-level knowledge distillation. We further extend this bridging effort by introducing an innovative object-level knowledge distillation method that harnesses highly accurate object-level masks and semantic text data from foundation models. Our methodology significantly surpasses the performance of existing state-of-the-art methods in 3D object detection and semantic segmentation tasks. For instance, on the ScanNet dataset, Bridge3D improves the baseline by a notable margin of 6.3%. Code will be available at: https://github.com/Zhimin-C/Bridge3D
Recent advances in graph neural networks (GNNs) have enabled more comprehensive modeling of molecules and molecular systems, thereby enhancing the precision of molecular property prediction and molecular simulations. Nonetheless, as the field has been progressing to bigger and more complex architectures, state-of-the-art GNNs have become largely prohibitive for many large-scale applications. In this paper, we explore the utility of knowledge distillation (KD) for accelerating molecular GNNs. To this end, we devise KD strategies that facilitate the distillation of hidden representations in directional and equivariant GNNs, and evaluate their performance on the regression task of energy and force prediction. We validate our protocols across different teacher-student configurations and datasets, and demonstrate that they can consistently boost the predictive accuracy of student models without any modifications to their architecture. Moreover, we conduct comprehensive optimization of various components of our framework, and investigate the potential of data augmentation to further enhance performance. All in all, we manage to close the gap in predictive accuracy between teacher and student models by as much as 96.7% and 62.5% for energy and force prediction respectively, while fully preserving the inference throughput of the more lightweight models.
Knowledge distillation (KD) can enable collaborative learning among distributed clients that have different model architectures and do not share their local data and model parameters with others. Each client updates its local model using the average model output/feature of all client models as the target, known as federated KD. However, existing federated KD methods often do not perform well when clients' local models are trained with heterogeneous local datasets. In this paper, we propose Federated knowledge distillation enabled by Adversarial Learning (FedAL) to address the data heterogeneity among clients. First, to alleviate the local model output divergence across clients caused by data heterogeneity, the server acts as a discriminator to guide clients' local model training to achieve consensus model outputs among clients through a min-max game between clients and the discriminator. Moreover, catastrophic forgetting may happen during the clients' local training and global knowledge transfer due to clients' heterogeneous local data. Towards this challenge, we design the less-forgetting regularization for both local training and global knowledge transfer to guarantee clients' ability to transfer/learn knowledge to/from others. Experimental results show that FedAL and its variants achieve higher accuracy than other federated KD baselines.
Speech-driven 3D facial animation has been an attractive task in both academia and industry. Traditional methods mostly focus on learning a deterministic mapping from speech to animation. Recent approaches start to consider the non-deterministic fact of speech-driven 3D face animation and employ the diffusion model for the task. However, personalizing facial animation and accelerating animation generation are still two major limitations of existing diffusion-based methods. To address the above limitations, we propose DiffusionTalker, a diffusion-based method that utilizes contrastive learning to personalize 3D facial animation and knowledge distillation to accelerate 3D animation generation. Specifically, to enable personalization, we introduce a learnable talking identity to aggregate knowledge in audio sequences. The proposed identity embeddings extract customized facial cues across different people in a contrastive learning manner. During inference, users can obtain personalized facial animation based on input audio, reflecting a specific talking style. With a trained diffusion model with hundreds of steps, we distill it into a lightweight model with 8 steps for acceleration. Extensive experiments are conducted to demonstrate that our method outperforms state-of-the-art methods. The code will be released.
Knowledge distillation (KD) has demonstrated remarkable success across various domains, but its application to medical imaging tasks, such as kidney and liver tumor segmentation, has encountered challenges. Many existing KD methods are not specifically tailored for these tasks. Moreover, prevalent KD methods often lack a careful consideration of `what' and `from where' to distill knowledge from the teacher to the student. This oversight may lead to issues like the accumulation of training bias within shallower student layers, potentially compromising the effectiveness of KD. To address these challenges, we propose Hierarchical Layer-selective Feedback Distillation (HLFD). HLFD strategically distills knowledge from a combination of middle layers to earlier layers and transfers final layer knowledge to intermediate layers at both the feature and pixel levels. This design allows the model to learn higher-quality representations from earlier layers, resulting in a robust and compact student model. Extensive quantitative evaluations reveal that HLFD outperforms existing methods by a significant margin. For example, in the kidney segmentation task, HLFD surpasses the student model (without KD) by over 10\%, significantly improving its focus on tumor-specific features. From a qualitative standpoint, the student model trained using HLFD excels at suppressing irrelevant information and can focus sharply on tumor-specific details, which opens a new pathway for more efficient and accurate diagnostic tools. Code is available \href{https://github.com/vangorade/RethinkingKD_ISBI24}{here}.
Click-Through Rate (CTR) prediction, which aims to estimate the probability of a user clicking on an item, is a key task in online advertising. Numerous existing CTR models concentrate on modeling the feature interactions within a solitary domain, thereby rendering them inadequate for fulfilling the requisites of multi-domain recommendations in real industrial scenarios. Some recent approaches propose intricate architectures to enhance knowledge sharing and augment model training across multiple domains. However, these approaches encounter difficulties when being transferred to new recommendation domains, owing to their reliance on the modeling of ID features (e.g., item id). To address the above issue, we propose the Universal Feature Interaction Network (UFIN) approach for CTR prediction. UFIN exploits textual data to learn universal feature interactions that can be effectively transferred across diverse domains. For learning universal feature representations, we regard the text and feature as two different modalities and propose an encoder-decoder network founded on a Large Language Model (LLM) to enforce the transfer of data from the text modality to the feature modality. Building upon the above foundation, we further develop a mixtureof-experts (MoE) enhanced adaptive feature interaction model to learn transferable collaborative patterns across multiple domains. Furthermore, we propose a multi-domain knowledge distillation framework to enhance feature interaction learning. Based on the above methods, UFIN can effectively bridge the semantic gap to learn common knowledge across various domains, surpassing the constraints of ID-based models. Extensive experiments conducted on eight datasets show the effectiveness of UFIN, in both multidomain and cross-platform settings. Our code is available at https://github.com/RUCAIBox/UFIN.
In current synthetic aperture radar (SAR) object classification, one of the major challenges is the severe overfitting issue due to the limited dataset (few-shot) and noisy data. Considering the advantages of knowledge distillation as a learned label smoothing regularization, this paper proposes a novel Double Reverse Regularization Network based on Self-Knowledge Distillation (DRRNet-SKD). Specifically, through exploring the effect of distillation weight on the process of distillation, we are inspired to adopt the double reverse thought to implement an effective regularization network by combining offline and online distillation in a complementary way. Then, the Adaptive Weight Assignment (AWA) module is designed to adaptively assign two reverse-changing weights based on the network performance, allowing the student network to better benefit from both teachers. The experimental results on OpenSARShip and FUSAR-Ship demonstrate that DRRNet-SKD exhibits remarkable performance improvement on classical CNNs, outperforming state-of-the-art self-knowledge distillation methods.
Creating multi-view wire art (MVWA), a static 3D sculpture with diverse interpretations from different viewpoints, is a complex task even for skilled artists. In response, we present DreamWire, an AI system enabling everyone to craft MVWA easily. Users express their vision through text prompts or scribbles, freeing them from intricate 3D wire organisation. Our approach synergises 3D B\'ezier curves, Prim's algorithm, and knowledge distillation from diffusion models or their variants (e.g., ControlNet). This blend enables the system to represent 3D wire art, ensuring spatial continuity and overcoming data scarcity. Extensive evaluation and analysis are conducted to shed insight on the inner workings of the proposed system, including the trade-off between connectivity and visual aesthetics.
Machine \emph{unlearning}, which involves erasing knowledge about a \emph{forget set} from a trained model, can prove to be costly and infeasible by existing techniques. We propose a nearly compute-free zero-shot unlearning technique based on a discrete representational bottleneck. We show that the proposed technique efficiently unlearns the forget set and incurs negligible damage to the model's performance on the rest of the data set. We evaluate the proposed technique on the problem of \textit{class unlearning} using three datasets: CIFAR-10, CIFAR-100, and LACUNA-100. We compare the proposed technique to SCRUB, a state-of-the-art approach which uses knowledge distillation for unlearning. Across all three datasets, the proposed technique performs as well as, if not better than SCRUB while incurring almost no computational cost.
This article focuses on the development and evaluation of Small-sized Czech sentence embedding models. Small models are important components for real-time industry applications in resource-constrained environments. Given the limited availability of labeled Czech data, alternative approaches, including pre-training, knowledge distillation, and unsupervised contrastive fine-tuning, are investigated. Comprehensive intrinsic and extrinsic analyses are conducted, showcasing the competitive performance of our models compared to significantly larger counterparts, with approximately 8 times smaller size and 5 times faster speed than conventional Base-sized models. To promote cooperation and reproducibility, both the models and the evaluation pipeline are made publicly accessible. Ultimately, this article presents practical applications of the developed sentence embedding models in Seznam.cz, the Czech search engine. These models have effectively replaced previous counterparts, enhancing the overall search experience for instance, in organic search, featured snippets, and image search. This transition has yielded improved performance.
Since rumors widely spread on social networks can cause seri- ous negative impacts, a batch of studies have investigated how to detect rumors. Most of them rely on existing datasets and try to improve the detection performance on those known datasets, but their performance drops significantly when detecting newly emerging events. This is not in line with the original intention of the rumor detection task. To tackle this issue, we formulate the rumor detection problem as a domain adaption task and propose the Class-based Adversarial Domain Adaptive framework, CADA, which is a general model framework where any latest rumor detec- tion methods can be plugged-in. The improvement of new emerging rumor event detection is based on adversarial training. Specifically, CADA considers class-based discriminators to achieve fine-grained alignment of declarations to be detected of different classes. Ex- periments on three public datasets show that CADA can improve the detection performance of existing rumor detection models and achieve better results than state-of-the-art models. In terms of ac- curacy, the performance is improved by at least 3% compared with the original base model in the PHEME dataset, and as high as 10% in the Twitter datasets.
The challenging environment of real-time data processing systems at the Large Hadron Collider (LHC) strictly limits the computational complexity of algorithms that can be deployed. For deep learning models, this implies that only models with low computational complexity that have weak inductive bias are feasible. To address this issue, we utilize knowledge distillation to leverage both the performance of large models and the reduced computational complexity of small ones. In this paper, we present an implementation of knowledge distillation, demonstrating an overall boost in the student models' performance for the task of classifying jets at the LHC. Furthermore, by using a teacher model with a strong inductive bias of Lorentz symmetry, we show that we can induce the same inductive bias in the student model which leads to better robustness against arbitrary Lorentz boost.
Deep learning (DL) has shown great potential in revolutionizing the traditional communications system. Many applications in communications have adopted DL techniques due to their powerful representation ability. However, the learning-based methods can be dependent on the training dataset and perform worse on unseen interference due to limited model generalizability and complexity. In this paper, we consider the semantic communication (SemCom) system with multiple users, where there is a limited number of training samples and unexpected interference. To improve the model generalization ability and reduce the model size, we propose a knowledge distillation (KD) based system where Transformer based encoder-decoder is implemented as the semantic encoder-decoder and fully connected neural networks are implemented as the channel encoder-decoder. Specifically, four types of knowledge transfer and model compression are analyzed. Important system and model parameters are considered, including the level of noise and interference, the number of interfering users and the size of the encoder and decoder. Numerical results demonstrate that KD significantly improves the robustness and the generalization ability when applied to unexpected interference, and it reduces the performance loss when compressing the model size.
As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high computational requirements and limited input sequence length. Despite these separate efforts, no investigation has been done into the intersection of these two fields. In this work, we provide an evaluation of model compression via knowledge distillation on efficient attention transformers. We provide cost-performance trade-offs for the compression of state-of-the-art efficient attention architectures and the gains made in performance in comparison to their full attention counterparts. Furthermore, we introduce a new long-context Named Entity Recognition dataset, GONERD, to train and test the performance of NER models on long sequences. We find that distilled efficient attention transformers can preserve a significant amount of original model performance, preserving up to 98.6% across short-context tasks (GLUE, SQUAD, CoNLL-2003), up to 94.6% across long-context Question-and-Answering tasks (HotpotQA, TriviaQA), and up to 98.8% on long-context Named Entity Recognition (GONERD), while decreasing inference times by up to 57.8%. We find that, for most models on most tasks, performing knowledge distillation is an effective method to yield high-performing efficient attention models with low costs.