PyTorchKR Papers

최신 논문

총 1,512편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2210.13014공식 코드 · Papers with Code

Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks

We study a new paradigm of knowledge transfer that aims at encoding graph topological information into graph neural networks (GNNs) by distilling knowledge from a teacher GNN model trained on a complete graph to a student GNN model operating on a smaller or sparser graph. To this end, we revisit the connection between thermodynamics and the behavior of GNN, based on which we propose Neural Heat Kernel (NHK) to encapsulate the geometric property of the underlying manifold concerning the architecture of GNNs. A fundamental and principled solution is derived by aligning NHKs on teacher and student models, dubbed as Geometric Knowledge Distillation. We develop non- and parametric instantiations and demonstrate their efficacy in various experimental settings for knowledge distillation regarding different types of privileged topological information and teacher-student schemes.

arXiv:2210.11787공식 코드 · Papers with Code

Modeling Document-level Temporal Structures for Building Temporal Dependency Graphs

We propose to leverage news discourse profiling to model document-level temporal structures for building temporal dependency graphs. Our key observation is that the functional roles of sentences used for profiling news discourse signify different time frames relevant to a news story and can, therefore, help to recover the global temporal structure of a document. Our analyses and experiments with the widely used knowledge distillation technique show that discourse profiling effectively identifies distant inter-sentence event and (or) time expression pairs that are temporally related and otherwise difficult to locate.

arXiv:2210.11728공식 코드 · Papers with Code

Distilling the Undistillable: Learning from a Nasty Teacher

The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense efforts considering its critical nature. Recent work Nasty Teacher proposed to develop teachers which can not be distilled or imitated by models attacking it. However, the promise of confidentiality offered by a nasty teacher is not well studied, and as a further step to strengthen against such loopholes, we attempt to bypass its defense and steal (or extract) information in its presence successfully. Specifically, we analyze Nasty Teacher from two different directions and subsequently leverage them carefully to develop simple yet efficient methodologies, named as HTC and SCM, which increase the learning from Nasty Teacher by upto 68.63% on standard datasets. Additionally, we also explore an improvised defense method based on our insights of stealing. Our detailed set of experiments and ablations on diverse models/settings demonstrate the efficacy of our approach.

arXiv:2210.11768공식 코드 · Papers with Code

Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation

Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausible in many real-world applications. Data augmentation methods such as representation interpolation, token replacement, or augmentation with models are applied to tackle this problem. However, these data augmentation methods either potentially cause shifts in decision boundaries (representation interpolation), are not expressive enough (token replacement), or introduce too much computational overhead (augmentation with models). To this end, we propose AugPro (Augmentation with Projection), an effective and efficient data augmentation method for distillation. Our method builds on top of representation interpolation augmentation methods to maintain the diversity of expressions and converts the augmented data to tokens to avoid shifting decision boundaries. It uses simple operations that come with little computational overhead. The results on multiple GLUE tasks show that our methods can improve distillation performance by a large margin at a low time cost. Codes are available at https://github.com/google-research/google-research/tree/master/augpro.

arXiv:2210.10486공식 코드 · Papers with Code

Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval

Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information. As instances from different modalities can often provide complementary information describing the underlying concept, we propose a cross-attention framework for Vision Transformers (XModalViT) that fuses modality-specific information instead of discarding them. Our framework first maps paired datapoints from the individual photo and sketch modalities to fused representations that unify information from both modalities. We then decouple the input space of the aforementioned modality fusion network into independent encoders of the individual modalities via contrastive and relational cross-modal knowledge distillation. Such encoders can then be applied to downstream tasks like cross-modal retrieval. We demonstrate the expressive capacity of the learned representations by performing a wide range of experiments and achieving state-of-the-art results on three fine-grained sketch-based image retrieval benchmarks: Shoe-V2, Chair-V2 and Sketchy. Implementation is available at https://github.com/abhrac/xmodal-vit.

arXiv:2210.09609공식 코드 · Papers with Code

SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP

The message-passing mechanism helps Graph Neural Networks (GNNs) achieve remarkable results on various node classification tasks. Nevertheless, the recursive nodes fetching and aggregation in message-passing cause inference latency when deploying GNNs to large-scale graphs. One promising inference acceleration direction is to distill the GNNs into message-passing-free student multi-layer perceptrons (MLPs). However, the MLP student cannot fully learn the structure knowledge due to the lack of structure inputs, which causes inferior performance in the heterophily and inductive scenarios. To address this, we intend to inject structure information into MLP-like students in low-latency and interpretable ways. Specifically, we first design a Structure-Aware MLP (SA-MLP) student that encodes both features and structures without message-passing. Then, we introduce a novel structure-mixing knowledge distillation strategy to enhance the learning ability of MLPs for structure information. Furthermore, we design a latent structure embedding approximation technique with two-stage distillation for inductive scenarios. Extensive experiments on eight benchmark datasets under both transductive and inductive settings show that our SA-MLP can consistently outperform the teacher GNNs, while maintaining faster inference as MLPs. The source code of our work can be found in https://github.com/JC-202/SA-MLP.

arXiv:2210.09022공식 코드 · Papers with Code

Distilling Object Detectors With Global Knowledge

Knowledge distillation learns a lightweight student model that mimics a cumbersome teacher. Existing methods regard the knowledge as the feature of each instance or their relations, which is the instance-level knowledge only from the teacher model, i.e., the local knowledge. However, the empirical studies show that the local knowledge is much noisy in object detection tasks, especially on the blurred, occluded, or small instances. Thus, a more intrinsic approach is to measure the representations of instances w.r.t. a group of common basis vectors in the two feature spaces of the teacher and the student detectors, i.e., global knowledge. Then, the distilling algorithm can be applied as space alignment. To this end, a novel prototype generation module (PGM) is proposed to find the common basis vectors, dubbed prototypes, in the two feature spaces. Then, a robust distilling module (RDM) is applied to construct the global knowledge based on the prototypes and filtrate noisy global and local knowledge by measuring the discrepancy of the representations in two feature spaces. Experiments with Faster-RCNN and RetinaNet on PASCAL and COCO datasets show that our method achieves the best performance for distilling object detectors with various backbones, which even surpasses the performance of the teacher model. We also show that the existing methods can be easily combined with global knowledge and obtain further improvement. Code is available: https://github.com/hikvision-research/DAVAR-Lab-ML.

arXiv:2210.08086공식 코드 · Papers with Code

Knowledge Distillation approach towards Melanoma Detection

Melanoma is regarded as the most threatening among all skin cancers. There is a pressing need to build systems which can aid in the early detection of melanoma and enable timely treatment to patients. Recent methods are geared towards machine learning based systems where the task is posed as image recognition, tag dermoscopic images of skin lesions as melanoma or non-melanoma. Even though these methods show promising results in terms of accuracy, they are computationally quite expensive to train, that questions the ability of these models to be deployable in a clinical setting or memory constraint devices. To address this issue, we focus on building simple and performant models having few layers, less than ten compared to hundreds. As well as with fewer learnable parameters, 0.26 million (M) compared to 42.5M using knowledge distillation with the goal to detect melanoma from dermoscopic images. First, we train a teacher model using a ResNet-50 to detect melanoma. Using the teacher model, we train the student model known as Distilled Student Network (DSNet) which has around 0.26M parameters using knowledge distillation achieving an accuracy of 91.7%. We compare against ImageNet pre-trained models such MobileNet, VGG-16, Inception-V3, EfficientNet-B0, ResNet-50 and ResNet-101. We find that our approach works well in terms of inference runtime compared to other pre-trained models, 2.57 seconds compared to 14.55 seconds. We find that DSNet (0.26M parameters), which is 15 times smaller, consistently performs better than EfficientNet-B0 (4M parameters) in both melanoma and non-melanoma detection across Precision, Recall and F1 scores

arXiv:2210.07978공식 코드 · Papers with Code

Improving generalizability of distilled self-supervised speech processing models under distorted settings

Self-supervised learned (SSL) speech pre-trained models perform well across various speech processing tasks. Distilled versions of SSL models have been developed to match the needs of on-device speech applications. Though having similar performance as original SSL models, distilled counterparts suffer from performance degradation even more than their original versions in distorted environments. This paper proposes to apply Cross-Distortion Mapping and Domain Adversarial Training to SSL models during knowledge distillation to alleviate the performance gap caused by the domain mismatch problem. Results show consistent performance improvements under both in- and out-of-domain distorted setups for different downstream tasks while keeping efficient model size.

arXiv:2210.07795공식 코드 · Papers with Code

EfficientVLM: Fast and Accurate Vision-Language Models via Knowledge Distillation and Modal-adaptive Pruning

Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and deployment in real-world applications due to space, memory, and latency constraints. In this work, we introduce a distilling then pruning framework to compress large vision-language models into smaller, faster, and more accurate ones. We first shrink the size of a pre-trained large VLM and apply knowledge distillation in the vision-language pre-training stage to obtain a task-agnostic compact VLM. Then we propose a modal-adaptive pruning algorithm to automatically infer the importance of vision and language modalities for different downstream tasks and adaptively remove redundant structures and neurons in different encoders with controllable target sparsity. We apply our framework to train EfficientVLM, a fast and accurate vision-language model consisting of 6 vision layers, 3 text layers, and 3 cross-modal fusion layers, accounting for only 93 million parameters in total, which is 44.3% of the teacher model. EfficientVLM retains 98.4% performance of the teacher model and accelerates its inference speed by 2.2x. EfficientVLM achieves a large absolute improvement over previous SoTA efficient VLMs of similar sizes by a large margin on various vision-language tasks, including VQAv2 (+4.9%), NLVR2 (+5.6%), ITR (R@1 on TR +17.2%, on IR + 15.6% ) and COCO caption generation (CIDEr +6.5), demonstrating a large potential on training lightweight VLMs.

arXiv:2210.07686공식 코드 · Papers with Code

Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation

Recent neural methods for vehicle routing problems always train and test the deep models on the same instance distribution (i.e., uniform). To tackle the consequent cross-distribution generalization concerns, we bring the knowledge distillation to this field and propose an Adaptive Multi-Distribution Knowledge Distillation (AMDKD) scheme for learning more generalizable deep models. Particularly, our AMDKD leverages various knowledge from multiple teachers trained on exemplar distributions to yield a light-weight yet generalist student model. Meanwhile, we equip AMDKD with an adaptive strategy that allows the student to concentrate on difficult distributions, so as to absorb hard-to-master knowledge more effectively. Extensive experimental results show that, compared with the baseline neural methods, our AMDKD is able to achieve competitive results on both unseen in-distribution and out-of-distribution instances, which are either randomly synthesized or adopted from benchmark datasets (i.e., TSPLIB and CVRPLIB). Notably, our AMDKD is generic, and consumes less computational resources for inference.

arXiv:2210.06297공식 코드 · Papers with Code

Multimodality Multi-Lead ECG Arrhythmia Classification using Self-Supervised Learning

Electrocardiogram (ECG) signal is one of the most effective sources of information mainly employed for the diagnosis and prediction of cardiovascular diseases (CVDs) connected with the abnormalities in heart rhythm. Clearly, single modality ECG (i.e. time series) cannot convey its complete characteristics, thus, exploiting both time and time-frequency modalities in the form of time-series data and spectrogram is needed. Leveraging the cutting-edge self-supervised learning (SSL) technique on unlabeled data, we propose SSL-based multimodality ECG classification. Our proposed network follows SSL learning paradigm and consists of two modules corresponding to pre-stream task, and down-stream task, respectively. In the SSL-pre-stream task, we utilize self-knowledge distillation (KD) techniques with no labeled data, on various transformations and in both time and frequency domains. In the down-stream task, which is trained on labeled data, we propose a gate fusion mechanism to fuse information from multimodality.To evaluate the effectiveness of our approach, ten-fold cross validation on the 12-lead PhysioNet 2020 dataset has been conducted.

arXiv:2210.06020공식 코드 · Papers with Code

Integrating Translation Memories into Non-Autoregressive Machine Translation

Non-autoregressive machine translation (NAT) has recently made great progress. However, most works to date have focused on standard translation tasks, even though some edit-based NAT models, such as the Levenshtein Transformer (LevT), seem well suited to translate with a Translation Memory (TM). This is the scenario considered here. We first analyze the vanilla LevT model and explain why it does not do well in this setting. We then propose a new variant, TM-LevT, and show how to effectively train this model. By modifying the data presentation and introducing an extra deletion operation, we obtain performance that are on par with an autoregressive approach, while reducing the decoding load. We also show that incorporating TMs during training dispenses to use knowledge distillation, a well-known trick used to mitigate the multimodality issue.

arXiv:2210.06458공식 코드 · Papers with Code

Efficient Knowledge Distillation from Model Checkpoints

Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers). As empirically there exists a strong correlation between the performance of teacher and student models, it is commonly believed that a high performing teacher is preferred. Consequently, practitioners tend to use a well trained network or an ensemble of them as the teacher. In this paper, we make an intriguing observation that an intermediate model, i.e., a checkpoint in the middle of the training procedure, often serves as a better teacher compared to the fully converged model, although the former has much lower accuracy. More surprisingly, a weak snapshot ensemble of several intermediate models from a same training trajectory can outperform a strong ensemble of independently trained and fully converged models, when they are used as teachers. We show that this phenomenon can be partially explained by the information bottleneck principle: the feature representations of intermediate models can have higher mutual information regarding the input, and thus contain more "dark knowledge" for effective distillation. We further propose an optimal intermediate teacher selection algorithm based on maximizing the total task-related mutual information. Experiments verify its effectiveness and applicability.

arXiv:2210.05508공식 코드 · Papers with Code

Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data

Machine Learning (ML) is changing DBs as many DB components are being replaced by ML models. One open problem in this setting is how to update such ML models in the presence of data updates. We start this investigation focusing on data insertions (dominating updates in analytical DBs). We study how to update neural network (NN) models when new data follows a different distribution (a.k.a. it is "out-of-distribution" -- OOD), rendering previously-trained NNs inaccurate. A requirement in our problem setting is that learned DB components should ensure high accuracy for tasks on old and new data (e.g., for approximate query processing (AQP), cardinality estimation (CE), synthetic data generation (DG), etc.). This paper proposes a novel updatability framework (DDUp). DDUp can provide updatability for different learned DB system components, even based on different NNs, without the high costs to retrain the NNs from scratch. DDUp entails two components: First, a novel, efficient, and principled statistical-testing approach to detect OOD data. Second, a novel model updating approach, grounded on the principles of transfer learning with knowledge distillation, to update learned models efficiently, while still ensuring high accuracy. We develop and showcase DDUp's applicability for three different learned DB components, AQP, CE, and DG, each employing a different type of NN. Detailed experimental evaluation using real and benchmark datasets for AQP, CE, and DG detail DDUp's performance advantages.

arXiv:2210.05638공식 코드 · Papers with Code

APSNet: Attention Based Point Cloud Sampling

Processing large point clouds is a challenging task. Therefore, the data is often downsampled to a smaller size such that it can be stored, transmitted and processed more efficiently without incurring significant performance degradation. Traditional task-agnostic sampling methods, such as farthest point sampling (FPS), do not consider downstream tasks when sampling point clouds, and thus non-informative points to the tasks are often sampled. This paper explores a task-oriented sampling for 3D point clouds, and aims to sample a subset of points that are tailored specifically to a downstream task of interest. Similar to FPS, we assume that point to be sampled next should depend heavily on the points that have already been sampled. We thus formulate point cloud sampling as a sequential generation process, and develop an attention-based point cloud sampling network (APSNet) to tackle this problem. At each time step, APSNet attends to all the points in a cloud by utilizing the history of previously sampled points, and samples the most informative one. Both supervised learning and knowledge distillation-based self-supervised learning of APSNet are proposed. Moreover, joint training of APSNet over multiple sample sizes is investigated, leading to a single APSNet that can generate arbitrary length of samples with prominent performances. Extensive experiments demonstrate the superior performance of APSNet against state-of-the-arts in various downstream tasks, including 3D point cloud classification, reconstruction, and registration.

arXiv:2210.05391공식 코드 · Papers with Code

PP-StructureV2: A Stronger Document Analysis System

A large amount of document data exists in unstructured form such as raw images without any text information. Designing a practical document image analysis system is a meaningful but challenging task. In previous work, we proposed an intelligent document analysis system PP-Structure. In order to further upgrade the function and performance of PP-Structure, we propose PP-StructureV2 in this work, which contains two subsystems: Layout Information Extraction and Key Information Extraction. Firstly, we integrate Image Direction Correction module and Layout Restoration module to enhance the functionality of the system. Secondly, 8 practical strategies are utilized in PP-StructureV2 for better performance. For Layout Analysis model, we introduce ultra light-weight detector PP-PicoDet and knowledge distillation algorithm FGD for model lightweighting, which increased the inference speed by 11 times with comparable mAP. For Table Recognition model, we utilize PP-LCNet, CSP-PAN and SLAHead to optimize the backbone module, feature fusion module and decoding module, respectively, which improved the table structure accuracy by 6\% with comparable inference speed. For Key Information Extraction model, we introduce VI-LayoutXLM which is a visual-feature independent LayoutXLM architecture, TB-YX sorting algorithm and U-DML knowledge distillation algorithm, which brought 2.8\% and 9.1\% improvement respectively on the Hmean of Semantic Entity Recognition and Relation Extraction tasks. All the above mentioned models and code are open-sourced in the GitHub repository PaddleOCR.

arXiv:2210.05280공식 코드 · Papers with Code

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

Recently, Cross-Domain Few-Shot Learning (CD-FSL) which aims at addressing the Few-Shot Learning (FSL) problem across different domains has attracted rising attention. The core challenge of CD-FSL lies in the domain gap between the source and novel target datasets. Though many attempts have been made for CD-FSL without any target data during model training, the huge domain gap makes it still hard for existing CD-FSL methods to achieve very satisfactory results. Alternatively, learning CD-FSL models with few labeled target domain data which is more realistic and promising is advocated in previous work~\cite{fu2021meta}. Thus, in this paper, we stick to this setting and technically contribute a novel Multi-Expert Domain Decompositional Network (ME-D2N). Concretely, to solve the data imbalance problem between the source data with sufficient examples and the auxiliary target data with limited examples, we build our model under the umbrella of multi-expert learning. Two teacher models which can be considered to be experts in their corresponding domain are first trained on the source and the auxiliary target sets, respectively. Then, the knowledge distillation technique is introduced to transfer the knowledge from two teachers to a unified student model. Taking a step further, to help our student model learn knowledge from different domain teachers simultaneously, we further present a novel domain decomposition module that learns to decompose the student model into two domain-related sub parts. This is achieved by a novel domain-specific gate that learns to assign each filter to only one specific domain in a learnable way. Extensive experiments demonstrate the effectiveness of our method. Codes and models are available at https://github.com/lovelyqian/ME-D2N_for_CDFSL.

arXiv:2210.05521공식 코드 · Papers with Code

Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval

Inverted file structure is a common technique for accelerating dense retrieval. It clusters documents based on their embeddings; during searching, it probes nearby clusters w.r.t. an input query and only evaluates documents within them by subsequent codecs, thus avoiding the expensive cost of exhaustive traversal. However, the clustering is always lossy, which results in the miss of relevant documents in the probed clusters and hence degrades retrieval quality. In contrast, lexical matching, such as overlaps of salient terms, tends to be strong feature for identifying relevant documents. In this work, we present the Hybrid Inverted Index (HI$^2$), where the embedding clusters and salient terms work collaboratively to accelerate dense retrieval. To make best of both effectiveness and efficiency, we devise a cluster selector and a term selector, to construct compact inverted lists and efficiently searching through them. Moreover, we leverage simple unsupervised algorithms as well as end-to-end knowledge distillation to learn these two modules, with the latter further boosting the effectiveness. Based on comprehensive experiments on popular retrieval benchmarks, we verify that clusters and terms indeed complement each other, enabling HI$^2$ to achieve lossless retrieval quality with competitive efficiency across various index settings. Our code and checkpoint are publicly available at https://github.com/namespace-Pt/Adon/tree/HI2.

arXiv:2210.05185공식 코드 · Papers with Code

Meta-Learning with Self-Improving Momentum Target

The idea of using a separately trained target model (or teacher) to improve the performance of the student model has been increasingly popular in various machine learning domains, and meta-learning is no exception; a recent discovery shows that utilizing task-wise target models can significantly boost the generalization performance. However, obtaining a target model for each task can be highly expensive, especially when the number of tasks for meta-learning is large. To tackle this issue, we propose a simple yet effective method, coined Self-improving Momentum Target (SiMT). SiMT generates the target model by adapting from the temporal ensemble of the meta-learner, i.e., the momentum network. This momentum network and its task-specific adaptations enjoy a favorable generalization performance, enabling self-improving of the meta-learner through knowledge distillation. Moreover, we found that perturbing parameters of the meta-learner, e.g., dropout, further stabilize this self-improving process by preventing fast convergence of the distillation loss during meta-training. Our experimental results demonstrate that SiMT brings a significant performance gain when combined with a wide range of meta-learning methods under various applications, including few-shot regression, few-shot classification, and meta-reinforcement learning. Code is available at https://github.com/jihoontack/SiMT.