PyTorchKR Papers

최신 논문

총 58편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2210.12067공식 코드 · Papers with Code

Efficient Dataset Distillation Using Random Feature Approximation

Dataset distillation compresses large datasets into smaller synthetic coresets which retain performance with the aim of reducing the storage and computational burden of processing the entire dataset. Today's best-performing algorithm, \textit{Kernel Inducing Points} (KIP), which makes use of the correspondence between infinite-width neural networks and kernel-ridge regression, is prohibitively slow due to the exact computation of the neural tangent kernel matrix, scaling $O(|S|^2)$, with $|S|$ being the coreset size. To improve this, we propose a novel algorithm that uses a random feature approximation (RFA) of the Neural Network Gaussian Process (NNGP) kernel, which reduces the kernel matrix computation to $O(|S|)$. Our algorithm provides at least a 100-fold speedup over KIP and can run on a single GPU. Our new method, termed an RFA Distillation (RFAD), performs competitively with KIP and other dataset condensation algorithms in accuracy over a range of large-scale datasets, both in kernel regression and finite-width network training. We demonstrate the effectiveness of our approach on tasks involving model interpretability and privacy preservation.

arXiv:2209.14987

No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy"

New methods designed to preserve data privacy require careful scrutiny. Failure to preserve privacy is hard to detect, and yet can lead to catastrophic results when a system implementing a ``privacy-preserving'' method is attacked. A recent work selected for an Outstanding Paper Award at ICML 2022 (Dong et al., 2022) claims that dataset condensation (DC) significantly improves data privacy when training machine learning models. This claim is supported by theoretical analysis of a specific dataset condensation technique and an empirical evaluation of resistance to some existing membership inference attacks. In this note we examine the claims in the work of Dong et al. (2022) and describe major flaws in the empirical evaluation of the method and its theoretical analysis. These flaws imply that their work does not provide statistically significant evidence that DC improves the privacy of training ML models over a naive baseline. Moreover, previously published results show that DP-SGD, the standard approach to privacy preserving ML, simultaneously gives better accuracy and achieves a (provably) lower membership attack success rate.

arXiv:2208.10494

Dataset Condensation with Latent Space Knowledge Factorization and Sharing

In this paper, we introduce a novel approach for systematically solving dataset condensation problem in an efficient manner by exploiting the regularity in a given dataset. Instead of condensing the dataset directly in the original input space, we assume a generative process of the dataset with a set of learnable codes defined in a compact latent space followed by a set of tiny decoders which maps them differently to the original input space. By combining different codes and decoders interchangeably, we can dramatically increase the number of synthetic examples with essentially the same parameter count, because the latent space is much lower dimensional and since we can assume as many decoders as necessary to capture different styles represented in the dataset with negligible cost. Such knowledge factorization allows efficient sharing of information between synthetic examples in a systematic way, providing far better trade-off between compression ratio and quality of the generated examples. We experimentally show that our method achieves new state-of-the-art records by significant margins on various benchmark datasets such as SVHN, CIFAR10, CIFAR100, and TinyImageNet.

arXiv:2208.00311

Delving into Effective Gradient Matching for Dataset Condensation

As deep learning models and datasets rapidly scale up, network training is extremely time-consuming and resource-costly. Instead of training on the entire dataset, learning with a small synthetic dataset becomes an efficient solution. Extensive research has been explored in the direction of dataset condensation, among which gradient matching achieves state-of-the-art performance. The gradient matching method directly targets the training dynamics by matching the gradient when training on the original and synthetic datasets. However, there are limited deep investigations into the principle and effectiveness of this method. In this work, we delve into the gradient matching method from a comprehensive perspective and answer the critical questions of what, how, and where to match. We propose to match the multi-level gradients to involve both intra-class and inter-class gradient information. We demonstrate that the distance function should focus on the angle, considering the magnitude simultaneously to delay the overfitting. An overfitting-aware adaptive learning step strategy is also proposed to trim unnecessary optimization steps for algorithmic efficiency improvement. Ablation and comparison experiments demonstrate that our proposed methodology shows superior accuracy, efficiency, and generalization compared to prior work.

arXiv:2207.09639공식 코드 · Papers with Code

DC-BENCH: Dataset Condensation Benchmark

Dataset Condensation is a newly emerging technique aiming at learning a tiny dataset that captures the rich information encoded in the original dataset. As the size of datasets contemporary machine learning models rely on becomes increasingly large, condensation methods become a prominent direction for accelerating network training and reducing data storage. Despite numerous methods have been proposed in this rapidly growing field, evaluating and comparing different condensation methods is non-trivial and still remains an open issue. The quality of condensed dataset are often shadowed by many critical contributing factors to the end performance, such as data augmentation and model architectures. The lack of a systematic way to evaluate and compare condensation methods not only hinders our understanding of existing techniques, but also discourages practical usage of the synthesized datasets. This work provides the first large-scale standardized benchmark on Dataset Condensation. It consists of a suite of evaluations to comprehensively reflect the generability and effectiveness of condensation methods through the lens of their generated dataset. Leveraging this benchmark, we conduct a large-scale study of current condensation methods, and report many insightful findings that open up new possibilities for future development. The benchmark library, including evaluators, baseline methods, and generated datasets, is open-sourced to facilitate future research and application.

arXiv:2206.07746공식 코드 · Papers with Code

Condensing Graphs via One-Step Gradient Matching

As training deep learning models on large dataset takes a lot of time and resources, it is desired to construct a small synthetic dataset with which we can train deep learning models sufficiently. There are recent works that have explored solutions on condensing image datasets through complex bi-level optimization. For instance, dataset condensation (DC) matches network gradients w.r.t. large-real data and small-synthetic data, where the network weights are optimized for multiple steps at each outer iteration. However, existing approaches have their inherent limitations: (1) they are not directly applicable to graphs where the data is discrete; and (2) the condensation process is computationally expensive due to the involved nested optimization. To bridge the gap, we investigate efficient dataset condensation tailored for graph datasets where we model the discrete graph structure as a probabilistic model. We further propose a one-step gradient matching scheme, which performs gradient matching for only one single step without training the network weights. Our theoretical analysis shows this strategy can generate synthetic graphs that lead to lower classification loss on real graphs. Extensive experiments on various graph datasets demonstrate the effectiveness and efficiency of the proposed method. In particular, we are able to reduce the dataset size by 90% while approximating up to 98% of the original performance and our method is significantly faster than multi-step gradient matching (e.g. 15x in CIFAR10 for synthesizing 500 graphs). Code is available at \url{https://github.com/amazon-research/DosCond}.

arXiv:2206.00240

Privacy for Free: How does Dataset Condensation Help Privacy?

To prevent unintentional data leakage, research community has resorted to data generators that can produce differentially private data for model training. However, for the sake of the data privacy, existing solutions suffer from either expensive training cost or poor generalization performance. Therefore, we raise the question whether training efficiency and privacy can be achieved simultaneously. In this work, we for the first time identify that dataset condensation (DC) which is originally designed for improving training efficiency is also a better solution to replace the traditional data generators for private data generation, thus providing privacy for free. To demonstrate the privacy benefit of DC, we build a connection between DC and differential privacy, and theoretically prove on linear feature extractors (and then extended to non-linear feature extractors) that the existence of one sample has limited impact ($O(m/n)$) on the parameter distribution of networks trained on $m$ samples synthesized from $n (n \gg m)$ raw samples by DC. We also empirically validate the visual privacy and membership privacy of DC-synthesized data by launching both the loss-based and the state-of-the-art likelihood-based membership inference attacks. We envision this work as a milestone for data-efficient and privacy-preserving machine learning.

arXiv:2205.14959공식 코드 · Papers with Code

Dataset Condensation via Efficient Synthetic-Data Parameterization

The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning. Recent studies on dataset condensation attempt to reduce the dependence on such massive data by synthesizing a compact training dataset. However, the existing approaches have fundamental limitations in optimization due to the limited representability of synthetic datasets without considering any data regularity characteristics. To this end, we propose a novel condensation framework that generates multiple synthetic data with a limited storage budget via efficient parameterization considering data regularity. We further analyze the shortcomings of the existing gradient matching-based condensation methods and develop an effective optimization technique for improving the condensation of training data information. We propose a unified algorithm that drastically improves the quality of condensed data against the current state-of-the-art on CIFAR-10, ImageNet, and Speech Commands.

arXiv:2204.07513공식 코드 · Papers with Code

Synthesizing Informative Training Samples with GAN

Remarkable progress has been achieved in synthesizing photo-realistic images with generative adversarial networks (GANs). Recently, GANs are utilized as the training sample generator when obtaining or storing real training data is expensive even infeasible. However, traditional GANs generated images are not as informative as the real training samples when being used to train deep neural networks. In this paper, we propose a novel method to synthesize Informative Training samples with GAN (IT-GAN). Specifically, we freeze a pre-trained GAN model and learn the informative latent vectors that correspond to informative training samples. The synthesized images are required to preserve information for training deep neural networks rather than visual reality or fidelity. Experiments verify that the deep neural networks can learn faster and achieve better performance when being trained with our IT-GAN generated images. We also show that our method is a promising solution to dataset condensation problem.

arXiv:2203.01531공식 코드 · Papers with Code

CAFE: Learning to Condense Dataset by Aligning Features

Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one. State-of-the-art approaches largely rely on learning the synthetic data by matching the gradients between the real and synthetic data batches. Despite the intuitive motivation and promising results, such gradient-based methods, by nature, easily overfit to a biased set of samples that produce dominant gradients, and thus lack global supervision of data distribution. In this paper, we propose a novel scheme to Condense dataset by Aligning FEatures (CAFE), which explicitly attempts to preserve the real-feature distribution as well as the discriminant power of the resulting synthetic set, lending itself to strong generalization capability to various architectures. At the heart of our approach is an effective strategy to align features from the real and synthetic data across various scales, while accounting for the classification of real samples. Our scheme is further backed up by a novel dynamic bi-level optimization, which adaptively adjusts parameter updates to prevent over-/under-fitting. We validate the proposed CAFE across various datasets, and demonstrate that it generally outperforms the state of the art: on the SVHN dataset, for example, the performance gain is up to 11%. Extensive experiments and analyses verify the effectiveness and necessity of proposed designs.

arXiv:2202.02916공식 코드 · Papers with Code

Dataset Condensation with Contrastive Signals

Recent studies have demonstrated that gradient matching-based dataset synthesis, or dataset condensation (DC), methods can achieve state-of-the-art performance when applied to data-efficient learning tasks. However, in this study, we prove that the existing DC methods can perform worse than the random selection method when task-irrelevant information forms a significant part of the training dataset. We attribute this to the lack of participation of the contrastive signals between the classes resulting from the class-wise gradient matching strategy. To address this problem, we propose Dataset Condensation with Contrastive signals (DCC) by modifying the loss function to enable the DC methods to effectively capture the differences between classes. In addition, we analyze the new loss function in terms of training dynamics by tracking the kernel velocity. Furthermore, we introduce a bi-level warm-up strategy to stabilize the optimization. Our experimental results indicate that while the existing methods are ineffective for fine-grained image classification tasks, the proposed method can successfully generate informative synthetic datasets for the same tasks. Moreover, we demonstrate that the proposed method outperforms the baselines even on benchmark datasets such as SVHN, CIFAR-10, and CIFAR-100. Finally, we demonstrate the high applicability of the proposed method by applying it to continual learning tasks.

arXiv:2201.05610

When less is more: Simplifying inputs aids neural network understanding

How do neural network image classifiers respond to simpler and simpler inputs? And what do such responses reveal about the learning process? To answer these questions, we need a clear measure of input simplicity (or inversely, complexity), an optimization objective that correlates with simplification, and a framework to incorporate such objective into training and inference. Lastly we need a variety of testbeds to experiment and evaluate the impact of such simplification on learning. In this work, we measure simplicity with the encoding bit size given by a pretrained generative model, and minimize the bit size to simplify inputs in training and inference. We investigate the effect of such simplification in several scenarios: conventional training, dataset condensation and post-hoc explanations. In all settings, inputs are simplified along with the original classification task, and we investigate the trade-off between input simplicity and task performance. For images with injected distractors, such simplification naturally removes superfluous information. For dataset condensation, we find that inputs can be simplified with almost no accuracy degradation. When used in post-hoc explanation, our learning-based simplification approach offers a valuable new tool to explore the basis of network decisions.

arXiv:2110.04181공식 코드 · Papers with Code

Dataset Condensation with Distribution Matching

Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets. A recent promising direction for reducing training cost is dataset condensation that aims to replace the original large training set with a significantly smaller learned synthetic set while preserving the original information. While training deep models on the small set of condensed images can be extremely fast, their synthesis remains computationally expensive due to the complex bi-level optimization and second-order derivative computation. In this work, we propose a simple yet effective method that synthesizes condensed images by matching feature distributions of the synthetic and original training images in many sampled embedding spaces. Our method significantly reduces the synthesis cost while achieving comparable or better performance. Thanks to its efficiency, we apply our method to more realistic and larger datasets with sophisticated neural architectures and obtain a significant performance boost. We also show promising practical benefits of our method in continual learning and neural architecture search.

arXiv:2102.08259공식 코드 · Papers with Code

Dataset Condensation with Differentiable Siamese Augmentation

In many machine learning problems, large-scale datasets have become the de-facto standard to train state-of-the-art deep networks at the price of heavy computation load. In this paper, we focus on condensing large training sets into significantly smaller synthetic sets which can be used to train deep neural networks from scratch with minimum drop in performance. Inspired from the recent training set synthesis methods, we propose Differentiable Siamese Augmentation that enables effective use of data augmentation to synthesize more informative synthetic images and thus achieves better performance when training networks with augmentations. Experiments on multiple image classification benchmarks demonstrate that the proposed method obtains substantial gains over the state-of-the-art, 7% improvements on CIFAR10 and CIFAR100 datasets. We show with only less than 1% data that our method achieves 99.6%, 94.9%, 88.5%, 71.5% relative performance on MNIST, FashionMNIST, SVHN, CIFAR10 respectively. We also explore the use of our method in continual learning and neural architecture search, and show promising results.

arXiv:2006.05929공식 코드 · Papers with Code

Dataset Condensation with Gradient Matching

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This paper proposes a training set synthesis technique for data-efficient learning, called Dataset Condensation, that learns to condense large dataset into a small set of informative synthetic samples for training deep neural networks from scratch. We formulate this goal as a gradient matching problem between the gradients of deep neural network weights that are trained on the original and our synthetic data. We rigorously evaluate its performance in several computer vision benchmarks and demonstrate that it significantly outperforms the state-of-the-art methods. Finally we explore the use of our method in continual learning and neural architecture search and report promising gains when limited memory and computations are available.

arXiv:2509.10367v2cs.LG

불일치 기반 데이터셋 응축 관점

A Discrepancy-Based Perspective on Dataset Condensation

유한 개의 원소로 이루어진 데이터셋 $\mathcal{T} = \{\mathbf{x}_i\}_{i = 1}^N$이 주어졌을 때, 데이터셋 응축(DC)의 목표는 ($M \ll N$)보다 훨씬 작은 합성 데이터셋 $\mathcal{S} = \{\tilde{\mathbf{x}}_j\}_{j = 1}^M$을 구성하여, $\mathcal{S}$에 대해 처음부터 학습한 모델이 $\mathcal{T}$에 대해 학습한 모델과 동등하거나 더 우수한 일반화 성능을 달성하도록 하는 것이다. DC의 최근 발전은 $\mathcal{T}$가 나타내는 데이터 분포를 축소된 점 집합으로 근사하는 문제와 밀접한 연관이 있음을 보여준다. 본 연구에서는 기존 DC 방법을 포괄하는 통합 프레임워크를 제시하고, DC의 과제 특정적 개념을 불일치(discrepancy) 개념을 이용한 보다 일반적이고 형식적인 정의로 확장한다. 불일치는 서로 다른 체제(regime)에서 확률 분포 간 거리를 정량화한다. 이 프레임워크는 DC의 목표를 일반화를 넘어 넓혀, 견고성(robustness), 프라이버시(privacy), 그 밖의 바람직한 성질과 같은 추가 목표를 수용한다.

arXiv:2607.09081v1cs.CV

행동 분할 데이터셋 압축을 위한 적응형 잠재 궤적 앵커링

Adaptive Latent Trajectory Anchoring for Action Segmentation Dataset Condensation

행동 분할을 위한 데이터셋 압축(dataset condensation)은 길고 다듬어지지 않은 비디오 데이터셋을 간결하고 정보가 풍부한 표현으로 합성한다. 기존 방법은 변분 오토인코더(Variational Autoencoder)와 반복적 잠재 최적화에 의존하며, 계산 비용이 크고 과도하게 평탄화된 재구성 및 경직된 시간적 제약이라는 문제를 겪는다. 본 논문은 압축 패러다임을 최적화 기반 역변환에서 결정론적 잠재 매핑으로 전환할 것을 제안한다. 노이즈 제거 확산 암묵 모델(Denoising Diffusion Implicit Models, DDIM)을 활용하여, 행동 구간을 노이즈 매니폴드 내 희소한 잠재 점들에 의해 앵커링된 연속 궤적으로 표현한다. 표현 효율을 극대화하기 위해, 구간별 재구성 난이도에 따라 앵커링 예산을 동적으로 재분배하는 적응형 할당 메커니즘을 도입한다. 광범위한 실험을 통해, 본 프레임워크가 주요 데이터셋에서 분할 성능 면에서 최신 기법들을 크게 능가함을 입증한다. 특히, 본 방법은 Breakfast 데이터셋에서 2.4%의 압축 비율을 유지하면서도 실제 데이터 학습과 동등한 성능을 달성한다.

arXiv:2606.05883v2cs.CV

디퓨전 모델 학습을 위한 기하학적 인식 데이터셋 축소

Geometry-Aware Dataset Condensation for Diffusion Model Training

데이터셋 축소(dataset condensation)는 합성이나 선택을 통해 실제 데이터로부터 소형 데이터셋을 구축하는 것을 목표로 합니다. 그러나 기존 접근 방식은 디퓨전 모델 학습에 적합하지 않습니다. 합성 데이터 생성은 종종 실제 모델링에 적합하지 않은 낮은 충실도(fidelity)의 샘플을 생성하는 반면, 실제 부분집합 선택은 디퓨전 가능도(likelihood) 목적 함수에 필요한 분포 기하학을 보존하는 데 실패하는 경우가 많습니다. 이를 해결하기 위해, 우리는 실제 부분집합 선택을 기하학적 인식 분포 정렬 문제로 재정의할 것을 제안합니다. 단측 부분 최적 전송(optimal transport)을 통합함으로써, 우리의 방법은 저밀도 영역에서 일치하지 않는 질량(mass)을 허용하면서 소형 부분집합을 전체 데이터 분포와 선택적으로 정렬하여, 효과적인 디퓨전 모델 학습에 필요한 기하학적 구조가 보존되도록 합니다. 분포 충실도를 더욱 보장하기 위해, 우리는 기하학적 정렬을 경량 특징(feature) 통계 및 의미론적 일관성 정규화(regularization)로 보완합니다. 이 정렬 목표를 달성하기 위해 효율적인 2단계 이산 최적화 전략을 제안합니다. 디퓨전 변종, 부분집합 크기, 이미지 해상도 및 학습 라운드에 걸친 광범위한 실험을 통해 우리의 방법이 디퓨전 모델 학습에서 우수한 충실도와 분포 커버리지를 달성함을 보여줍니다. 코드는 https://github.com/2018cx/GADC에서 확인할 수 있습니다.