The Ohio State University（俄亥俄州立大学）；Nanjing University（南京大学）；Cornell University（康奈尔大学）
Wei-Lun Chao, Han-Jia Ye, De-Chuan Zhan, Mark Campbell, Kilian Q. Weinberger
备注：
An extended version of the paper titled "A Meta Understanding of Meta-Learning" presented in ICML 2019 Workshop on Adaptive and Multitask Learning: Algorithms & Systems
Recent years have witnessed an abundance of new publications and approaches on meta-learning. This community-wide enthusiasm has sparked great insights but has also created a plethora of seemingly different frameworks, which can be hard to compare and evaluate. In this paper, we aim to provide a principled, unifying framework by revisiting and strengthening the connection between meta-learning and traditional supervised learning. By treating pairs of task-specific data sets and target models as (feature, label) samples, we can reduce many meta-learning algorithms to instances of supervised learning. This view not only unifies meta-learning into an intuitive and practical framework but also allows us to transfer insights from supervised learning directly to improve meta-learning. For example, we obtain a better understanding of generalization properties, and we can readily transfer well-understood techniques, such as model ensemble, pre-training, joint training, data augmentation, and even nearest neighbor based methods. We provide an intuitive analogy of these methods in the context of meta-learning and show that they give rise to significant improvements in model performance on few-shot learning.
University of Toronto（多伦多大学）；LG AI Research（LG人工智能研究院）
Online class-incremental continual learning (CL) studies the problem of learning new classes continually from an online non-stationary data stream, intending to adapt to new data while mitigating catastrophic forgetting. While memory replay has shown promising results, the recency bias in online learning caused by the commonly used Softmax classifier remains an unsolved challenge. Although the Nearest-Class-Mean (NCM) classifier is significantly undervalued in the CL community, we demonstrate that it is a simple yet effective substitute for the Softmax classifier. It addresses the recency bias…
Carnegie Mellon University（卡内基梅隆大学）；Hong Kong University of Science and Technology（香港科技大学）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）
The goal of few-shot learning is to learn a classifier that can recognize unseen classes from limited support data with labels. A common practice for this task is to train a model on the base set first and then transfer to novel classes through fine-tuning (Here fine-tuning procedure is defined as transferring knowledge from base to novel data, i.e. learning to transfer in few-shot scenario.) or meta-learning. However, as the base classes have no overlap to the novel set, simply transferring whole knowledge from base data is not an optimal solution since some knowledge in the base model may be…
Télécom ParisTech（巴黎高等电信学院）；Institute for Infocomm Research（信息通信研究院）；CentraleSupélec（中央理工-高等电力学院）；Nanyang Technological University（南洋理工大学）
GANS are powerful generative models that are able to model the manifold of natural images. We leverage this property to perform manifold regularization by approximating the Laplacian norm using a Monte Carlo approximation that is easily computed with the GAN. When incorporated into the feature-matching GAN of Improved GAN, we achieve state-of-the-art results for GAN-based semi-supervised learning on the CIFAR-10 dataset, with a method that is significantly easier to implement than competing methods.
Due to the high human cost of annotation, it is non-trivial to curate a large-scale medical dataset that is fully labeled for all classes of interest. Instead, it would be convenient to collect multiple small partially labeled datasets from different matching sources, where the medical images may have only been annotated for a subset of classes of interest. This paper offers an empirical understanding of an under-explored problem, namely partially supervised multi-label classification (PSMLC), where a multi-label classifier is trained with only partially labeled medical images. In contrast to …
In this paper we revisit the idea of pseudo-labeling in the context of semi-supervised learning where a learning algorithm has access to a small set of labeled samples and a large set of unlabeled samples. Pseudo-labeling works by applying pseudo-labels to samples in the unlabeled set by using a model trained on the combination of the labeled samples and any previously pseudo-labeled samples, and iteratively repeating this process in a self-training cycle. Current methods seem to have abandoned this approach in favor of consistency regularization methods that train models under a combination o…
Due to the need to store the intermediate activations for back-propagation, end-to-end (E2E) training of deep networks usually suffers from high GPUs memory footprint. This paper aims to address this problem by revisiting the locally supervised learning, where a network is split into gradient-isolated modules and trained with local supervision. We experimentally show that simply training local modules with E2E loss tends to collapse task-relevant information at early layers, and hence hurts the performance of the full model. To avoid this issue, we propose an information propagation (InfoPro) …
VSITE College for Information Technologies（VSITE信息技术学院）
Semi-supervised learning an attractive technique in practical deployments of deep models since it relaxes the dependence on labeled data. It is especially important in the scope of dense prediction because pixel-level annotation requires significant effort. This paper considers semi-supervised algorithms that enforce consistent predictions over perturbed unlabeled inputs. We study the advantages of perturbing only one of the two model instances and preventing the backward pass through the unperturbed instance. We also propose a competitive perturbation model as a composition of geometric warp …
We present a semi-supervised learning framework based on graph embeddings. Given a graph between instances, we train an embedding for each instance to jointly predict the class label and the neighborhood context in the graph. We develop both transductive and inductive variants of our method. In the transductive variant of our method, the class labels are determined by both the learned embeddings and input feature vectors, while in the inductive variant, the embeddings are defined as a parametric function of the feature vectors, so predictions can be made on instances not seen during training. …
Deep learning highly relies on the quantity of annotated data. However, the annotations for 3D volumetric medical data require experienced physicians to spend hours or even days for investigation. Self-supervised learning is a potential solution to get rid of the strong requirement of training data by deeply exploiting raw data information. In this paper, we propose a novel self-supervised learning framework for volumetric medical images. Specifically, we propose a context restoration task, i.e., Rubik's cube++, to pre-train 3D neural networks. Different from the existing context-restoration-b…
Revisiting Supervision for Continual Representation Learning
IDEAS NCBR；Warsaw University of Technology（华沙理工大学）；Gdańsk University of Technology（格但斯克理工大学）；Tooploox；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）
Remote-sensing (RS) Change Detection (CD) aims to detect "changes of interest" from co-registered bi-temporal images. The performance of existing deep supervised CD methods is attributed to the large amounts of annotated data used to train the networks. However, annotating large amounts of remote sensing images is labor-intensive and expensive, particularly with bi-temporal images, as it requires pixel-wise comparisons by a human expert. On the other hand, we often have access to unlimited unlabeled multi-temporal RS imagery thanks to ever-increasing earth observation programs. In this paper, …
Beijing Institute of Technology（北京理工大学）；Renmin University of China（中国人民大学）
Graph convolutional networks (GCNs) have achieved promising performance on various graph-based tasks. However they suffer from over-smoothing when stacking more layers. In this paper, we present a quantitative study on this observation and develop novel insights towards the deeper GCN. First, we interpret the current graph convolutional operations from an optimization perspective and argue that over-smoothing is mainly caused by the naive first-order approximation of the solution to the optimization problem. Subsequently, we introduce two metrics to measure the over-smoothing on node-level tas…
University of Bucharest（布加勒斯特大学）；SecurifAI（SecurifAI公司）；MBZ University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Aalborg University（奥尔堡大学）；Milestone Systems（Milestone Systems公司）；Geopipe Inc（Geopipe公司）；Linköping University（林雪平大学）
A self-supervised multi-task learning (SSMTL) framework for video anomaly detection was recently introduced in literature. Due to its highly accurate results, the method attracted the attention of many researchers. In this work, we revisit the self-supervised multi-task learning framework, proposing several updates to the original method. First, we study various detection methods, e.g. based on detecting high-motion regions using optical flow or background subtraction, since we believe the currently used pre-trained YOLOv3 is suboptimal, e.g. objects in motion or objects from unknown classes a…
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this paper, we first study how biases in the dataset affect existing methods. Our results show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets. Second, given the generality of the approach, we try to realize further gains with minor…
MetaMask: Revisiting Dimensional Confounder for Self-Supervised Learning
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)（南方海洋科学与工程广东省实验室（广州））；Gaoling School of Artificial Intelligence（高瓴人工智能学院）；Renmin University of China（中国人民大学）；Beijing Key Laboratory of Big Data Management and Analysis Methods（北京市大数据管理与分析方法重点实验室）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Guangzhou HKUST Fok Ying Tung Research Institute（广州香港科技大学霍英东研究院）
Collecting quality data from software projects can be time-consuming and expensive. Hence, some researchers explore "unsupervised" approaches to quality prediction that does not require labelled data. An alternate technique is to use "supervised" approaches that learn models from project data labelled with, say, "defective" or "not-defective". Most researchers use these supervised models since, it is argued, they can exploit more knowledge of the projects. At FSE'16, Yang et al. reported startling results where unsupervised defect predictors outperformed supervised predictors for effort-aware …
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI Research（脸书人工智能研究院）
Self-training is one of the earliest and simplest semi-supervised methods. The key idea is to augment the original labeled dataset with unlabeled data paired with the model's prediction (i.e. the pseudo-parallel data). While self-training has been extensively studied on classification problems, in complex sequence generation tasks (e.g. machine translation) it is still unclear how self-training works due to the compositionality of the target space. In this work, we first empirically show that self-training is able to decently improve the supervised baseline on neural sequence generation tasks.…
Warsaw University of Technology（华沙理工大学）；NASK - National Research Institute（NASK国家研究院）
Distance Metric Learning (DML) has attracted much attention in image processing in recent years. This paper analyzes its impact on supervised fine-tuning language models for Natural Language Processing (NLP) classification tasks under few-shot learning settings. We investigated several DML loss functions in training RoBERTa language models on known SentEval Transfer Tasks datasets. We also analyzed the possibility of using proxy-based DML losses during model inference. Our systematic experiments have shown that under few-shot learning settings, particularly proxy-based DML losses can positivel…
Subspace clustering is the classical problem of clustering a collection of data samples that approximately lie around several low-dimensional subspaces. The current state-of-the-art approaches for this problem are based on the self-expressive model which represents the samples as linear combination of other samples. However, these approaches require sufficiently well-spread samples for accurate representation which might not be necessarily accessible in many applications. In this paper, we shed light on this commonly neglected issue and argue that data distribution within each subspace plays a…
Beyond Templates: Revisiting Zero-Shot Remote Sensing through Meta-Prompting
Remote Sensing Lab, National Technical University of Athens（遥感实验室，国家技术大学雅典分校）；Remote Sensing Lab, Department of Engineering and Sciences, National Technical University of Athens（遥感实验室，工程与科学系，国家技术大学雅典分校）；Universitas Mercatorum（默卡托大学）
Recent progress in semi- and self-supervised learning has caused a rift in the long-held belief about the need for an enormous amount of labeled data for machine learning and the irrelevancy of unlabeled data. Although it has been successful in various data, there is no dominant semi- and self-supervised learning method that can be generalized for tabular data (i.e. most of the existing methods require appropriate tabular datasets and architectures). In this paper, we revisit self-training which can be applied to any kind of algorithm including the most widely used architecture, gradient boost…
Andalusian Institute of Data Science and Computational Intelligence（安达卢西亚数据科学与计算智能研究所）；University of Granada（格拉纳达大学）
Data Science and Machine Learning have become fundamental assets for companies and research institutions alike. As one of its fields, supervised classification allows for class prediction of new samples, learning from given training data. However, some properties can cause datasets to be problematic to classify. In order to evaluate a dataset a priori, data complexity metrics have been used extensively. They provide information regarding different intrinsic characteristics of the data, which serve to evaluate classifier compatibility and a course of action that improves performance. However, m…
Revisiting Non-separable Binary Classification and its Applications in Anomaly Detection
Georgia Institute of Technology（佐治亚理工学院）；School of Cybersecurity and Privacy（网络安全与隐私学院）；Lengo AI（Lengo AI公司）；School of Electrical and Computer Engineering（电气与计算机工程学院）；Apple（苹果公司）
School of Computer Communication Sciences（计算机与通信科学学院）
Nowadays, with the widespread of smartphones and other portable gadgets equipped with a variety of sensors, data is ubiquitous available and the focus of machine learning has shifted from being able to infer from small training samples to dealing with large scale high-dimensional data. In domains such as personal healthcare applications, which motivates this survey, distributed machine learning is a promising line of research, both for scaling up learning algorithms, but mostly for dealing with data which is inherently produced at different locations. This report offers a thorough overview of …
This paper briefly reviews the connections between meta-learning and self-supervised learning. Meta-learning can be applied to improve model generalization capability and to construct general AI algorithms. Self-supervised learning utilizes self-supervision from original data and extracts higher-level generalizable features through unsupervised pre-training or optimization of contrastive loss objectives. In self-supervised learning, data augmentation techniques are widely applied and data labels are not required since pseudo labels can be estimated from trained models on similar tasks. Meta-le…
Deep learning-based symbol detector gains increasing attention due to the simple algorithm design than the traditional model-based algorithms such as Viterbi and BCJR. The supervised learning framework is often employed to predict the input symbols, where training symbols are used to train the model. There are two major limitations in the supervised approaches: a) a model needs to be retrained from scratch when new train symbols come to adapt to a new channel status, and b) the length of the training symbols needs to be longer than a certain threshold to make the model generalize well on unsee…
