Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userDiff-ResNets for Few-shot Learning -- an ODE Perspective
51
0
0.0
(
0
)
Added by
Tangjun Wang
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Interpreting deep neural networks from the ordinary differential equations (ODEs) perspective has inspired many efficient and robust network architectures. However, existing ODE based approaches ignore the relationship among data points, which is a critical component in many problems including few-shot learning and semi-supervised learning. In this paper, inspired by the diffusive ODEs, we propose a novel diffusion residual network (Diff-ResNet) to strengthen the interactions among data points. Under the structured data assumption, it is proved that the diffusion mechanism can decrease the distance-diameter ratio that improves the separability of inter-class points and reduces the distance among local intra-class points. This property can be easily adopted by the residual networks for constructing the separable hyperplanes. The synthetic binary classification experiments demonstrate the effectiveness of the proposed diffusion mechanism. Moreover, extensive experiments of few-shot image classification and semi-supervised graph node classification in various datasets validate the advantages of the proposed Diff-ResNet over existing few-shot learning methods.
rate research
Read More
Few-Shot Learning (FSL) is a challenging task, i.e., how to recognize novel classes with few examples? Pre-training based methods effectively tackle the problem by pre-training a feature extractor and then predict novel classes via a nearest neighbor classifier with mean-based prototypes. Nevertheless, due to the data scarcity, the mean-based prototypes are usually biased. In this paper, we diminish the bias by regarding it as a prototype optimization problem. Although the existing meta-optimizers can also be applied for the optimization, they all overlook a crucial gradient bias issue, i.e., the mean-based gradient estimation is also biased on scarce data. Consequently, we regard the gradient itself as meta-knowledge and then propose a novel prototype optimization-based meta-learning framework, called MetaNODE. Specifically, we first regard the mean-based prototypes as initial prototypes, and then model the process of prototype optimization as continuous-time dynamics specified by a Neural Ordinary Differential Equation (Neural ODE). A gradient flow inference network is carefully designed to learn to estimate the continuous gradients for prototype dynamics. Finally, the optimal prototypes can be obtained by solving the Neural ODE using the Runge-Kutta method. Extensive experiments demonstrate that our proposed method obtains superior performance over the previous state-of-the-art methods. Our code will be publicly available upon acceptance.
We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal Model (SCM) for the causalities among the pre-trained knowledge, sample features, and labels. Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view. It is worth noting that the contribution of IFSL is orthogonal to existing fine-tuning and meta-learning based FSL methods, hence IFSL can improve all of them, achieving a new 1-/5-shot state-of-the-art on textit{mini}ImageNet, textit{tiered}ImageNet, and cross-domain CUB. Code is released at https://github.com/yue-zhongqi/ifsl.
We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the orthogonal group O(d). This nested system of two flows, where the parameter-flow is constrained to lie on the compact manifold, provides stability and effectiveness of training and provably solves the gradient vanishing-explosion problem which is intrinsically related to training deep neural network architectures such as Neural ODEs. Consequently, it leads to better downstream models, as we show on the example of training reinforcement learning policies with evolution strategies, and in the supervised learning setting, by comparing with previous SOTA baselines. We provide strong convergence results for our proposed mechanism that are independent of the depth of the network, supporting our empirical studies. Our results show an intriguing connection between the theory of deep neural networks and the field of matrix flows on compact manifolds.
In this paper we present the first baseline results for the task of few-shot learning of discrete embedding vectors for image recognition. Few-shot learning is a highly researched task, commonly leveraged by recognition systems that are resource constrained to train on a small number of images per class. Few-shot systems typically store a continuous embedding vector of each class, posing a risk to privacy where system breaches or insider threats are a concern. Using discrete embedding vectors, we devise a simple cryptographic protocol, which uses one-way hash functions in order to build recognition systems that do not store their users embedding vectors directly, thus providing the guarantee of computational pan privacy in a practical and wide-spread setting.
We propose a transductive Laplacian-regularized inference for few-shot tasks. Given any feature embedding learned from the base classes, we minimize a quadratic binary-assignment function containing two terms: (1) a unary term assigning query samples to the nearest class prototype, and (2) a pairwise Laplacian term encouraging nearby query samples to have consistent label assignments. Our transductive inference does not re-train the base model, and can be viewed as a graph clustering of the query set, subject to supervision constraints from the support set. We derive a computationally efficient bound optimizer of a relaxation of our function, which computes independent (parallel) updates for each query sample, while guaranteeing convergence. Following a simple cross-entropy training on the base classes, and without complex meta-learning strategies, we conducted comprehensive experiments over five few-shot learning benchmarks. Our LaplacianShot consistently outperforms state-of-the-art methods by significant margins across different models, settings, and data sets. Furthermore, our transductive inference is very fast, with computational times that are close to inductive inference, and can be used for large-scale few-shot tasks.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
