We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data, such as irregular samples, missing data, or unaligned measurements from multiple sensors. Our method relies on a continuous-time-dependent model of the series' evolution dynamics. It leverages adaptations of conditional, implicit neural representations for sequential data. A modulation mechanism, driven by a meta-learning algorithm, allows adaptation to unseen samples and extrapolation beyond observed time-windows for long-term predictions. The model provides a highly flexible and unified framework for imputation and forecasting tasks across a wide range of challenging scenarios. It achieves state-of-the-art performance on classical benchmarks and outperforms alternative time-continuous models.
Few-shot meta-learning presents a challenge for gradient descent optimization due to the limited number of training samples per task. To address this issue, we propose an episodic memory optimization for meta-learning, we call EMO, which is inspired by the human ability to recall past learning experiences from the brain's memory. EMO retains the gradient history of past experienced tasks in external memory, enabling few-shot learning in a memory-augmented way. By learning to retain and recall the learning process of past training tasks, EMO nudges parameter updates in the right direction, even when the gradients provided by a limited number of examples are uninformative. We prove theoretically that our algorithm converges for smooth, strongly convex objectives. EMO is generic, flexible, and model-agnostic, making it a simple plug-and-play optimizer that can be seamlessly embedded into existing optimization-based few-shot meta-learning approaches. Empirical results show that EMO scales well with most few-shot classification benchmarks and improves the performance of optimization-based meta-learning methods, resulting in accelerated convergence.
In-context learning (ICL) is one of the surprising and useful features of large language models and subject of intense research. Recently, stylized meta-learning-like ICL setups have been devised that train transformers on sequences of input-output pairs $(x, f(x))$. The function $f$ comes from a function class and generalization is checked by evaluating on sequences generated from unseen functions from the same class. One of the main discoveries in this line of research has been that for several function classes, such as linear regression, transformers successfully generalize to new functions in the class. However, the inductive biases of these models resulting in this behavior are not clearly understood. A model with unlimited training data and compute is a Bayesian predictor: it learns the pretraining distribution. In this paper we empirically examine how far this Bayesian perspective can help us understand ICL. To this end, we generalize the previous meta-ICL setup to hierarchical meta-ICL setup which involve unions of multiple task families. We instantiate this setup on a diverse range of linear and nonlinear function families and find that transformers can do ICL in this setting as well. Where Bayesian inference is tractable, we find evidence that high-capacity transformers mimic the Bayesian predictor. The Bayesian perspective provides insights into the inductive bias of ICL and how transformers perform a particular task when they are trained on multiple tasks. We also find that transformers can learn to generalize to new function classes that were not seen during pretraining. This involves deviation from the Bayesian predictor. We examine these deviations in more depth offering new insights and hypotheses.
The human brain constantly learns and rapidly adapts to new situations by integrating acquired knowledge and experiences into memory. Developing this capability in machine learning models is considered an important goal of AI research since deep neural networks perform poorly when there is limited data or when they need to adapt quickly to new unseen tasks. Meta-learning models are proposed to facilitate quick learning in low-data regimes by employing absorbed information from the past. Although some models have recently been introduced that reached high-performance levels, they are not biologically plausible. We have proposed a bio-plausible meta-learning model inspired by the hippocampus and the prefrontal cortex using spiking neural networks with a reward-based learning system. Our proposed model includes a memory designed to prevent catastrophic forgetting, a phenomenon that occurs when meta-learning models forget what they have learned as soon as the new task begins. Also, our new model can easily be applied to spike-based neuromorphic devices and enables fast learning in neuromorphic hardware. The final analysis will discuss the implications and predictions of the model for solving few-shot classification tasks. In solving these tasks, our model has demonstrated the ability to compete with the existing state-of-the-art meta-learning techniques.
Stochastic multi-level compositional optimization problems cover many new machine learning paradigms, e.g., multi-step model-agnostic meta-learning, which require efficient optimization algorithms for large-scale data. This paper studies the decentralized stochastic multi-level optimization algorithm, which is challenging because the multi-level structure and decentralized communication scheme may make the number of levels significantly affect the order of the convergence rate. To this end, we develop two novel decentralized optimization algorithms to optimize the multi-level compositional optimization problem. Our theoretical results show that both algorithms can achieve the level-independent convergence rate for nonconvex problems under much milder conditions compared with existing single-machine algorithms. To the best of our knowledge, this is the first work that achieves the level-independent convergence rate under the decentralized setting. Moreover, extensive experiments confirm the efficacy of our proposed algorithms.
Deep graph generative modeling has gained enormous attraction in recent years due to its impressive ability to directly learn the underlying hidden graph distribution. Despite their initial success, these techniques, like much of the existing deep generative methods, require a large number of training samples to learn a good model. Unfortunately, large number of training samples may not always be available in scenarios such as drug discovery for rare diseases. At the same time, recent advances in few-shot learning have opened door to applications where available training data is limited. In this work, we introduce the hitherto unexplored paradigm of few-shot graph generative modeling. Towards this, we develop GSHOT, a meta-learning based framework for few-shot labeled graph generative modeling. GSHOT learns to transfer meta-knowledge from similar auxiliary graph datasets. Utilizing these prior experiences, GSHOT quickly adapts to an unseen graph dataset through self-paced fine-tuning. Through extensive experiments on datasets from diverse domains having limited training samples, we establish that GSHOT generates graphs of superior fidelity compared to existing baselines.
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support set. As a result, it can perform well on tasks when the semantics of sampled classes are distinct while failing to differentiate classes with similar semantics. In this paper, we propose a novel Task-Adaptive Reference Transformation (TART) network, aiming to enhance the generalization by transforming the class prototypes to per-class fixed reference points in task-adaptive metric spaces. To further maximize divergence between transformed prototypes in task-adaptive metric spaces, TART introduces a discriminative reference regularization among transformed prototypes. Extensive experiments are conducted on four benchmark datasets and our method demonstrates clear superiority over the state-of-the-art models in all the datasets. In particular, our model surpasses the state-of-the-art method by 7.4% and 5.4% in 1-shot and 5-shot classification on the 20 Newsgroups dataset, respectively.
The paper explores how the human natural language structure can be seen as a product of evolution of inter-personal communication code, targeting maximisation of such culture-agnostic and cross-lingual metrics such as anti-entropy, compression factor and cross-split F1 score. The exploration is done as part of a larger unsupervised language learning effort, the attempt is made to perform meta-learning in a space of hyper-parameters maximising F1 score based on the "ground truth" language structure, by means of maximising the metrics mentioned above. The paper presents preliminary results of cross-lingual word-level segmentation tokenisation study for Russian, Chinese and English as well as subword segmentation or morphological parsing study for English. It is found that language structure form the word-level segmentation or tokenisation can be found as driven by all of these metrics, anti-entropy being more relevant to English and Russian while compression factor more specific for Chinese. The study for subword segmentation or morphological parsing on English lexicon has revealed straight connection between the compression been found to be associated with compression factor, while, surprising, the same connection with anti-entropy has turned to be the inverse.
This paper proposes Meta-SAGE, a novel approach for improving the scalability of deep reinforcement learning models for combinatorial optimization (CO) tasks. Our method adapts pre-trained models to larger-scale problems in test time by suggesting two components: a scale meta-learner (SML) and scheduled adaptation with guided exploration (SAGE). First, SML transforms the context embedding for subsequent adaptation of SAGE based on scale information. Then, SAGE adjusts the model parameters dedicated to the context embedding for a specific instance. SAGE introduces locality bias, which encourages selecting nearby locations to determine the next location. The locality bias gradually decays as the model is adapted to the target instance. Results show that Meta-SAGE outperforms previous adaptation methods and significantly improves scalability in representative CO tasks. Our source code is available at https://github.com/kaist-silab/meta-sage
Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple alternating (implicit) gradient-based algorithms can match the convergence rate of single-level gradient descent (GD) when addressing bilevel problems with a strongly convex lower-level objective. However, it remains unclear whether this result can be generalized to bilevel problems beyond this basic setting. In this paper, we first introduce a stationary metric for the considered bilevel problems, which generalizes the existing metric, for a nonconvex lower-level objective that satisfies the Polyak-{\L}ojasiewicz (PL) condition. We then propose a Generalized ALternating mEthod for bilevel opTimization (GALET) tailored to BLO with convex PL LL problem and establish that GALET achieves an $\epsilon$-stationary point for the considered problem within $\tilde{\cal O}(\epsilon^{-1})$ iterations, which matches the iteration complexity of GD for single-level smooth nonconvex problems.
Many hardware-aware neural architecture search (NAS) methods have been developed to optimize the topology of neural networks (NN) with the joint objectives of higher accuracy and lower latency. Recently, both accuracy and latency predictors have been used in NAS with great success, achieving high sample efficiency and accurate modeling of hardware (HW) device latency respectively. However, a new accuracy predictor needs to be trained for every new NAS search space or NN task, and a new latency predictor needs to be additionally trained for every new HW device. In this paper, we explore methods to enable multi-task, multi-search-space, and multi-HW adaptation of accuracy and latency predictors to reduce the cost of NAS. We introduce a novel search-space independent NN encoding based on zero-cost proxies that achieves sample-efficient prediction on multiple tasks and NAS search spaces, improving the end-to-end sample efficiency of latency and accuracy predictors by over an order of magnitude in multiple scenarios. For example, our NN encoding enables multi-search-space transfer of latency predictors from NASBench-201 to FBNet (and vice-versa) in under 85 HW measurements, a 400$\times$ improvement in sample efficiency compared to a recent meta-learning approach. Our method also improves the total sample efficiency of accuracy predictors by over an order of magnitude. Finally, we demonstrate the effectiveness of our method for multi-search-space and multi-task accuracy prediction on 28 NAS search spaces and tasks.
Transfer learning for extremely low resource languages is a challenging task as there is no large scale monolingual corpora for pre training or sufficient annotated data for fine tuning. We follow the work of MetaXL which suggests using meta learning for transfer learning from a single source language to an extremely low resource one. We propose an enhanced approach which uses multiple source languages chosen in a data driven manner. In addition, we introduce a sample selection strategy for utilizing the languages in training by using a multi armed bandit algorithm. Using both of these improvements we managed to achieve state of the art results on the NER task for the extremely low resource languages while using the same amount of data, making the representations better generalized. Also, due to the method ability to use multiple languages it allows the framework to use much larger amounts of data, while still having superior results over the former MetaXL method even with the same amounts of data.
Speaker identification systems are deployed in diverse environments, often different from the lab conditions on which they are trained and tested. In this paper, first, we show the problem of generalization using fixed thresholds (computed using EER metric) for imposter identification in unseen speaker recognition and then introduce a robust speaker-specific thresholding technique for better performance. Secondly, inspired by the recent use of meta-learning techniques in speaker verification, we propose an end-to-end meta-learning framework for imposter detection which decouples the problem of imposter detection from unseen speaker identification. Thus, unlike most prior works that use some heuristics to detect imposters, the proposed network learns to detect imposters by leveraging the utterances of the enrolled speakers. Furthermore, we show the efficacy of the proposed techniques on VoxCeleb1, VCTK and the FFSVC 2022 datasets, beating the baselines by up to 10%.
Prompt tuning for pre-trained masked language models (MLM) has shown promising performance in natural language processing tasks with few labeled examples. It tunes a prompt for the downstream task, and a verbalizer is used to bridge the predicted token and label prediction. Due to the limited training data, prompt initialization is crucial for prompt tuning. Recently, MetaPrompting (Hou et al., 2022) uses meta-learning to learn a shared initialization for all task-specific prompts. However, a single initialization is insufficient to obtain good prompts for all tasks and samples when the tasks are complex. Moreover, MetaPrompting requires tuning the whole MLM, causing a heavy burden on computation and memory as the MLM is usually large. To address these issues, we use a prompt pool to extract more task knowledge and construct instance-dependent prompts via attention. We further propose a novel soft verbalizer (RepVerb) which constructs label embedding from feature embeddings directly. Combining meta-learning the prompt pool and RepVerb, we propose MetaPrompter for effective structured prompting. MetaPrompter is parameter-efficient as only the pool is required to be tuned. Experimental results demonstrate that MetaPrompter performs better than the recent state-of-the-arts and RepVerb outperforms existing soft verbalizers.
Federated bilevel optimization (FBO) has shown great potential recently in machine learning and edge computing due to the emerging nested optimization structure in meta-learning, fine-tuning, hyperparameter tuning, etc. However, existing FBO algorithms often involve complicated computations and require multiple sub-loops per iteration, each of which contains a number of communication rounds. In this paper, we propose a simple and flexible FBO framework named SimFBO, which is easy to implement without sub-loops, and includes a generalized server-side aggregation and update for improving communication efficiency. We further propose System-level heterogeneity robust FBO (ShroFBO) as a variant of SimFBO with stronger resilience to heterogeneous local computation. We show that SimFBO and ShroFBO provably achieve a linear convergence speedup with partial client participation and client sampling without replacement, as well as improved sample and communication complexities. Experiments demonstrate the effectiveness of the proposed methods over existing FBO algorithms.
Learning heuristics for vehicle routing problems (VRPs) has gained much attention due to the less reliance on hand-crafted rules. However, existing methods are typically trained and tested on the same task with a fixed size and distribution (of nodes), and hence suffer from limited generalization performance. This paper studies a challenging yet realistic setting, which considers generalization across both size and distribution in VRPs. We propose a generic meta-learning framework, which enables effective training of an initialized model with the capability of fast adaptation to new tasks during inference. We further develop a simple yet efficient approximation method to reduce the training overhead. Extensive experiments on both synthetic and benchmark instances of the traveling salesman problem (TSP) and capacitated vehicle routing problem (CVRP) demonstrate the effectiveness of our method. The code is available at: https://github.com/RoyalSkye/Omni-VRP.
We propose the Taylorformer for random processes such as time series. Its two key components are: 1) the LocalTaylor wrapper which adapts Taylor approximations (used in dynamical systems) for use in neural network-based probabilistic models, and 2) the MHA-X attention block which makes predictions in a way inspired by how Gaussian Processes' mean predictions are linear smoothings of contextual data. Taylorformer outperforms the state-of-the-art in terms of log-likelihood on 5/6 classic Neural Process tasks such as meta-learning 1D functions, and has at least a 14\% MSE improvement on forecasting tasks, including electricity, oil temperatures and exchange rates. Taylorformer approximates a consistent stochastic process and provides uncertainty-aware predictions. Our code is provided in the supplementary material.
Neural processes are a family of probabilistic models that inherit the flexibility of neural networks to parameterize stochastic processes. Despite providing well-calibrated predictions, especially in regression problems, and quick adaptation to new tasks, the Gaussian assumption that is commonly used to represent the predictive likelihood fails to capture more complicated distributions such as multimodal ones. To overcome this limitation, we propose Conditional Quantile Neural Processes (CQNPs), a new member of the neural processes family, which exploits the attractive properties of quantile regression in modeling the distributions irrespective of their form. By introducing an extension of quantile regression where the model learns to focus on estimating informative quantiles, we show that the sampling efficiency and prediction accuracy can be further enhanced. Our experiments with real and synthetic datasets demonstrate substantial improvements in predictive performance compared to the baselines, and better modeling of heterogeneous distributions' characteristics such as multimodality.
This paper presents an effective and general data augmentation framework for medical image segmentation. We adopt a computationally efficient and data-efficient gradient-based meta-learning scheme to explicitly align the distribution of training and validation data which is used as a proxy for unseen test data. We improve the current data augmentation strategies with two core designs. First, we learn class-specific training-time data augmentation (TRA) effectively increasing the heterogeneity within the training subsets and tackling the class imbalance common in segmentation. Second, we jointly optimize TRA and test-time data augmentation (TEA), which are closely connected as both aim to align the training and test data distribution but were so far considered separately in previous works. We demonstrate the effectiveness of our method on four medical image segmentation tasks across different scenarios with two state-of-the-art segmentation models, DeepMedic and nnU-Net. Extensive experimentation shows that the proposed data augmentation framework can significantly and consistently improve the segmentation performance when compared to existing solutions. Code is publicly available.
This paper presents a method that can quickly adapt dynamic 3D avatars to arbitrary text descriptions of novel styles. Among existing approaches for avatar stylization, direct optimization methods can produce excellent results for arbitrary styles but they are unpleasantly slow. Furthermore, they require redoing the optimization process from scratch for every new input. Fast approximation methods using feed-forward networks trained on a large dataset of style images can generate results for new inputs quickly, but tend not to generalize well to novel styles and fall short in quality. We therefore investigate a new approach, AlteredAvatar, that combines those two approaches using the meta-learning framework. In the inner loop, the model learns to optimize to match a single target style well; while in the outer loop, the model learns to stylize efficiently across many styles. After training, AlteredAvatar learns an initialization that can quickly adapt within a small number of update steps to a novel style, which can be given using texts, a reference image, or a combination of both. We show that AlteredAvatar can achieve a good balance between speed, flexibility and quality, while maintaining consistency across a wide range of novel views and facial expressions.