Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation

• URL: http://arxiv.org/abs/2407.19523v4
• Date: Mon, 06 Jan 2025 14:02:17 GMT
• Title: Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
• Authors: Cheems Wang, Yiqin Lv, Yixiu Mao, Yun Qu, Yi Xu, Xiangyang Ji,
• Abstract summary: We consider explicitly generative modeling task distributions placed over task identifiers. We propose robustifying fast adaptation from adversarial training. This work has practical implications, particularly in dealing with task distribution shifts in meta-learning.
• Score: 45.568230152488276
• License:
• Abstract: Meta-learning is a practical learning paradigm to transfer skills across tasks from a few examples. Nevertheless, the existence of task distribution shifts tends to weaken meta-learners' generalization capability, particularly when the training task distribution is naively hand-crafted or based on simple priors that fail to cover critical scenarios sufficiently. Here, we consider explicitly generative modeling task distributions placed over task identifiers and propose robustifying fast adaptation from adversarial training. Our approach, which can be interpreted as a model of a Stackelberg game, not only uncovers the task structure during problem-solving from an explicit generative model but also theoretically increases the adaptation robustness in worst cases. This work has practical implications, particularly in dealing with task distribution shifts in meta-learning, and contributes to theoretical insights in the field. Our method demonstrates its robustness in the presence of task subpopulation shifts and improved performance over SOTA baselines in extensive experiments. The code is available at the project site https://sites.google.com/view/ar-metalearn.

Related papers

• Beyond Any-Shot Adaptation: Predicting Optimization Outcome for Robustness Gains without Extra Pay [46.92143725900031]
  We present Model Predictive Task Sampling (MPTS) to establish connections between the task space and adaptation risk landscape. MPTS characterizes the task episodic information with a generative model and directly predicts task-specific adaptation risk values from posterior inference. MPTS can be seamlessly integrated into zero-shot, few-shot, and many-shot learning paradigms.
  arXiv  Detail & Related papers  (2025-01-19T13:14:53Z)
• Task Vectors in In-Context Learning: Emergence, Formation, and Benefit [17.72043522825441]
  We investigate the formation of task vectors in a controlled setting using models trained from scratch on synthetic datasets. Our findings confirm that task vectors naturally emerge under certain conditions, but the tasks may be relatively weakly and/or non-locally encoded within the model. To promote strong task vectors encoded at a prescribed location within the model, we propose an auxiliary training mechanism based on a task vector prompting loss.
  arXiv  Detail & Related papers  (2025-01-16T01:54:23Z)
• Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
  Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
  arXiv  Detail & Related papers  (2023-11-23T15:46:54Z)
• Towards Task Sampler Learning for Meta-Learning [37.02030832662183]
  Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task diversity will enhance the generalization ability of meta-learning models. This paper challenges this view through empirical and theoretical analysis.
  arXiv  Detail & Related papers  (2023-07-18T01:53:18Z)
• Algorithm Design for Online Meta-Learning with Task Boundary Detection [63.284263611646]
  We propose a novel algorithm for task-agnostic online meta-learning in non-stationary environments. We first propose two simple but effective detection mechanisms of task switches and distribution shift. We show that a sublinear task-averaged regret can be achieved for our algorithm under mild conditions.
  arXiv  Detail & Related papers  (2023-02-02T04:02:49Z)
• Fully Online Meta-Learning Without Task Boundaries [80.09124768759564]
  We study how meta-learning can be applied to tackle online problems of this nature. We propose a Fully Online Meta-Learning (FOML) algorithm, which does not require any ground truth knowledge about the task boundaries. Our experiments show that FOML was able to learn new tasks faster than the state-of-the-art online learning methods.
  arXiv  Detail & Related papers  (2022-02-01T07:51:24Z)
• A Channel Coding Benchmark for Meta-Learning [21.2424398453955]
  Several important issues in meta-learning have proven hard to study thus far. We propose the channel coding problem as a benchmark for meta-learning. Going forward, this benchmark provides a tool for the community to study the capabilities and limitations of meta-learning.
  arXiv  Detail & Related papers  (2021-07-15T19:37:43Z)
• Adaptive Task Sampling for Meta-Learning [79.61146834134459]
  Key idea of meta-learning for few-shot classification is to mimic the few-shot situations faced at test time. We propose an adaptive task sampling method to improve the generalization performance.
  arXiv  Detail & Related papers  (2020-07-17T03:15:53Z)
• Expert Training: Task Hardness Aware Meta-Learning for Few-Shot Classification [62.10696018098057]
  We propose an easy-to-hard expert meta-training strategy to arrange the training tasks properly. A task hardness aware module is designed and integrated into the training procedure to estimate the hardness of a task. Experimental results on the miniImageNet and tieredImageNetSketch datasets show that the meta-learners can obtain better results with our expert training strategy.
  arXiv  Detail & Related papers  (2020-07-13T08:49:00Z)
• Meta Adaptation using Importance Weighted Demonstrations [19.37671674146514]
  In some cases, the distribution shifts, so much, that it is difficult for an agent to infer the new task. We propose a novel algorithm to generalize on any related task by leveraging prior knowledge on a set of specific tasks. We show experiments where the robot is trained from a diversity of environmental tasks and is also able to adapt to an unseen environment.
  arXiv  Detail & Related papers  (2019-11-23T07:22:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.