GPS: Genetic Prompt Search for Efficient Few-shot Learning

• URL: http://arxiv.org/abs/2210.17041v1
• Date: Mon, 31 Oct 2022 03:36:21 GMT
• Title: GPS: Genetic Prompt Search for Efficient Few-shot Learning
• Authors: Hanwei Xu, Yujun Chen, Yulun Du, Nan Shao, Yanggang Wang, Haiyu Li, Zhilin Yang
• Abstract summary: We introduce Genetic Prompt Search (GPS) to improve few-shot learning with prompts. GPS is gradient-free and requires no update of model parameters but only a small validation set. Our method is also better than other parameter-efficient tuning methods such as prompt tuning.
• Score: 15.28478657477945
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Prompt-based techniques have demostrated great potential for improving the few-shot generalization of pretrained language models. However, their performance heavily relies on the manual design of prompts and thus requires a lot of human efforts. In this paper, we introduce Genetic Prompt Search (GPS) to improve few-shot learning with prompts, which utilizes a genetic algorithm to automatically search for high-performing prompts. GPS is gradient-free and requires no update of model parameters but only a small validation set. Experiments on diverse datasets proved the effectiveness of GPS, which outperforms manual prompts by a large margin of 2.6 points. Our method is also better than other parameter-efficient tuning methods such as prompt tuning.

Related papers

• GPS: General Per-Sample Prompter [13.775690509818753]
  We propose GPS, the first general-purpose, per-sample prompting method.<n>GPS generates adaptive, input-specific prompts without extensive optimization and without access to a task-specific training set.
  arXiv  Detail & Related papers  (2025-11-18T18:10:09Z)
• Differentiable Prompt Learning for Vision Language Models [49.132774679968456]
  We propose a differentiable prompt learning method dubbed differentiable prompt learning (DPL) DPL is formulated as an optimization problem to automatically determine the optimal context length of the prompt to be added to each layer. We empirically find that by using only limited data, our DPL method can find deep continuous prompt configuration with high confidence.
  arXiv  Detail & Related papers  (2024-12-31T14:13:28Z)
• Adapting Vision-Language Models to Open Classes via Test-Time Prompt Tuning [50.26965628047682]
  Adapting pre-trained models to open classes is a challenging problem in machine learning. In this paper, we consider combining the advantages of both and come up with a test-time prompt tuning approach. Our proposed method outperforms all comparison methods on average considering both base and new classes.
  arXiv  Detail & Related papers  (2024-08-29T12:34:01Z)
• Visual Prompting for Generalized Few-shot Segmentation: A Multi-scale Approach [29.735863112700358]
  We study the effectiveness of prompting a transformer-decoder with learned visual prompts for the generalized few-shot segmentation (GFSS) task. Our goal is to achieve strong performance not only on novel categories with limited examples, but also to retain performance on base categories. We introduce a unidirectional causal attention mechanism between the novel prompts, learned with limited examples, and the base prompts, learned with abundant data.
  arXiv  Detail & Related papers  (2024-04-17T20:35:00Z)
• Test-Time Personalization with Meta Prompt for Gaze Estimation [23.01057994927244]
  We take inspiration from the recent advances in Natural Language Processing (NLP) by updating a negligible number of parameters, "prompts", at the test time. We propose to meta-learn the prompt to ensure that its updates align with the goal. Our experiments show that the meta-learned prompt can be effectively adapted even with a simple symmetry loss.
  arXiv  Detail & Related papers  (2024-01-03T07:02:35Z)
• Plum: Prompt Learning using Metaheuristic [28.024094195968672]
  We introduce metaheuristics, a branch of discrete non-visual optimization methods with over 100 options. Within our paradigm, we test six typical methods, demonstrating their effectiveness in white-box and black-box prompt learning. We show that these methods can be used to discover more human-understandable prompts, opening the door to a cornucopia of possibilities in prompt optimization.
  arXiv  Detail & Related papers  (2023-11-14T18:14:56Z)
• Generative Input: Towards Next-Generation Input Methods Paradigm [49.98958865125018]
  We propose a novel Generative Input paradigm named GeneInput. It uses prompts to handle all input scenarios and other intelligent auxiliary input functions, optimizing the model with user feedback to deliver personalized results. The results demonstrate that we have achieved state-of-the-art performance for the first time in the Full-mode Key-sequence to Characters(FK2C) task.
  arXiv  Detail & Related papers  (2023-11-02T12:01:29Z)
• Automatic Prompt Optimization with "Gradient Descent" and Beam Search [64.08364384823645]
  Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts. We propose a simple and nonparametric solution to this problem, Automatic Prompt Optimization (APO) APO uses minibatches of data to form natural language "gradients" that criticize the current prompt. The gradients are then "propagated" into the prompt by editing the prompt in the opposite semantic direction of the gradient.
  arXiv  Detail & Related papers  (2023-05-04T15:15:22Z)
• RPLKG: Robust Prompt Learning with Knowledge Graph [14.531071492983767]
  multimodal pre-trained models like CLIP have significantly boosted performance in various experiments.<n>Existing methods often lack interpretability and impose high computational costs.<n>We propose Robust Prompt Learning with Knowledge Graph (RPLKG) to curate diverse, interpretable prompt sets automatically.
  arXiv  Detail & Related papers  (2023-04-21T08:22:58Z)
• Toward Human Readable Prompt Tuning: Kubrick's The Shining is a good movie, and a good prompt too? [84.91689960190054]
  Large language models can perform new tasks in a zero-shot fashion, given natural language prompts. It is underexplored what factors make the prompts effective, especially when the prompts are natural language.
  arXiv  Detail & Related papers  (2022-12-20T18:47:13Z)
• Unified Vision and Language Prompt Learning [86.1530128487077]
  We present a systematic study on two representative prompt tuning methods, namely text prompt tuning and visual prompt tuning. A major finding is that text prompt tuning fails on data with high intra-class visual variances while visual prompt tuning cannot handle low inter-class variances. To combine the best from both worlds, we propose a simple approach called Unified Prompt Tuning (UPT), which essentially learns a tiny neural network to jointly optimize prompts across different modalities.
  arXiv  Detail & Related papers  (2022-10-13T17:50:24Z)
• Universal Prompt Tuning for Graph Neural Networks [10.250964386142819]
  We introduce a universal prompt-based tuning method called Graph Prompt Feature (GPF) for pre-trained GNN models under any pre-training strategy. GPF operates on the input graph's feature space and can theoretically achieve an equivalent effect to any form of prompting function. Our method significantly outperforms existing specialized prompt-based tuning methods when applied to models utilizing the pre-training strategy they specialize in.
  arXiv  Detail & Related papers  (2022-09-30T05:19:27Z)
• RLPrompt: Optimizing Discrete Text Prompts With Reinforcement Learning [84.75064077323098]
  This paper proposes RLPrompt, an efficient discrete prompt optimization approach with reinforcement learning (RL) RLPrompt is flexibly applicable to different types of LMs, such as masked gibberish (e.g., grammaBERT) and left-to-right models (e.g., GPTs) Experiments on few-shot classification and unsupervised text style transfer show superior performance over a wide range of existing finetuning or prompting methods.
  arXiv  Detail & Related papers  (2022-05-25T07:50:31Z)

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.