Cross-Domain Few-Shot Graph Classification with a Reinforced Task Coordinator

نویسندگان

چکیده

Cross-domain graph few-shot learning attempts to address the prevalent data scarcity issue in mining problems. However, utilization of cross-domain induces another intractable domain shift which severely degrades generalization ability models. The combat with is hindered due coarse source domains and ignorance accessible prompts. To these challenges, this paper, we design a novel Task Coordinator leverage small set labeled target as prompt tasks, then model association discover relevance between meta-tasks from tasks. Based on discovered relevance, our achieves adaptive task selection enables optimization learner using selected fine-grained meta-tasks. Extensive experiments conducted molecular property prediction benchmarks validate effectiveness proposed method by comparing it state-of-the-art baselines.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Few-Shot Learning with Graph Neural Networks

We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic message-passing inference algorithms with their neural-network counterparts, we define a graph neural network architecture that generalizes several of the recentl...

متن کامل

Few-Shot Adversarial Domain Adaptation

This work provides a framework for addressing the problem of supervised domain adaptation with deep models. The main idea is to exploit adversarial learning to learn an embedded subspace that simultaneously maximizes the confusion between two domains while semantically aligning their embedding. The supervised setting becomes attractive especially when there are only a few target data samples th...

متن کامل

Few-shot Classification by Learning Disentangled Representations

Machine learning has improved state-of-the art performance in numerous domains, by using large amounts of data. In reality, labelled data is often not available for the task of interest. A fundamental problem of artificial intelligence is finding a representation that can generalize to never seen before classes. In this research, the power of generative models is combined with disentangled repr...

متن کامل

Few-to-few Cross-domain Object Matching

Cross-domain object matching refers to the task of inferring unknown alignment between objects in two data collections that do not have a shared data representation. In recent years several methods have been proposed for solving the special case that assumes each object is to be paired with exactly one object, resulting in a constrained optimization problem over permutations. A related problem ...

متن کامل

Meta-Learning for Semi-Supervised Few-Shot Classification

In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained on episodes representing different classification problems, each with a small labeled training set and its corres...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence

سال: 2023

ISSN: ['2159-5399', '2374-3468']

DOI: https://doi.org/10.1609/aaai.v37i4.25615