相关论文: SEAL: Searching Expandable Architectures for Incre…

Deep learning methods typically depend on the availability of labeled data, which is expensive and time-consuming to obtain. Active learning addresses such effort by prioritizing which samples are best to annotate in order to maximize the…

Software flaw detection using multimodal deep learning models has been demonstrated as a very competitive approach on benchmark problems. In this work, we demonstrate that even better performance can be achieved using neural architecture…

Neural architecture search (NAS) methods rely on a search strategy for deciding which architectures to evaluate next and a performance estimation strategy for assessing their performance (e.g., using full evaluations, multi-fidelity…

Neural Architecture Search (NAS) is a collection of methods to craft the way neural networks are built. We apply this idea to Federated Learning (FL), wherein predefined neural network models are trained on the client/device data. This…

In neural architecture search, the structure of the neural network to best model a given dataset is determined by an automated search process. Efficient Neural Architecture Search (ENAS), proposed by Pham et al. (2018), has recently…

Deep learning methods have been successful in solving tasks in machine learning and have made breakthroughs in many sectors owing to their ability to automatically extract features from unstructured data. However, their performance relies…

Continual learning approaches help deep neural network models adapt and learn incrementally by trying to solve catastrophic forgetting. However, whether these existing approaches, applied traditionally to image-based tasks, work with the…

Existing Neural Architecture Search (NAS) methods either encode neural architectures using discrete encodings that do not scale well, or adopt supervised learning-based methods to jointly learn architecture representations and optimize…

Deep learning has made breakthroughs and substantial in many fields due to its powerful automatic representation capabilities. It has been proven that neural architecture design is crucial to the feature representation of data and the final…

Spatial-temporal sequence forecasting (STSF) is a long-standing research problem with widespread real-world applications. Neural architecture search (NAS), which automates the neural network design, has been shown effective in tackling the…

Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the…

Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing…

This work explores class-incremental learning (CIL) for sound event detection (SED), advancing adaptability towards real-world scenarios. CIL's success in domains like computer vision inspired our SED-tailored method, addressing the unique…

Learning the causal structure behind data is invaluable for improving generalization and obtaining high-quality explanations. We propose a novel framework, Invariant Structure Learning (ISL), that is designed to improve causal structure…

Neural Architecture Search remains a very challenging meta-learning problem. Several recent techniques based on parameter-sharing idea have focused on reducing the NAS running time by leveraging proxy models, leading to architectures with…

Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…

In various scenarios, a single phase of modelling and solving is either not sufficient or not feasible to solve the problem at hand. A standard approach to solving AI planning problems, for example, is to incrementally extend the planning…

Cascading multiple pre-trained models is an effective way to compose an end-to-end system. However, fine-tuning the full cascaded model is parameter and memory inefficient and our observations reveal that only applying adapter modules on…

Despite the recent progresses, particularly in developing Language Models, there are fundamental challenges and unanswered questions about how such models can continually learn/memorize, self-improve, and find effective solutions. In this…

We propose a novel interactive learning framework which we refer to as Interactive Attention Learning (IAL), in which the human supervisors interactively manipulate the allocated attentions, to correct the model's behavior by updating the…