RNAs are fundamental in living cells and perform critical functions determined by their tertiary architectures. However, accurate modeling of 3D RNA structure remains a challenging problem. We present a novel method, DRfold, to predict RNA tertiary structures by simultaneous learning of local frame rotations and geometric restraints from experimentally solved RNA structures, where the learned knowledge is converted into a hybrid energy potential to guide RNA structure assembly. The method significantly outperforms previous approaches by >73.3% in TM-score on a sequence-nonredundant dataset containing recently released structures. Detailed analyses showed that the major contribution to the improvements arise from the deep end-to-end learning supervised with the atom coordinates and the composite energy function integrating complementary information from geometry restraints and end-to-end learning models. The open-source DRfold program with fast training protocol allows large-scale application of high-resolution RNA structure modeling and can be further improved with future expansion of RNA structure databases.
Avalanche: an End-to-End Library for Continual Learning
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.
more »
« less
- Award ID(s):
- 1909696
- NSF-PAR ID:
- 10274721
- Author(s) / Creator(s):
- ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; more »
- Date Published:
- Journal Name:
- CLVISION
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Abstract -
Training Automatic Speech Recognition (ASR) systems with sequentially incoming data from alternate domains is an essential milestone in order to reach human intelligibility level in speech recognition. The main challenge of sequential learning is that current adaptation techniques result in significant performance degradation for previously-seen domains.To mitigate the catastrophic forgetting problem, this study proposes effective domain expansion techniques for two scenarios: 1)where only new domain data is available, and 2) where both prior and new domain data are available. We examine the efficacy of the approaches through experiments on adapting a model trained with native English to different English accents. For the first scenario, we study several existing and proposed regularization-based approaches to mitigate performance loss of initial data.The experiments demonstrate the superior performanceo four proposed Soft KL-Divergence(SKLD)-Model Averaging (MA) approach. In this approach, SKLD first alleviates the forgetting problem during adaptation; next, MA makes the final efficient compromise between the two domains by averaging parameters of the initial and adapted models. For the second scenario, we explore several rehearsal-based approaches, which leverage initial data to maintain the original model performance.We propose Gradient Averaging (GA) as well as an approach which operates by averaging gradients computed for both initial and new domains. Experiments demonstrate that GA outperforms retraining and specifically designed continual learning approaches, such as Averaged Gradient Episodic Memory (AGEM). Moreover, GA significantly improves computational costs over the complete retraining approach.more » « less
-
Computer vision models suffer from a phenomenon known as catastrophic forgetting when learning novel concepts from continuously shifting training data. Typical solutions for this continual learning problem require extensive rehearsal of previously seen data, which increases memory costs and may violate data privacy. Recently, the emergence of large-scale pre-trained vision transformer models has enabled prompting approaches as an alternative to data-rehearsal. These approaches rely on a key-query mechanism to generate prompts and have been found to be highly resistant to catastrophic forgetting in the well-established rehearsal-free continual learning setting. However, the key mechanism of these methods is not trained end-to-end with the task sequence. Our experiments show that this leads to a reduction in their plasticity, hence sacrificing new task accuracy, and inability to benefit from expanded parameter capacity. We instead propose to learn a set of prompt components which are assembled with input-conditioned weights to produce input-conditioned prompts, resulting in a novel attention-based end-to-end key-query scheme. Our experiments show that we outperform the current SOTA method DualPrompt on established benchmarks by as much as 4.5% in average final accuracy. We also outperform the state of art by as much as 4.4% accuracy on a continual learning benchmark which contains both class-incremental and domain-incremental task shifts, corresponding to many practical settings.more » « less
-
As an alternative to resource-intensive deep learning approaches to the continual learning problem, we propose a simple, fast algorithm inspired by adaptive resonance theory (ART). To cope with the curse of dimensionality and avoid catastrophic forgetting, we apply incremental principal component analysis (IPCA) to the model's previously learned weights. Experiments show that this approach approximates the performance achieved using static PCA and is competitive with continual deep learning methods. Our implementation is available on https://github.com/neil-ash/ART-IPCAmore » « less
-
In recent years, neural networks have demonstrated an outstanding ability to achieve complex learning tasks across various domains. However, they suffer from the "catastrophic forgetting" problem when they face a sequence of learning tasks, where they forget the old ones as they learn new tasks. This problem is also highly related to the "stability-plasticity dilemma". The more plastic the network, the easier it can learn new tasks, but the faster it also forgets previous ones. Conversely, a stable network cannot learn new tasks as fast as a very plastic network. However, it is more reliable to preserve the knowledge it has learned from the previous tasks. Several solutions have been proposed to overcome the forgetting problem by making the neural network parameters more stable, and some of them have mentioned the significance of dropout in continual learning. However, their relationship has not been sufficiently studied yet. In this paper, we investigate this relationship and show that a stable network with dropout learns a gating mechanism such that for different tasks, different paths of the network are active. Our experiments show that the stability achieved by this implicit gating plays a very critical role in leading to performance comparable to or better than other involved continual learning algorithms to overcome catastrophic forgetting.more » « less