Related papers: Continual Learning as Shared-Manifold Continuation…
The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been…
Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations. We study multimodal learning and sensor fusion from a latent…
Supervised manifold learning methods learn data representations by preserving the geometric structure of data while enhancing the separation between data samples from different classes. In this work, we propose a theoretical study of…
Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks without explicitly preserving the cross-modal semantic geometry inherited from pretraining and…
We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to…
Benefiting from massive corpora and advanced hardware, large language models (LLMs) exhibit remarkable capabilities in language understanding and generation. However, their performance degrades in scenarios where multiple tasks are…
A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguably do the…
Adapting model parameters to incoming streams of data is a crucial factor to deep learning scalability. Interestingly, prior continual learning strategies in online settings inadvertently anchor their updated parameters to a local parameter…
Manifold learning methods are an invaluable tool in today's world of increasingly huge datasets. Manifold learning algorithms can discover a much lower-dimensional representation (embedding) of a high-dimensional dataset through non-linear…
In this paper, we aim at tackling a general but interesting cross-modality feature learning question in remote sensing community --- can a limited amount of highly-discrimin-ative (e.g., hyperspectral) training data improve the performance…
Manifold learning techniques have become increasingly valuable as data continues to grow in size. By discovering a lower-dimensional representation (embedding) of the structure of a dataset, manifold learning algorithms can substantially…
We investigate recurrent neural networks with asymmetric interactions and demonstrate that the inclusion of self-couplings or sparse excitatory inter-module connections leads to the emergence of a densely connected manifold of dynamically…
Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart home automation, all of which rely on robust human activity recognition (HAR). Continual…
Continual learning poses a fundamental challenge for modern machine learning systems, requiring models to adapt to new tasks while retaining knowledge from previous ones. Addressing this challenge necessitates the development of efficient…
Continual learning in natural language processing plays a crucial role in adapting to evolving data and preventing catastrophic forgetting. Despite significant progress, existing methods still face challenges, such as inefficient parameter…
Artificial intelligence systems in critical fields like autonomous driving and medical imaging analysis often continually learn new tasks using a shared stream of input data. For instance, after learning to detect traffic signs, a model may…
Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-based methods (e.g., EWC) can overconstrain updates when task optima are weakly overlapping,…
Continual learning requires incremental compatibility with a sequence of tasks. However, the design of model architecture remains an open question: In general, learning all tasks with a shared set of parameters suffers from severe…
Continual Learning requires a model to learn multiple tasks in sequence while maintaining both stability:preserving knowledge from previously learned tasks, and plasticity:effectively learning new tasks. Gradient projection has emerged as…
In continual learning, the learner learns multiple tasks in sequence, with data being acquired only once for each task. Catastrophic forgetting is a major challenge to continual learning. To reduce forgetting, some existing rehearsal-based…