相关论文: ADER: Adaptively Distilled Exemplar Replay Towards…

Consistent distillation methods have evolved into effective techniques that significantly accelerate the sampling process of diffusion models. Although existing methods have achieved remarkable results, the selection of target timesteps…

In real-world applications, learning-enabled systems often undergo iterative model development to address challenging or emerging tasks, which involve collecting new data, training a new model and validating the model. This continual model…

Continual learning seeks to enable deep learners to train on a series of tasks of unknown length without suffering from the catastrophic forgetting of previous tasks. One effective solution is replay, which involves storing few previous…

Modern recommender systems operate in uniquely dynamic settings: user interests, item pools, and popularity trends shift continuously, and models must adapt in real time without forgetting past preferences. While existing tutorials on…

In this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting. KD-based methods are successfully used in CIL, but they often struggle…

In standard adversarial training, models are optimized to fit one-hot labels within allowable adversarial perturbation budgets. However, the ignorance of underlying distribution shifts brought by perturbations causes the problem of robust…

The emerging meta- and multi-verse landscape is yet another step towards the more prevalent use of already ubiquitous online markets. In such markets, recommender systems play critical roles by offering items of interest to the users,…

In this paper, we study a sequential decision-making problem, called Adaptive Sampling for Discovery (ASD). Starting with a large unlabeled dataset, algorithms for ASD adaptively label the points with the goal to maximize the sum of…

Lifelong learning with deep neural networks is well-known to suffer from catastrophic forgetting: the performance on previous tasks drastically degrades when learning a new task. To alleviate this effect, we propose to leverage a large…

Techniques such as ensembling and distillation promise model quality improvements when paired with almost any base model. However, due to increased test-time cost (for ensembles) and increased complexity of the training pipeline (for…

Nonlinear model predictive control (NMPC) requires accurate and computationally efficient plant models. Our previous work has shown that the classical compartmentalization model reduction approach for distillation columns can be enhanced by…

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…

Many real-world applications such as robotics provide hard constraints on power and compute that limit the viable model complexity of Reinforcement Learning (RL) agents. Similarly, in many distributed RL settings, acting is done on…

Incremental language learning with pseudo-data can alleviate catastrophic forgetting in neural networks. However, to obtain better performance, former methods have higher demands for pseudo-data of the previous tasks. The performance…

Embeddings, low-dimensional vector representation of objects, are fundamental in building modern machine learning systems. In industrial settings, there is usually an embedding team that trains an embedding model to solve intended tasks…

Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled…

Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on…

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

Adversarial attacks pose a significant threat to the security and safety of deep neural networks being applied to modern applications. More specifically, in computer vision-based tasks, experts can use the knowledge of model architecture to…