相关论文: Learning To Help: Training Models to Assist Legacy…

Machine unlearning seeks to remove the influence of specific training data from a model, a need driven by privacy regulations and robustness concerns. Existing approaches typically modify model parameters, but such updates can be unstable,…

We study a distributed machine learning problem carried out by an edge server and multiple agents in a wireless network. The objective is to minimize a global function that is a sum of the agents' local loss functions. And the optimization…

Large language models (LLMs) have recently gained much attention in building autonomous agents. However, the performance of current LLM-based web agents in long-horizon tasks is far from optimal, often yielding errors such as repeatedly…

Large language Models (LLMs) have demonstrated remarkable skills across various domains. Understanding the mechanisms behind their abilities and implementing controls over them is becoming increasingly important for developing better…

The integration of machine learning (ML) is critical for industrial competitiveness, yet its adoption is frequently stalled by the prohibitive costs and operational disruptions of upgrading legacy systems. The financial and logistical…

LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain…

Emerging technologies and applications including Internet of Things (IoT), social networking, and crowd-sourcing generate large amounts of data at the network edge. Machine learning models are often built from the collected data, to enable…

Recent research studies revealed that neural networks are vulnerable to adversarial attacks. State-of-the-art defensive techniques add various adversarial examples in training to improve models' adversarial robustness. However, these…

Deep neural networks have been successfully deployed in various domains of artificial intelligence, including computer vision and natural language processing. We observe that the current standard procedure for training DNNs discards all the…

Interleaving learning is a human learning technique where a learner interleaves the studies of multiple topics, which increases long-term retention and improves ability to transfer learned knowledge. Inspired by the interleaving learning…

Future machine learning (ML) powered applications, such as autonomous driving and augmented reality, involve training and inference tasks with timeliness requirements and are communication and computation intensive, which demands for the…

Despite advances in Visual Question Answering (VQA), the ability of models to assess their own correctness remains underexplored. Recent work has shown that VQA models, out-of-the-box, can have difficulties abstaining from answering when…

AI systems often struggle to provide reliable predictions across all inputs, motivating hybrid human-AI decision-making. Existing Learning to Defer (L2D) approaches address this by training models to selectively defer to human experts.…

The impact of machine learning models on healthcare will depend on the degree of trust that healthcare professionals place in the predictions made by these models. In this paper, we present a method to provide people with clinical expertise…

In [1, 2], we have explored the theoretical aspects of feature extraction optimization processes for solving largescale problems and overcoming machine learning limitations. Majority of optimization algorithms that have been introduced in…

Large Language Models excel in generative tasks but exhibit inefficiencies in structured text selection, particularly in extractive question answering. This challenge is magnified in resource-constrained environments, where deploying…

The rise of the phenomenon of the "right to be forgotten" has prompted research on machine unlearning, which grants data owners the right to actively withdraw data that has been used for model training, and requires the elimination of the…

Meta learning uses information from base learners (e.g. classifiers or estimators) as well as information about the learning problem to improve upon the performance of a single base learner. For example, the Bayes error rate of a given…

Federated learning (FL) is usually performed on resource-constrained edge devices, e.g., with limited memory for the computation. If the required memory to train a model exceeds this limit, the device will be excluded from the training.…

We consider prediction with expert advice for strongly convex and bounded losses, and investigate trade-offs between regret and "variance" (i.e., squared difference of learner's predictions and best expert predictions). With $K$ experts,…