Related papers: Robult: Leveraging Redundancy and Modality Specifi…

Recent advancements in Machine Unlearning (MU) have introduced solutions to selectively remove certain training samples, such as those with outdated or sensitive information, from trained models. Despite these advancements, evaluation of MU…

Multimodal learning typically relies on the assumption that all modalities are fully available during both the training and inference phases. However, in real-world scenarios, consistently acquiring complete multimodal data presents…

Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust. Recently, it has been shown that the…

Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will…

Cross-modal retrieval maps data under different modality via semantic relevance. Existing approaches implicitly assume that data pairs are well-aligned and ignore the widely existing annotation noise, i.e., noisy correspondence (NC).…

This paper proposes a new principled multi-task representation learning framework (InfoMTL) to extract noise-invariant sufficient representations for all tasks. It ensures sufficiency of shared representations for all tasks and mitigates…

A major challenge of reinforcement learning (RL) in real-world applications is the variation between environments, tasks or clients. Meta-RL (MRL) addresses this issue by learning a meta-policy that adapts to new tasks. Standard MRL methods…

Multimodal learning has achieved great successes in many scenarios. Compared with unimodal learning, it can effectively combine the information from different modalities to improve the performance of learning tasks. In reality, the…

Human action recognition (HAR) with multi-modal inputs (RGB-D, skeleton, point cloud) can achieve high accuracy but typically relies on large labeled datasets and degrades sharply when sensors fail or are noisy. We present Robust…

In document classification for, e.g., legal and biomedical text, we often deal with hundreds of classes, including very infrequent ones, as well as temporal concept drift caused by the influence of real world events, e.g., policy changes,…

Dealing with label noise in tabular classification tasks poses a persistent challenge in machine learning. While robust boosting methods have shown promise in binary classification, their effectiveness in complex, multi-class scenarios is…

We study the problem of robust learning under clean-label data-poisoning attacks, where the attacker injects (an arbitrary set of) correctly-labeled examples to the training set to fool the algorithm into making mistakes on specific test…

We demonstrate that learning procedures that rely on aggregated labels, e.g., label information distilled from noisy responses, enjoy robustness properties impossible without data cleaning. This robustness appears in several ways. In the…

The major challenge of learning from multi-label data has arisen from the overwhelming size of label space which makes this problem NP-hard. This problem can be alleviated by gradually involving easy to hard tags into the learning process.…

Radiologists must utilize multiple modal images for tumor segmentation and diagnosis due to the limitations of medical imaging and the diversity of tumor signals. This leads to the development of multimodal learning in segmentation.…

Designing learning algorithms that are resistant to perturbations of the underlying data distribution is a problem of wide practical and theoretical importance. We present a general approach to this problem focusing on unsupervised…

Model quantization enables efficient deployment of deep neural networks on edge devices through low-bit parameter representation, yet raises critical challenges for implementing machine unlearning (MU) under data privacy regulations.…

Multimodal learning integrates complementary information from different modalities such as image, text, and audio to improve model performance, but its success relies on large-scale labeled data, which is costly to obtain. Active learning…

Missing modality issues are common in real-world applications, arising from factors such as equipment failures and privacy concerns. When fine-tuning pre-trained models on downstream datasets with missing modalities, performance can degrade…

Missing modalities consistently lead to significant performance degradation in multimodal models. Existing approaches either synthesize missing modalities at high computational cost or apply prompt-based fine-tuning that relies only on…