相关论文: Machine Unlearning in Hyperbolic vs. Euclidean Mul…

Learning the representation of data with hierarchical structures in the hyperbolic space attracts increasing attention in recent years. Due to the constant negative curvature, the hyperbolic space resembles tree metrics and captures the…

Language models are increasingly applied to biological sequences like proteins and mRNA, yet their default Euclidean geometry may mismatch the hierarchical structures inherent to biological data. While hyperbolic geometry provides a better…

Learning representations according to the underlying geometry is of vital importance for non-Euclidean data. Studies have revealed that the hyperbolic space can effectively embed hierarchical or tree-like data. In particular, the few past…

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification…

Knowledge graph (KG) embedding methods map entities and relations into continuous vector spaces, improving performance in tasks like link prediction and question answering. With rising privacy concerns, machine unlearning (MU) has emerged…

Deep machine unlearning is the problem of `removing' from a trained neural network a subset of its training set. This problem is very timely and has many applications, including the key tasks of removing biases (RB), resolving confusion…

Benefiting from the effectiveness of graph neural networks (GNNs) and contrastive learning, GNN-based contrastive learning has become mainstream for knowledge-aware recommendation. However, most existing contrastive learning-based methods…

Self-Supervised Contrastive Learning has proven effective in deriving high-quality representations from unlabeled data. However, a major challenge that hinders both unimodal and multimodal contrastive learning is feature suppression, a…

Learning generalized face anti-spoofing (FAS) models against presentation attacks is essential for the security of face recognition systems. Previous FAS methods usually encourage models to extract discriminative features, of which the…

Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches…

Concept Bottleneck Models (CBMs) have become a popular approach to enable interpretability in neural networks by constraining classifier inputs to a set of human-understandable concepts. While effective, current models embed concepts in…

Hyperbolic representations are effective in modeling knowledge graph data which is prevalently used to facilitate multi-hop reasoning. However, a rigorous and detailed comparison of the two spaces for this task is lacking. In this paper,…

Data representation in non-Euclidean spaces has proven effective for capturing hierarchical and complex relationships in real-world datasets. Hyperbolic spaces, in particular, provide efficient embeddings for hierarchical structures. This…

Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove specific content…

In large-scale recommender systems, the user-item networks are generally scale-free or expand exponentially. The latent features (also known as embeddings) used to describe the user and item are determined by how well the embedding space…

Machine Unlearning removes specific knowledge about training data samples from an already trained model. It has significant practical benefits, such as purging private, inaccurate, or outdated information from trained models without the…

Deep neural networks often rely on spurious correlations in training data, leading to biased or unfair predictions in safety-critical domains such as medicine and autonomous driving. While conventional bias mitigation typically requires…

While numerous machine unlearning (MU) methods have recently been developed with promising results in erasing the influence of forgotten data, classes, or concepts, they are also highly vulnerable-for example, simple fine-tuning can…

This study investigates the concept of the `right to be forgotten' within the context of large language models (LLMs). We explore machine unlearning as a pivotal solution, with a focus on pre-trained models--a notably under-researched area.…

As large language models (LLMs) are trained on massive datasets, they have raised significant privacy and ethical concerns due to their potential to inadvertently retain sensitive information. Unlearning seeks to selectively remove specific…