Ninghao Liu · PaperMetrix

Towards Explanation of DNN-based Prediction with Guided Feature Inversion

2018

While deep neural networks (DNN) have become an effective computational tool, the prediction results are often criticized by the lack of interpretability, which is essential in many real-world applications such as health informatics. Existing attempts …

Unseen Anomaly Detection on Networks via Multi-Hypersphere Learning

2022 · Society for Industrial and Applied Mathematics eBooks

Network anomaly detection is a crucial task since a few anomalies can cause huge losses. Semi-supervised anomaly detection methods can effectively leverage a small number of labels as prior knowledge to enhance detection accuracy. But …

Attacking Neural Networks with Neural Networks: Towards Deep Synchronization for Backdoor Attacks

2023

Backdoor attacks inject poisoned samples into training data, where backdoor triggers are embedded into the model trained on the mixture of poisoned and clean samples.An interesting phenomenon can be observed in the training process: the …

UniGLM: Training One Unified Language Model for Text-Attributed Graph Embedding

2024 · arXiv (Cornell University)

Representation learning on text-attributed graphs (TAGs), where nodes are represented by textual descriptions, is crucial for textual and relational knowledge systems and recommendation systems. Currently, state-of-the-art embedding methods for TAGs primarily focus on fine-tuning language …

Enhancing Explainable Rating Prediction through Annotated Macro Concepts

2024

Generating recommendation reasons for recommendation results is a long-standing problem because it is challenging to explain the underlying reasons for recommending an item based on user and item IDs.Existing models usually learn semantic embeddings for …

Towards Stable and Explainable Attention Mechanisms

2025 · IEEE Transactions on Knowledge and Data Engineering