Publications

Knowledge Graph Unlearning with Schema

Published in The Third Learning on Graphs Conference, 2024

Graph unlearning emerges as a crucial step to eliminate the impact of deleted elements from a trained model. However, unlearning on the knowledge graph (KG) has not yet been extensively studied. We remark that KG unlearning is non-trivial because KG is distinctive from general graphs. In this paper, we first propose a new unlearning method based on schema for KG. Specifically, we update the representation of the deleted element’s neighborhood with an unlearning object that regulates the affinity between the affected neighborhood and the instances within the same schema. Second, we raise a new task: schema unlearning. Given a schema graph to be deleted, we remove all instances matching the pattern and make the trained model forget the removed instances. Last, we evaluate the proposed unlearning method on various KG embedding models with benchmark datasets. Our codes are available at https://github.com/NKUShaw/KGUnlearningBySchema.

Recommended citation: Yang Xiao, Ruimeng Ye, Bo Hui.
Download Paper | Download Slides

Advancing Certified Robustness of Explanation via Gradient Quantization

Published in Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, 2024

Explaining black-box models is fundamental to gaining trust and deploying these models in real applications. As existing explanation methods have been shown to lack robustness against adversarial perturbations, there has been a growing interest in generating robust explanations. However, existing works resort to empirical defense strategies and these heuristic methods fail against powerful adversaries. In this paper, we certify the robustness of explanations motivated by the success of randomized smoothing. Specifically, we compute a tight radius in which the robustness of the explanation is certified. While a challenge is how to formulate the robustness of the explanation mathematically, we quantize the explanation into discrete spaces to mimic classification in randomized smoothing. To address the high computational cost of randomized smoothing, we introduce randomized gradient smoothing. Also, we explore the robustness of the semantic explanation by certifying the robustness of capsules. In the experiment, we demonstrate the effectiveness of our method on benchmark datasets from the perspectives of post-hoc explanation and semantic explanation respectively. Our work is a promising step towards filling the gap between the theoretical robustness bound and empirical explanations. Our code has been released at here.

Recommended citation: Yang Xiao, Zijie Zhang, Yuchen Fang, Da Yan, Yang Zhou, Wei-Shinn Ku, Bo Hui."Advancing Certified Robustness of Explanation via Gradient Quantization. " Proceedings of the 33rd ACM International Conference on Information and Knowledge Management (CIKM 24). October 21--25, 2024, Boise, ID, USA.
Download Paper

BMT-BENCH: A Benchmark Sports Dataset for Video Generation

Published in the 2024 IEEE International Conference on Image Processing, 2024

Recommended citation: Ziang Shi,Yang Xiao, Da Yan, Min-Te Sun, Wei-Shinn Ku, Bo Hui. "BMT-BENCH: A Benchmark Sports Dataset for Video Generation. " the 2024 IEEE International Conference on Image Processing. October 27--30, 2024, Abu Dhabi, United Arab Emirates
Download Paper

Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning

Published in ArXiv, 2024

As large language models (LLMs) continue to advance, ensuring their alignment with human values becomes increasingly critical. Traditional alignment methods heavily rely on human feedback to fine-tune models. With the emergence of superhuman models whose outputs may surpass human understanding, evaluating and aligning these models using human judgments poses significant challenges. To address the challenges, recent works use weak supervisors to elicit knowledge from much stronger models. However, there are important disanalogies between the empirical setup in the existing works and the genuine goal of alignment. We remark that existing works investigate the phenomenon of weak-to-strong generation in analogous setup (i.e., binary classification), rather than practical alignment-relevant tasks (e.g., safety). In this paper, we bridge this gap by extending weak-to-strong generation to the context of practical alignment. We empirically demonstrate the widespread phenomenon of weak-to-strong generation in three complicated alignment tasks: safety, toxicity, and legal reasoning}. Furthermore, we explore efficient strategies for improving alignment performance to enhance the quality of model outcomes. Lastly, we summarize and analyze the challenges and potential solutions in regard to specific alignment tasks, which we hope to catalyze the research progress on the topic of weak-to-strong generalization. Our code is released at https://github.com/yeruimeng/WTS.git.

Recommended citation: Ruimeng Ye, Yang Xiao, Bo Hui.
Download Paper

Post-hoc and manifold explanations analysis of facial expression data based on deep learning

Published in ArXiv, 2024

The complex information processing system of humans generates a lot of objective and subjective evaluations, making the exploration of human cognitive products of great cutting-edge theoretical value. In recent years, deep learning technologies, which are inspired by biological brain mechanisms, have made significant strides in the application of psychological or cognitive scientific research, particularly in the memorization and recognition of facial data. This paper investigates through experimental research how neural networks process and store facial expression data and associate these data with a range of psychological attributes produced by humans. Researchers utilized deep learning model VGG16, demonstrating that neural networks can learn and reproduce key features of facial data, thereby storing image memories. Moreover, the experimental results reveal the potential of deep learning models in understanding human emotions and cognitive processes and establish a manifold visualization interpretation of cognitive products or psychological attributes from a non-Euclidean space perspective, offering new insights into enhancing the explainability of AI. This study not only advances the application of AI technology in the field of psychology but also provides a new psychological theoretical understanding the information processing of the AI. The code is available at here.

Recommended citation: Yang Xiao. "Post-hoc and manifold explanations analysis of facial expression data based on deep learning." ArXiv:2404.18352(2024).
Download Paper

A survey of lottery ticket hypothesis

Published in ArXiv, 2024

The Lottery Ticket Hypothesis (LTH) states that a dense neural network model contains a highly sparse subnetwork (i.e., winning tickets) that can achieve even better performance than the original model when trained in isolation. While LTH has been proved both empirically and theoretically in many works, there still are some open issues, such as efficiency and scalability, to be addressed. Also, the lack of open-source frameworks and consensual experimental setting poses a challenge to future research on LTH. We, for the first time, examine previous research and studies on LTH from different perspectives. We also discuss issues in existing works and list potential directions for further exploration. This survey aims to provide an in-depth look at the state of LTH and develop a duly maintained platform to conduct experiments and compare with the most updated baselines.

Recommended citation: Bohan Liu, Zijie Zhang, Peixiong He, Zhensen Wang, Yang Xiao, Ruimeng Ye, Yang Zhou, Wei-Shinn Ku, Bo Hui. "A survey of lottery ticket hypothesis." ArXiv:2403.04861(2024).
Download Paper

A Paper about Efficient Knowledge Graph Unlearning

Published in The 39th Annual AAAI Conference on Artificial Intelligence, 2024

This paper is about Efficient Knowledge Graph Unlearning.

Recommended citation: Yang Xiao(First Author).