Bin Chen   (陈斌)

Currently, I am a second-year master student at University of Electronic Science and Technology of China(UESTC), supervised by Prof. Fan Zhou and Prof. Ting Zhong. My research interests include but are not limited to TKG reasoning, MultiModal learning, IP geolocation, and Trustworthy Neural Networks, etc.

Email: binchen4110 AT gmail Dot com

Read Paper Record  /  Google Scholar  /  Github  /  CV

We present RipGeo for robust street-level IP geolocation. Furthermore, considering the widespread noise in measurement data, we propose two novel self-supervised perturbational training strategies to enhance the generalization and robustness of the model. Besides, a multi-task learning framework is introduced to solve the homogenized representation problem caused by perturbational training.

We present TrustGeo for trustworthy street-level IP geolocation. We incorporate the sources of uncertainty in the learning process of the model to improve prediction accuracy and generalization.

We propose an innovative method, LSGAT, which not only exhibits remarkable precision in entity predictions but also enhances interpretability by identifying pivotal historical events influencing event predictions.

We propose SDFEN to address the inefficiency problem while enhancing the quality of generated samples by reducing the iterative steps in the reverse process of diffusion method. Specifically, a shallow diffusion strategy is introduced to initiate the reverse process with an adaptive time step to accelerate inference.