Search Results for author: Defu Cao

Found 16 papers, 4 papers with code

Enhancing Self-Attention with Knowledge-Assisted Attention Maps

no code implementations NAACL 2022 Jiangang Bai, Yujing Wang, Hong Sun, Ruonan Wu, Tianmeng Yang, Pengfei Tang, Defu Cao, Mingliang Zhang1, Yunhai Tong, Yaming Yang, Jing Bai, Ruofei Zhang, Hao Sun, Wei Shen

Large-scale pre-trained language models have attracted extensive attentions in the research community and shown promising results on various tasks of natural language processing.

Multi-Task Learning Natural Language Understanding

Exploring Neuron Interactions and Emergence in LLMs: From the Multifractal Analysis Perspective

no code implementations14 Feb 2024 Xiongye Xiao, Chenyu Zhou, Heng Ping, Defu Cao, Yaxing Li, Yizhuo Zhou, Shixuan Li, Paul Bogdan

Prior studies on the emergence in large models have primarily focused on how the functional capabilities of large language models (LLMs) scale with model size.

Guiding Large Language Models with Divide-and-Conquer Program for Discerning Problem Solving

no code implementations8 Feb 2024 Yizhou Zhang, Lun Du, Defu Cao, Qiang Fu, Yan Liu

Foundation models, such as Large language Models (LLMs), have attracted significant amount of interest due to their large number of applications.

Fake News Detection Hallucination +1

Neuro-Inspired Hierarchical Multimodal Learning

no code implementations27 Sep 2023 Xiongye Xiao, Gengshuo Liu, Gaurav Gupta, Defu Cao, Shixuan Li, Yaxing Li, Tianqing Fang, Mingxi Cheng, Paul Bogdan

Integrating and processing information from various sources or modalities are critical for obtaining a comprehensive and accurate perception of the real world.

Estimating Treatment Effects from Irregular Time Series Observations with Hidden Confounders

no code implementations4 Mar 2023 Defu Cao, James Enouen, Yujing Wang, Xiangchen Song, Chuizheng Meng, Hao Niu, Yan Liu

Causal analysis for time series data, in particular estimating individualized treatment effect (ITE), is a key task in many real-world applications, such as finance, retail, healthcare, etc.

Causal Inference Irregular Time Series +2

Coupled Multiwavelet Neural Operator Learning for Coupled Partial Differential Equations

1 code implementation4 Mar 2023 Xiongye Xiao, Defu Cao, Ruochen Yang, Gaurav Gupta, Gengshuo Liu, Chenzhong Yin, Radu Balan, Paul Bogdan

Coupled partial differential equations (PDEs) are key tasks in modeling the complex dynamics of many physical processes.

Operator learning

Estimating Treatment Effects in Continuous Time with Hidden Confounders

no code implementations19 Feb 2023 Defu Cao, James Enouen, Yan Liu

Estimating treatment effects plays a crucial role in causal inference, having many real-world applications like policy analysis and decision making.

Causal Inference Decision Making +2

DSLOB: A Synthetic Limit Order Book Dataset for Benchmarking Forecasting Algorithms under Distributional Shift

no code implementations17 Nov 2022 Defu Cao, Yousef El-Laham, Loc Trinh, Svitlana Vyetrenko, Yan Liu

Using the proposed synthetic dataset, we provide a holistic analysis on the forecasting performance of three different state-of-the-art forecasting methods.

Benchmarking Time Series +1

Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media

no code implementations14 Oct 2022 Yizhou Zhang, Defu Cao, Yan Liu

To address these issues, in this paper, we build up a causal framework that model the causal effect of misinformation from the perspective of temporal point process.

counterfactual Misinformation

When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning

no code implementations31 Mar 2022 Chuizheng Meng, Sungyong Seo, Defu Cao, Sam Griesemer, Yan Liu

Physics-informed machine learning (PIML), referring to the combination of prior knowledge of physics, which is the high level abstraction of natural phenomenons and human behaviours in the long history, with data-driven machine learning models, has emerged as an effective way to mitigate the shortage of training data, to increase models' generalizability and to ensure the physical plausibility of results.

BIG-bench Machine Learning Physics-informed machine learning

Spectral Temporal Graph Neural Network for Trajectory Prediction

no code implementations5 Jun 2021 Defu Cao, Jiachen Li, Hengbo Ma, Masayoshi Tomizuka

To this end, we propose a Spectral Temporal Graph Neural Network (SpecTGNN), which can capture inter-agent correlations and temporal dependency simultaneously in frequency domain in addition to time domain.

Autonomous Vehicles Motion Forecasting +1

Multivariate Time-series Anomaly Detection via Graph Attention Network

2 code implementations4 Sep 2020 Hang Zhao, Yujing Wang, Juanyong Duan, Congrui Huang, Defu Cao, Yunhai Tong, Bixiong Xu, Jing Bai, Jie Tong, Qi Zhang

Anomaly detection on multivariate time-series is of great importance in both data mining research and industrial applications.

Anomaly Detection Graph Attention +3

Cannot find the paper you are looking for? You can Submit a new open access paper.