Search Results for author: Hang Gao

Found 47 papers, 21 papers with code

SOAR: Self-Occluded Avatar Recovery from a Single Video In the Wild

no code implementations31 Oct 2024 Zhuoyang Pan, Angjoo Kanazawa, Hang Gao

SOAR leverages structural normal prior and generative diffusion prior to address such an ill-posed reconstruction problem.

Ranking Policy Learning via Marketplace Expected Value Estimation From Observational Data

no code implementations6 Oct 2024 Ehsan Ebrahimzadeh, Nikhil Monga, Hang Gao, Alex Cozzi, Abraham Bagherjeiran

We build empirical estimates for the expected reward of the marketplace from observational data that account for the heterogeneity of economic value across session contexts as well as the distribution shifts in learning from observational user activity data.

Bayesian Inference

Managing Basis Risks in Weather Parametric Insurance: A Quantitative Study of Diversification and Key Influencing Factors

no code implementations25 Sep 2024 Hang Gao, Shuohua Yang, Xinli Liu

Weather parametric insurance relies on weather indices rather than actual loss assessments, enhancing claims efficiency, reducing moral hazard, and improving fairness.

Fairness

Molecular Graph Representation Learning via Structural Similarity Information

1 code implementation13 Sep 2024 Chengyu Yao, Hong Huang, Hang Gao, Fengge Wu, Haiming Chen, Junsuo Zhao

In particular, we propose a specially designed graph that leverages graph kernel algorithms to represent the similarity between molecules quantitatively.

Graph Representation Learning molecular representation +1

A foundation model enpowered by a multi-modal prompt engine for universal seismic geobody interpretation across surveys

no code implementations8 Sep 2024 Hang Gao, Xinming Wu, Luming Liang, Hanlin Sheng, Xu Si, Gao Hui, Yaxing Li

This model integrates a pre-trained vision foundation model (VFM) with a sophisticated multi-modal prompt engine.

Shape of Motion: 4D Reconstruction from a Single Video

no code implementations18 Jul 2024 Qianqian Wang, Vickie Ye, Hang Gao, Jake Austin, Zhengqi Li, Angjoo Kanazawa

Monocular dynamic reconstruction is a challenging and long-standing vision problem due to the highly ill-posed nature of the task.

4D reconstruction Dynamic Reconstruction +2

VRSD: Rethinking Similarity and Diversity for Retrieval in Large Language Models

no code implementations5 Jul 2024 Hang Gao, Yongfeng Zhang

This establishes the profound difficulty of pursuing similarity and diversity simultaneously in vector retrieval and lays a theoretical groundwork for further research.

Combinatorial Optimization Diversity +1

Introducing Diminutive Causal Structure into Graph Representation Learning

no code implementations13 Jun 2024 Hang Gao, Peng Qiao, Yifan Jin, Fengge Wu, Jiangmeng Li, Changwen Zheng

However, within the domain of graph representation learning, the inherent complexity of graph data obstructs the derivation of a comprehensive causal structure that encapsulates universal rules or relationships governing the entire dataset.

Graph Representation Learning

BvSP: Broad-view Soft Prompting for Few-Shot Aspect Sentiment Quad Prediction

1 code implementation11 Jun 2024 Yinhao Bai, Yalan Xie, Xiaoyi Liu, Yuhua Zhao, Zhixin Han, Mengting Hu, Hang Gao, Renhong Cheng

To tackle this issue, we further propose a Broadview Soft Prompting (BvSP) method that aggregates multiple templates with a broader view by taking into account the correlation between the different templates.

Language Modelling Sentence

Memory Sharing for Large Language Model based Agents

1 code implementation15 Apr 2024 Hang Gao, Yongfeng Zhang

The adaptation of Large Language Model (LLM)-based agents to execute tasks via natural language prompts represents a significant advancement, notably eliminating the need for explicit retraining or fine tuning, but are constrained by the comprehensiveness and diversity of the provided examples, leading to outputs that often diverge significantly from expected results, especially when it comes to the open-ended questions.

Common Sense Reasoning Diversity +4

LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty

no code implementations16 Feb 2024 Zhen Zhang, Yuhua Zhao, Hang Gao, Mengting Hu

Named Entity Recognition (NER) serves as a fundamental task in natural language understanding, bearing direct implications for web content analysis, search engines, and information retrieval systems.

In-Context Learning Information Retrieval +4

Hierarchical Topology Isomorphism Expertise Embedded Graph Contrastive Learning

1 code implementation21 Dec 2023 Jiangmeng Li, Yifan Jin, Hang Gao, Wenwen Qiang, Changwen Zheng, Fuchun Sun

To this end, we propose a novel hierarchical topology isomorphism expertise embedded graph contrastive learning, which introduces knowledge distillations to empower GCL models to learn the hierarchical topology isomorphism expertise, including the graph-tier and subgraph-tier.

Contrastive Learning Graph Representation Learning +1

Rethinking Causal Relationships Learning in Graph Neural Networks

1 code implementation15 Dec 2023 Hang Gao, Chengyu Yao, Jiangmeng Li, Lingyu Si, Yifan Jin, Fengge Wu, Changwen Zheng, Huaping Liu

In order to comprehensively analyze various GNN models from a causal learning perspective, we constructed an artificially synthesized dataset with known and controllable causal relationships between data and labels.

Unsupervised Social Event Detection via Hybrid Graph Contrastive Learning and Reinforced Incremental Clustering

1 code implementation8 Dec 2023 Yuanyuan Guo, Zehua Zang, Hang Gao, Xiao Xu, Rui Wang, Lixiang Liu, Jiangmeng Li

To this end, recent works explore learning discriminative information from social messages by leveraging graph contrastive learning (GCL) and embedding clustering in an unsupervised manner.

Clustering Contrastive Learning +1

Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control

no code implementations17 Oct 2023 Xianyue Peng, Hang Gao, Hao Wang, H. Michael Zhang

Over the years, reinforcement learning has emerged as a popular approach to develop signal control and vehicle platooning strategies either independently or in a hierarchical way.

Multi-agent Reinforcement Learning reinforcement-learning +2

Adversarial Driving Behavior Generation Incorporating Human Risk Cognition for Autonomous Vehicle Evaluation

no code implementations29 Sep 2023 Zhen Liu, Hang Gao, Hao Ma, Shuo Cai, Yunfeng Hu, Ting Qu, Hong Chen, Xun Gong

Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia.

Reinforcement Learning (RL)

Information Theory-Guided Heuristic Progressive Multi-View Coding

no code implementations21 Aug 2023 Jiangmeng Li, Hang Gao, Wenwen Qiang, Changwen Zheng

To this end, we rethink the existing multi-view learning paradigm from the perspective of information theory and then propose a novel information theoretical framework for generalized multi-view learning.

Contrastive Learning MULTI-VIEW LEARNING +1

NerfAcc: Efficient Sampling Accelerates NeRFs

no code implementations ICCV 2023 RuiLong Li, Hang Gao, Matthew Tancik, Angjoo Kanazawa

Optimizing and rendering Neural Radiance Fields is computationally expensive due to the vast number of samples required by volume rendering.

Introducing Expertise Logic into Graph Representation Learning from A Causal Perspective

no code implementations20 Jan 2023 Hang Gao, Jiangmeng Li, Wenwen Qiang, Lingyu Si, Xingzhe Su, Fengge Wu, Changwen Zheng, Fuchun Sun

By further observing the ramifications of introducing expertise logic into graph representation learning, we conclude that leading the GNNs to learn human expertise can improve the model performance.

Graph Representation Learning Knowledge Graphs

Monocular Dynamic View Synthesis: A Reality Check

1 code implementation24 Oct 2022 Hang Gao, RuiLong Li, Shubham Tulsiani, Bryan Russell, Angjoo Kanazawa

We study the recent progress on dynamic view synthesis (DVS) from monocular video.

Improving Aspect Sentiment Quad Prediction via Template-Order Data Augmentation

1 code implementation19 Oct 2022 Mengting Hu, Yike Wu, Hang Gao, Yinhao Bai, Shiwan Zhao

By fine-tuning the pre-trained language model with these template orders, our approach improves the performance of quad prediction, and outperforms state-of-the-art methods significantly in low-resource settings.

Aspect-Based Sentiment Analysis (ABSA) Data Augmentation +2

Classical Sequence Match is a Competitive Few-Shot One-Class Learner

1 code implementation COLING 2022 Mengting Hu, Hang Gao, Yinhao Bai, Mingming Liu

Nowadays, transformer-based models gradually become the default choice for artificial intelligence pioneers.

Meta-Learning

Robust Causal Graph Representation Learning against Confounding Effects

1 code implementation18 Aug 2022 Hang Gao, Jiangmeng Li, Wenwen Qiang, Lingyu Si, Bing Xu, Changwen Zheng, Fuchun Sun

This observation reveals that there exist confounders in graphs, which may interfere with the model learning semantic information, and current graph representation learning methods have not eliminated their influence.

Graph Neural Network Graph Representation Learning

Bootstrapping Informative Graph Augmentation via A Meta Learning Approach

1 code implementation11 Jan 2022 Hang Gao, Jiangmeng Li, Wenwen Qiang, Lingyu Si, Fuchun Sun, Changwen Zheng

To this end, we propose a novel approach to learning a graph augmenter that can generate an augmentation with uniformity and informativeness.

Contrastive Learning Informativeness +2

A Two-Stage Data-Free Adversarial Patch Generation Framework

no code implementations29 Sep 2021 Jiawei Liu, Hang Gao, Yunfeng Hu, Xun Gong

The proxy dataset selection stage calculates the proposed average patch saliency (APS) of each available dataset to select a high-APS proxy dataset that can guarantee patches' fooling abilities.

Vocal Bursts Valence Prediction

Information Theory-Guided Heuristic Progressive Multi-View Coding

no code implementations6 Sep 2021 Jiangmeng Li, Wenwen Qiang, Hang Gao, Bing Su, Farid Razzak, Jie Hu, Changwen Zheng, Hui Xiong

To this end, we rethink the existing multi-view learning paradigm from the information theoretical perspective and then propose a novel information theoretical framework for generalized multi-view learning.

Contrastive Learning MULTI-VIEW LEARNING +1

Learning with Holographic Reduced Representations

1 code implementation NeurIPS 2021 Ashwinkumar Ganesan, Hang Gao, Sunil Gandhi, Edward Raff, Tim Oates, James Holt, Mark McLean

HRRs today are not effective in a differentiable solution due to numerical instability, a problem we solve by introducing a projection step that forces the vectors to exist in a well behaved point in space.

Multi-Label Classification Retrieval

Hierarchical Ranking for Answer Selection

no code implementations1 Feb 2021 Hang Gao, Mengting Hu, Renhong Cheng, Tiegang Gao

Answer selection is a task to choose the positive answers from a pool of candidate answers for a given question.

Answer Selection Multi-Task Learning

Deep Learning on Knowledge Graph for Recommender System: A Survey

no code implementations25 Mar 2020 Yang Gao, Yi-Fan Li, Yu Lin, Hang Gao, Latifur Khan

Recent advances in research have demonstrated the effectiveness of knowledge graphs (KG) in providing valuable external knowledge to improve recommendation systems (RS).

Deep Learning Graph Embedding +3

Using Neural Networks for Programming by Demonstration

no code implementations10 Oct 2019 Karan K. Budhraja, Hang Gao, Tim Oates

A low time-complexity and data requirement favoring framework for reproducing emergent behavior, given an abstract demonstration, is discussed in [1], [2].

Universal Adversarial Perturbation for Text Classification

no code implementations10 Oct 2019 Hang Gao, Tim Oates

Given a state-of-the-art deep neural network text classifier, we show the existence of a universal and very small perturbation vector (in the embedding space) that causes natural text to be misclassified with high probability.

Adversarial Text General Classification +2

Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation

2 code implementations ICLR 2020 Hang Gao, Xizhou Zhu, Steve Lin, Jifeng Dai

This is typically done by augmenting static operators with learned free-form sampling grids in the image space, dynamically tuned to the data and task for adapting the receptive field.

Image Classification Object +1

Spatio-Temporal Action Graph Networks

1 code implementation4 Dec 2018 Roei Herzig, Elad Levi, Huijuan Xu, Hang Gao, Eli Brosh, Xiaolong Wang, Amir Globerson, Trevor Darrell

Events defined by the interaction of objects in a scene are often of critical importance; yet important events may have insufficient labeled examples to train a conventional deep model to generalize to future object appearance.

Activity Recognition Autonomous Driving +3

Disentangling Propagation and Generation for Video Prediction

1 code implementation ICCV 2019 Hang Gao, Huazhe Xu, Qi-Zhi Cai, Ruth Wang, Fisher Yu, Trevor Darrell

A dynamic scene has two types of elements: those that move fluidly and can be predicted from previous frames, and those which are disoccluded (exposed) and cannot be extrapolated.

Predict Future Video Frames

AutoLoc: Weakly-supervised Temporal Action Localization

1 code implementation22 Jul 2018 Zheng Shou, Hang Gao, Lei Zhang, Kazuyuki Miyazawa, Shih-Fu Chang

In this paper, we first develop a novel weakly-supervised TAL framework called AutoLoc to directly predict the temporal boundary of each action instance.

Weakly-supervised Temporal Action Localization Weakly Supervised Temporal Action Localization

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