Search Results for author: Zijian Li

Found 31 papers, 13 papers with code

Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clients

no code implementations17 Feb 2024 Xiaolu Wang, Zijian Li, Shi Jin, Jun Zhang

Federated learning (FL) is an emerging distributed training paradigm that aims to learn a common global model without exchanging or transferring the data that are stored locally at different clients.

Federated Learning

Unifying Invariance and Spuriousity for Graph Out-of-Distribution via Probability of Necessity and Sufficiency

no code implementations14 Feb 2024 Xuexin Chen, Ruichu Cai, Kaitao Zheng, Zhifan Jiang, Zhengting Huang, Zhifeng Hao, Zijian Li

Under mild conditions, we show that the invariant subgraph can be extracted by minimizing an upper bound, which is built on the theoretical advance of probability of necessity and sufficiency.

Graph Learning

Feature Attribution with Necessity and Sufficiency via Dual-stage Perturbation Test for Causal Explanation

no code implementations13 Feb 2024 Xuexin Chen, Ruichu Cai, Zhengting Huang, Yuxuan Zhu, Julien Horwood, Zhifeng Hao, Zijian Li, Jose Miguel Hernandez-Lobato

We investigate the problem of explainability in machine learning. To address this problem, Feature Attribution Methods (FAMs) measure the contribution of each feature through a perturbation test, where the difference in prediction is compared under different perturbations. However, such perturbation tests may not accurately distinguish the contributions of different features, when their change in prediction is the same after perturbation. In order to enhance the ability of FAMs to distinguish different features' contributions in this challenging setting, we propose to utilize the probability (PNS) that perturbing a feature is a necessary and sufficient cause for the prediction to change as a measure of feature importance. Our approach, Feature Attribution with Necessity and Sufficiency (FANS), computes the PNS via a perturbation test involving two stages (factual and interventional). In practice, to generate counterfactual samples, we use a resampling-based approach on the observed samples to approximate the required conditional distribution. Finally, we combine FANS and gradient-based optimization to extract the subset with the largest PNS. We demonstrate that FANS outperforms existing feature attribution methods on six benchmarks.

counterfactual Test

A self-attention-based differentially private tabular GAN with high data utility

no code implementations20 Dec 2023 Zijian Li, Zhihui Wang

Generative Adversarial Networks (GANs) have become a ubiquitous technology for data generation, with their prowess in image generation being well-established.

Generative Adversarial Network Image Generation

Identifying Semantic Component for Robust Molecular Property Prediction

1 code implementation8 Nov 2023 Zijian Li, Zunhong Xu, Ruichu Cai, Zhenhui Yang, Yuguang Yan, Zhifeng Hao, Guangyi Chen, Kun Zhang

Specifically, we first formulate the data generation process from the atom level to the molecular level, where the latent space is split into SI substructures, SR substructures, and SR atom variables.

Molecular Property Prediction Property Prediction

Subspace Identification for Multi-Source Domain Adaptation

1 code implementation NeurIPS 2023 Zijian Li, Ruichu Cai, Guangyi Chen, Boyang Sun, Zhifeng Hao, Kun Zhang

To mitigate the need for these strict assumptions, we propose a subspace identification theory that guarantees the disentanglement of domain-invariant and domain-specific variables under less restrictive constraints regarding domain numbers and transformation properties, thereby facilitating domain adaptation by minimizing the impact of domain shifts on invariant variables.

Disentanglement Domain Adaptation +1

Knowledge-tuning Large Language Models with Structured Medical Knowledge Bases for Reliable Response Generation in Chinese

1 code implementation8 Sep 2023 Haochun Wang, Sendong Zhao, Zewen Qiang, Zijian Li, Nuwa Xi, Yanrui Du, MuZhen Cai, Haoqiang Guo, Yuhan Chen, Haoming Xu, Bing Qin, Ting Liu

To address this challenge, we propose knowledge-tuning, which leverages structured medical knowledge bases for the LLMs to grasp domain knowledge efficiently and facilitate reliable response generation.

Domain Adaptation Hallucination +2

FedCiR: Client-Invariant Representation Learning for Federated Non-IID Features

no code implementations30 Aug 2023 Zijian Li, Zehong Lin, Jiawei Shao, Yuyi Mao, Jun Zhang

However, devices often have non-independent and identically distributed (non-IID) data, meaning their local data distributions can vary significantly.

Federated Learning Representation Learning

Feature Matching Data Synthesis for Non-IID Federated Learning

no code implementations9 Aug 2023 Zijian Li, Yuchang Sun, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang

For better privacy preservation, we propose a hard feature augmentation method to transfer real features towards the decision boundary, with which the synthetic data not only improve the model generalization but also erase the information of real features.

Data Augmentation Federated Learning +1

TNPAR: Topological Neural Poisson Auto-Regressive Model for Learning Granger Causal Structure from Event Sequences

no code implementations25 Jun 2023 Ruichu Cai, Yuequn Liu, Wei Chen, Jie Qiao, Yuguang Yan, Zijian Li, Keli Zhang, Zhifeng Hao

This observation prompts us to tackle two ensuing challenges: 1) how to model the event sequences while incorporating both the prior topological network and the latent Granger causal structure, and 2) how to learn the Granger causal structure.

Causal Discovery

Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection

1 code implementation12 Jul 2022 Xubin Zhong, Changxing Ding, Zijian Li, Shaoli Huang

Specifically, we shift the GT bounding boxes of each labeled human-object pair so that the shifted boxes cover only a certain portion of the GT ones.

Human-Object Interaction Detection Object

Federated Learning with GAN-based Data Synthesis for Non-IID Clients

no code implementations11 Jun 2022 Zijian Li, Jiawei Shao, Yuyi Mao, Jessie Hui Wang, Jun Zhang

A combination of the local private dataset and synthetic dataset with confident pseudo labels leads to nearly identical data distributions among clients, which improves the consistency among local models and benefits the global aggregation.

Federated Learning Generative Adversarial Network +1

Time-Series Domain Adaptation via Sparse Associative Structure Alignment: Learning Invariance and Variance

no code implementations7 May 2022 Zijian Li, Ruichu Cai, Jiawei Chen, Yuguan Yan, Wei Chen, Keli Zhang, Junjian Ye

Based on this inspiration, we investigate the domain-invariant unweighted sparse associative structures and the domain-variant strengths of the structures.

Time Series Time Series Analysis +2

REST: Debiased Social Recommendation via Reconstructing Exposure Strategies

1 code implementation13 Jan 2022 Ruichu Cai, Fengzhu Wu, Zijian Li, Jie Qiao, Wei Chen, Yuexing Hao, Hao Gu

By explicitly Reconstructing Exposure STrategies (REST in short), we formalize the recommendation problem as the counterfactual reasoning and propose the debiased social recommendation method.

counterfactual Counterfactual Reasoning +1

Motif Graph Neural Network

1 code implementation30 Dec 2021 Xuexin Chen, Ruichu Cai, Yuan Fang, Min Wu, Zijian Li, Zhifeng Hao

However, standard GNNs in the neighborhood aggregation paradigm suffer from limited discriminative power in distinguishing \emph{high-order} graph structures as opposed to \emph{low-order} structures.

Graph Classification Graph Embedding +2

Domain Adaptation with Invariant Representation Learning: What Transformations to Learn?

1 code implementation NeurIPS 2021 Petar Stojanov, Zijian Li, Mingming Gong, Ruichu Cai, Jaime Carbonell, Kun Zhang

We provide reasoning why when the supports of the source and target data from overlap, any map of $X$ that is fixed across domains may not be suitable for domain adaptation via invariant features.

Representation Learning Transfer Learning +1

TEA: A Sequential Recommendation Framework via Temporally Evolving Aggregations

1 code implementation14 Nov 2021 Zijian Li, Ruichu Cai, Fengzhu Wu, Sili Zhang, Hao Gu, Yuexing Hao, Yuguang

To achieve this, we firstly formalize sequential recommendation as a problem to estimate conditional probability given temporal dynamic heterogeneous graphs and user behavior sequences.

Sequential Recommendation

Transferable Time-Series Forecasting under Causal Conditional Shift

1 code implementation5 Nov 2021 Zijian Li, Ruichu Cai, Tom Z. J Fu, Zhifeng Hao, Kun Zhang

In order to address these challenges, we analyze variational conditional dependencies in time-series data and find that the causal structures are usually stable among domains, and further raise the causal conditional shift assumption.

Domain Adaptation Semi-supervised Domain Adaptation +2

Graph Domain Adaptation: A Generative View

no code implementations14 Jun 2021 Ruichu Cai, Fengzhu Wu, Zijian Li, Pengfei Wei, Lingling Yi, Kun Zhang

Based on this assumption, we propose a disentanglement-based unsupervised domain adaptation method for the graph-structured data, which applies variational graph auto-encoders to recover these latent variables and disentangles them via three supervised learning modules.

Disentanglement Graph Classification +2

Aggregating From Multiple Target-Shifted Sources

1 code implementation9 May 2021 Changjian Shui, Zijian Li, Jiaqi Li, Christian Gagné, Charles Ling, Boyu Wang

Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain.

Unsupervised Domain Adaptation

Unified Principles For Multi-Source Transfer Learning Under Label Shifts

no code implementations1 Jan 2021 Changjian Shui, Zijian Li, Jiaqi Li, Christian Gagné, Charles Ling, Boyu Wang

We study the label shift problem in multi-source transfer learning and derive new generic principles to control the target generalization risk.

Transfer Learning Unsupervised Domain Adaptation

Learning Disentangled Semantic Representation for Domain Adaptation

1 code implementation22 Dec 2020 Ruichu Cai, Zijian Li, Pengfei Wei, Jie Qiao, Kun Zhang, Zhifeng Hao

Different from previous efforts on the entangled feature space, we aim to extract the domain invariant semantic information in the latent disentangled semantic representation (DSR) of the data.

Domain Adaptation

Time Series Domain Adaptation via Sparse Associative Structure Alignment

no code implementations22 Dec 2020 Ruichu Cai, Jiawei Chen, Zijian Li, Wei Chen, Keli Zhang, Junjian Ye, Zhuozhang Li, Xiaoyan Yang, Zhenjie Zhang

To reduce the difficulty in the discovery of causal structure, we relax it to the sparse associative structure and propose a novel sparse associative structure alignment model for domain adaptation.

Domain Adaptation Time Series +1

Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition

1 code implementation22 Dec 2020 Zhifeng Hao, Di Lv, Zijian Li, Ruichu Cai, Wen Wen, Boyan Xu

In the proposed framework, the domain-specific information is integrated with the domain-specific latent variables by using a domain predictor.

Cross-Lingual NER Domain Adaptation +3

TAG : Type Auxiliary Guiding for Code Comment Generation

no code implementations ACL 2020 Ruichu Cai, Zhihao Liang, Boyan Xu, Zijian Li, Yuexing Hao, Yao Chen

Existing leading code comment generation approaches with the structure-to-sequence framework ignores the type information of the interpretation of the code, e. g., operator, string, etc.

Code Comment Generation Comment Generation +3

Disentanglement Challenge: From Regularization to Reconstruction

no code implementations30 Nov 2019 Jie Qiao, Zijian Li, Boyan Xu, Ruichu Cai, Kun Zhang

The challenge of learning disentangled representation has recently attracted much attention and boils down to a competition using a new real world disentanglement dataset (Gondal et al., 2019).


Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems

no code implementations13 Oct 2019 Zijian Li, Ruichu Cai, Kok Soon Chai, Hong Wei Ng, Hoang Dung Vu, Marianne Winslett, Tom Z. J. Fu, Boyan Xu, Xiaoyan Yang, Zhenjie Zhang

However, the mainstream domain adaptation methods cannot achieve ideal performance on time series data, because most of them focus on static samples and even the existing time series domain adaptation methods ignore the properties of time series data, such as temporal causal mechanism.

Domain Adaptation Fault Detection +2

An Encoder-Decoder Framework Translating Natural Language to Database Queries

no code implementations16 Nov 2017 Ruichu Cai, Boyan Xu, Xiaoyan Yang, Zhenjie Zhang, Zijian Li, Zhihao Liang

These techniques help the neural network better focus on understanding semantics of operations in natural language and save the efforts on SQL grammar learning.

Machine Translation Management +2

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