Search Results for author: Jie Ren

Found 59 papers, 26 papers with code

A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models

no code implementations13 Feb 2023 James Urquhart Allingham, Jie Ren, Michael W Dusenberry, Jeremiah Zhe Liu, Xiuye Gu, Yin Cui, Dustin Tran, Balaji Lakshminarayanan

In particular, we ask "Given a large pool of prompts, can we automatically score the prompts and ensemble those that are most suitable for a particular downstream dataset, without needing access to labeled validation data?".

Prompt Engineering Zero-Shot Learning

Improving the Robustness of Summarization Models by Detecting and Removing Input Noise

no code implementations20 Dec 2022 Kundan Krishna, Yao Zhao, Jie Ren, Balaji Lakshminarayanan, Jiaming Luo, Mohammad Saleh, Peter J. Liu

We present a large empirical study quantifying the sometimes severe loss in performance (up to 12 ROUGE-1 points) from different types of input noise for a range of datasets and model sizes.

Abstractive Text Summarization

TorchOpt: An Efficient Library for Differentiable Optimization

1 code implementation13 Nov 2022 Jie Ren, Xidong Feng, Bo Liu, Xuehai Pan, Yao Fu, Luo Mai, Yaodong Yang

TorchOpt further provides a high-performance distributed execution runtime.

Transferable Unlearnable Examples

no code implementations18 Oct 2022 Jie Ren, Han Xu, Yuxuan Wan, Xingjun Ma, Lichao Sun, Jiliang Tang

The unlearnable strategies have been introduced to prevent third parties from training on the data without permission.

Probabilistic Categorical Adversarial Attack & Adversarial Training

no code implementations17 Oct 2022 Pengfei He, Han Xu, Jie Ren, Yuxuan Wan, Zitao Liu, Jiliang Tang

To tackle this problem, we propose Probabilistic Categorical Adversarial Attack (PCAA), which transfers the discrete optimization problem to a continuous problem that can be solved efficiently by Projected Gradient Descent.

Adversarial Attack

Out-of-Distribution Detection and Selective Generation for Conditional Language Models

no code implementations30 Sep 2022 Jie Ren, Jiaming Luo, Yao Zhao, Kundan Krishna, Mohammad Saleh, Balaji Lakshminarayanan, Peter J. Liu

Furthermore, the space of potential low-quality outputs is larger as arbitrary text can be generated and it is important to know when to trust the generated output.

Abstractive Text Summarization Out-of-Distribution Detection +1

Exemplar-Based Image Colorization with A Learning Framework

no code implementations13 Sep 2022 Zhenfeng Xue, Jiandang Yang, Jie Ren, Yong liu

This method can be viewed as a hybrid of exemplar-based and learning-based method, and it decouples the colorization process and learning process so as to generate various color styles for the same gray image.

Colorization Image Colorization

Color Image Edge Detection using Multi-scale and Multi-directional Gabor filter

no code implementations16 Aug 2022 Yunhong Li, Yuandong Bi, Weichuan Zhang, Jie Ren, Jinni Chen

Second, a set of Gabor filters are used to smooth the input images and the color edge strength maps are extracted, which are fused into a new ESM with the noise robustness and accurate edge extraction.

Edge Detection

Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability

no code implementations24 Jul 2022 Quanshi Zhang, Xin Wang, Jie Ren, Xu Cheng, Shuyun Lin, Yisen Wang, Xiangming Zhu

This paper summarizes the common mechanism shared by twelve previous transferability-boosting methods in a unified view, i. e., these methods all reduce game-theoretic interactions between regional adversarial perturbations.

Defense Against Gradient Leakage Attacks via Learning to Obscure Data

no code implementations1 Jun 2022 Yuxuan Wan, Han Xu, Xiaorui Liu, Jie Ren, Wenqi Fan, Jiliang Tang

However, federated learning is still under the risk of privacy leakage because of the existence of attackers who deliberately conduct gradient leakage attacks to reconstruct the client data.

Federated Learning Privacy Preserving

Why Adversarial Training of ReLU Networks Is Difficult?

no code implementations30 May 2022 Xu Cheng, Hao Zhang, Yue Xin, Wen Shen, Jie Ren, Quanshi Zhang

We also prove that adversarial training tends to strengthen the influence of unconfident input samples with large gradient norms in an exponential manner.

Pluralistic Image Completion with Probabilistic Mixture-of-Experts

no code implementations18 May 2022 Xiaobo Xia, Wenhao Yang, Jie Ren, Yewen Li, Yibing Zhan, Bo Han, Tongliang Liu

Second, the constraints for diversity are designed to be task-agnostic, which causes the constraints to not work well.

Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs

1 code implementation4 May 2022 Jie Ren, Mingjie Li, Meng Zhou, Shih-Han Chan, Quanshi Zhang

Based on the proposed metrics, we analyze two typical phenomena of the change of the transformation complexity during the training process, and explore the ceiling of a DNN's complexity.

Adversarial Robustness Disentanglement

A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

2 code implementations1 May 2022 Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren, Zi Lin, Yeming Wen, Ghassen Jerfel, Zack Nado, Jasper Snoek, Dustin Tran, Balaji Lakshminarayanan

The most popular approaches to estimate predictive uncertainty in deep learning are methods that combine predictions from multiple neural networks, such as Bayesian neural networks (BNNs) and deep ensembles.

Data Augmentation Probabilistic Deep Learning

Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding

1 code implementation Findings (ACL) 2022 Rui Cao, Yihao Wang, Yuxin Liang, Ling Gao, Jie Zheng, Jie Ren, Zheng Wang

We define a maximum traceable distance metric, through which we learn to what extent the text contrastive learning benefits from the historical information of negative samples.

Contrastive Learning Sentence Embedding +3

A Theoretical Understanding of Gradient Bias in Meta-Reinforcement Learning

1 code implementation31 Dec 2021 Bo Liu, Xidong Feng, Jie Ren, Luo Mai, Rui Zhu, Haifeng Zhang, Jun Wang, Yaodong Yang

Gradient-based Meta-RL (GMRL) refers to methods that maintain two-level optimisation procedures wherein the outer-loop meta-learner guides the inner-loop gradient-based reinforcement learner to achieve fast adaptations.

Atari Games Meta Reinforcement Learning +3

MegBA: A GPU-Based Distributed Library for Large-Scale Bundle Adjustment

1 code implementation2 Dec 2021 Jie Ren, Wenteng Liang, Ran Yan, Luo Mai, Shiwen Liu, Xiao Liu

Large-scale Bundle Adjustment (BA) requires massive memory and computation resources which are difficult to be fulfilled by existing BA libraries.

Trap of Feature Diversity in the Learning of MLPs

no code implementations2 Dec 2021 Dongrui Liu, Shaobo Wang, Jie Ren, Kangrui Wang, Sheng Yin, Huiqi Deng, Quanshi Zhang

In this paper, we focus on a typical two-phase phenomenon in the learning of multi-layer perceptrons (MLPs), and we aim to explain the reason for the decrease of feature diversity in the first phase.

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness

1 code implementation NeurIPS 2021 Jie Ren, Die Zhang, Yisen Wang, Lu Chen, Zhanpeng Zhou, Yiting Chen, Xu Cheng, Xin Wang, Meng Zhou, Jie Shi, Quanshi Zhang

This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs.

Adversarial Robustness

Towards Axiomatic, Hierarchical, and Symbolic Explanation for Deep Models

no code implementations11 Nov 2021 Jie Ren, Mingjie Li, Qirui Chen, Huiqi Deng, Quanshi Zhang

This paper aims to show that the inference logic of a deep model can be faithfully approximated as a sparse, symbolic causal graph.

A Unified Game-Theoretic Interpretation of Adversarial Robustness

1 code implementation5 Nov 2021 Jie Ren, Die Zhang, Yisen Wang, Lu Chen, Zhanpeng Zhou, Yiting Chen, Xu Cheng, Xin Wang, Meng Zhou, Jie Shi, Quanshi Zhang

This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i. e.} the view of multi-order interactions between input variables of DNNs.

Adversarial Robustness

ESOD:Edge-based Task Scheduling for Object Detection

no code implementations20 Oct 2021 Yihao Wang, Ling Gao, Jie Ren, Rui Cao, Hai Wang, Jie Zheng, Quanli Gao

In detail, we train a DNN model (termed as pre-model) to predict which object detection model to use for the coming task and offloads to which edge servers by physical characteristics of the image task (e. g., brightness, saturation).

object-detection Object Detection +1

Cellular Network Radio Propagation Modeling with Deep Convolutional Neural Networks

no code implementations5 Oct 2021 Xin Zhang, Xiujun Shu, Bingwen Zhang, Jie Ren, Lizhou Zhou, Xin Chen

Deterministic models, such as ray tracing based on physical laws of wave propagation, are more accurate and site specific.

Towards a Game-Theoretic View of Baseline Values in the Shapley Value

no code implementations29 Sep 2021 Jie Ren, Zhanpeng Zhou, Qirui Chen, Quanshi Zhang

In the computation of Shapley values, people usually set an input variable to its baseline value to represent the absence of this variable.

Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI

no code implementations16 Jul 2021 Quanshi Zhang, Tian Han, Lixin Fan, Zhanxing Zhu, Hang Su, Ying Nian Wu, Jie Ren, Hao Zhang

This workshop pays a special interest in theoretic foundations, limitations, and new application trends in the scope of XAI.

Sawtooth Factorial Topic Embeddings Guided Gamma Belief Network

1 code implementation30 Jun 2021 Zhibin Duan, Dongsheng Wang, Bo Chen, Chaojie Wang, Wenchao Chen, Yewen Li, Jie Ren, Mingyuan Zhou

However, they often assume in the prior that the topics at each layer are independently drawn from the Dirichlet distribution, ignoring the dependencies between the topics both at the same layer and across different layers.

Topic Models Variational Inference

A Game-Theoretic Taxonomy of Visual Concepts in DNNs

no code implementations21 Jun 2021 Xu Cheng, Chuntung Chu, Yi Zheng, Jie Ren, Quanshi Zhang

In this paper, we rethink how a DNN encodes visual concepts of different complexities from a new perspective, i. e. the game-theoretic multi-order interactions between pixels in an image.

A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection

3 code implementations16 Jun 2021 Jie Ren, Stanislav Fort, Jeremiah Liu, Abhijit Guha Roy, Shreyas Padhy, Balaji Lakshminarayanan

Mahalanobis distance (MD) is a simple and popular post-processing method for detecting out-of-distribution (OOD) inputs in neural networks.

Intent Detection Out-of-Distribution Detection +1

Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?

no code implementations22 May 2021 Jie Ren, Zhanpeng Zhou, Qirui Chen, Quanshi Zhang

Therefore, we revisit the feature representation of a DNN in terms of causality, and propose to use causal patterns to examine whether the masking method faithfully removes information encoded in input variables.

Probabilistic Mixture-of-Experts for Efficient Deep Reinforcement Learning

1 code implementation19 Apr 2021 Jie Ren, Yewen Li, Zihan Ding, Wei Pan, Hao Dong

However, grasping distinguishable skills for some tasks with non-unique optima can be essential for further improving its learning efficiency and performance, which may lead to a multimodal policy represented as a mixture-of-experts (MOE).

reinforcement-learning Reinforcement Learning (RL)

Learning to Remove: Towards Isotropic Pre-trained BERT Embedding

1 code implementation12 Apr 2021 Yuxin Liang, Rui Cao, Jie Zheng, Jie Ren, Ling Gao

We train the weights on word similarity tasks and show that processed embedding is more isotropic.

Semantic Textual Similarity Word Similarity

Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning

no code implementations4 Apr 2021 Tong Chen, Hongzhi Yin, Jie Ren, Zi Huang, Xiangliang Zhang, Hao Wang

In WIDEN, we propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.

Graph Representation Learning Transductive Learning

A Unified Game-Theoretic Interpretation of Adversarial Robustness

1 code implementation12 Mar 2021 Jie Ren, Die Zhang, Yisen Wang, Lu Chen, Zhanpeng Zhou, Yiting Chen, Xu Cheng, Xin Wang, Meng Zhou, Jie Shi, Quanshi Zhang

This paper provides a unified view to explain different adversarial attacks and defense methods, i. e. the view of multi-order interactions between input variables of DNNs.

Adversarial Robustness

Identifying Gene-environment interactions with robust marginal Bayesian variable selection

no code implementations23 Feb 2021 Xi Lu, Kun Fan, Jie Ren, Cen Wu

In this study, we propose a novel marginal Bayesian variable selection method for G$\times$E studies.

Variable Selection Methodology

ZeRO-Offload: Democratizing Billion-Scale Model Training

3 code implementations18 Jan 2021 Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, Yuxiong He

By combining compute and memory efficiency with ease-of-use, ZeRO-Offload democratizes large-scale model training making it accessible to even data scientists with access to just a single GPU.

Understanding, Analyzing, and Optimizing the Complexity of Deep Models

no code implementations1 Jan 2021 Jie Ren, Mingjie Li, Meng Zhou, Shih-Han Chan, Zexu Liu, Quanshi Zhang

Based on the proposed metrics, we analyze two typical phenomena of the change of the transformation complexity during the training process, and explore the ceiling of a DNN’s complexity.


Towards A Unified Understanding and Improving of Adversarial Transferability

no code implementations ICLR 2021 Xin Wang, Jie Ren, Shuyun Lin, Xiangming Zhu, Yisen Wang, Quanshi Zhang

We discover and prove the negative correlation between the adversarial transferability and the interaction inside adversarial perturbations.

Analytic critical points of charged Renyi entropies from hyperbolic black holes

no code implementations23 Dec 2020 Jie Ren

The first system is the Reissner-Nordstrom-AdS$_5$ black hole, which has finite entropy at zero temperature.

High Energy Physics - Theory General Relativity and Quantum Cosmology

Receptivity and stability of hypersonic leading-edge sweep flows around a blunt body

no code implementations3 Dec 2020 Youcheng Xi, Jie Ren, Liang Wang, Song Fu

We establish an adjoint-based bi-orthogonal eigenfunction system to address the receptivity problem of such flows to any external forces and boundary perturbations.

Fluid Dynamics

HM-ANN: Efficient Billion-Point Nearest Neighbor Search on Heterogeneous Memory

no code implementations NeurIPS 2020 Jie Ren, Minjia Zhang, Dong Li

The emergence of heterogeneous memory (HM) brings a solution to significantly increase memory capacity and break the above tradeoff: Using HM, billions of data points can be placed in the main memory on a single machine without using any data compression.

Data Compression Quantization

A Unified Approach to Interpreting and Boosting Adversarial Transferability

1 code implementation8 Oct 2020 Xin Wang, Jie Ren, Shuyun Lin, Xiangming Zhu, Yisen Wang, Quanshi Zhang

We discover and prove the negative correlation between the adversarial transferability and the interaction inside adversarial perturbations.

Interpreting and Disentangling Feature Components of Various Complexity from DNNs

1 code implementation29 Jun 2020 Jie Ren, Mingjie Li, Zexu Liu, Quanshi Zhang

This paper aims to define, quantify, and analyze the feature complexity that is learned by a DNN.

Knowledge Distillation

SummAE: Zero-Shot Abstractive Text Summarization using Length-Agnostic Auto-Encoders

2 code implementations2 Oct 2019 Peter J. Liu, Yu-An Chung, Jie Ren

We show results for extractive and human baselines to demonstrate a large abstractive gap in performance.

Abstractive Text Summarization Denoising

Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift

2 code implementations NeurIPS 2019 Yaniv Ovadia, Emily Fertig, Jie Ren, Zachary Nado, D. Sculley, Sebastian Nowozin, Joshua V. Dillon, Balaji Lakshminarayanan, Jasper Snoek

Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {\em uncertainty}.

Probabilistic Deep Learning

Semi-parametric Bayesian variable selection for gene-environment interactions

3 code implementations3 Jun 2019 Jie Ren, Fei Zhou, Xiaoxi Li, Qi Chen, Hongmei Zhang, Shuangge Ma, Yu Jiang, Cen Wu

Existing Bayesian methods for G$\times$E interaction studies are challenged by the high-dimensional nature of the study and the complexity of environmental influences.


Interpretable Complex-Valued Neural Networks for Privacy Protection

1 code implementation ICLR 2020 Liyao Xiang, Haotian Ma, Hao Zhang, Yifan Zhang, Jie Ren, Quanshi Zhang

Previous studies have found that an adversary attacker can often infer unintended input information from intermediate-layer features.

Explaining Neural Networks Semantically and Quantitatively

no code implementations ICCV 2019 Runjin Chen, Hao Chen, Ge Huang, Jie Ren, Quanshi Zhang

This paper presents a method to explain the knowledge encoded in a convolutional neural network (CNN) quantitatively and semantically.

To Compress, or Not to Compress: Characterizing Deep Learning Model Compression for Embedded Inference

no code implementations21 Oct 2018 Qing Qin, Jie Ren, Jialong Yu, Ling Gao, Hai Wang, Jie Zheng, Yansong Feng, Jianbin Fang, Zheng Wang

We experimentally show that how two mainstream compression techniques, data quantization and pruning, perform on these network architectures and the implications of compression techniques to the model storage size, inference time, energy consumption and performance metrics.

Image Classification Model Compression +1

Active Learning for Wireless IoT Intrusion Detection

no code implementations4 Aug 2018 Kai Yang, Jie Ren, Yanqiao Zhu, Weiyi Zhang

This paper discusses the human-in-the-loop active learning approach for wireless intrusion detection.

Active Learning BIG-bench Machine Learning +1

An End-to-End Compression Framework Based on Convolutional Neural Networks

5 code implementations2 Aug 2017 Feng Jiang, Wen Tao, Shaohui Liu, Jie Ren, Xun Guo, Debin Zhao

The second CNN, named reconstruction convolutional neural network (RecCNN), is used to reconstruct the decoded image with high-quality in the decoding end.

Denoising Image Compression

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