Author name cluster

Xiangrui Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

AAAI Conference 2023 Conference Paper

Learning Compact Features via In-Training Representation Alignment

Xin Li
Xiangrui Li
Deng Pan
Yao Qiang
Dongxiao Zhu

Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of the feature extractor (i.e., last hidden layer) and a linear classifier (i.e., output layer) that are trained jointly with stochastic gradient descent (SGD) on the loss function (e.g., cross-entropy). In each epoch, the true gradient of the loss function is estimated using a mini-batch sampled from the training set and model parameters are then updated with the mini-batch gradients. Although the latter provides an unbiased estimation of the former, they are subject to substantial variances derived from the size and number of sampled mini-batches, leading to noisy and jumpy updates. To stabilize such undesirable variance in estimating the true gradients, we propose In-Training Representation Alignment (ITRA) that explicitly aligns feature distributions of two different mini-batches with a matching loss in the SGD training process. We also provide a rigorous analysis of the desirable effects of the matching loss on feature representation learning: (1) extracting compact feature representation; (2) reducing over-adaption on mini-batches via an adaptively weighting mechanism; and (3) accommodating to multi-modalities. Finally, we conduct large-scale experiments on both image and text classifications to demonstrate its superior performance to the strong baselines.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Improving Adversarial Robustness via Probabilistically Compact Loss with Logit Constraints

Xin Li
Xiangrui Li
Deng Pan
Dongxiao Zhu

Convolutional neural networks (CNNs) have achieved stateof-the-art performance on various tasks in computer vision. However, recent studies demonstrate that these models are vulnerable to carefully crafted adversarial samples and suffer from a significant performance drop when predicting them. Many methods have been proposed to improve adversarial robustness (e. g. , adversarial training and new loss functions to learn adversarially robust feature representations). Here we offer a unique insight into the predictive behavior of CNNs that they tend to misclassify adversarial samples into the most probable false classes. This inspires us to propose a new Probabilistically Compact (PC) loss with logit constraints which can be used as a drop-in replacement for crossentropy (CE) loss to improve CNN’s adversarial robustness. Specifically, PC loss enlarges the probability gaps between true class and false classes meanwhile the logit constraints prevent the gaps from being melted by a small perturbation. We extensively compare our method with the state-of-the-art using large scale datasets under both white-box and blackbox attacks to demonstrate its effectiveness. The source codes are available at https: //github. com/xinli0928/PC-LC.

PDF Details

IJCAI Conference 2020 Conference Paper

Explainable Recommendation via Interpretable Feature Mapping and Evaluation of Explainability

Deng Pan
Xiangrui Li
Xin Li
Dongxiao Zhu

Latent factor collaborative filtering (CF) has been a widely used technique for recommender system by learning the semantic representations of users and items. Recently, explainable recommendation has attracted much attention from research community. However, trade-off exists between explainability and performance of the recommendation where metadata is often needed to alleviate the dilemma. We present a novel feature mapping approach that maps the uninterpretable general features onto the interpretable aspect features, achieving both satisfactory accuracy and explainability in the recommendations by simultaneous minimization of rating prediction loss and interpretation loss. To evaluate the explainability, we propose two new evaluation metrics specifically designed for aspect-level explanation using surrogate ground truth. Experimental results demonstrate a strong performance in both recommendation and explaining explanation, eliminating the need for metadata. Code is available from https: //github. com/pd90506/AMCF.

PDF Details DOI

AAAI Conference 2020 Conference Paper

On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks

Xiangrui Li
Xin Li
Deng Pan
Dongxiao Zhu

Deep convolutional neural networks (CNNs) trained with logistic and softmax losses have made signiﬁcant advancement in visual recognition tasks in computer vision. When training data exhibit class imbalances, the class-wise reweighted version of logistic and softmax losses are often used to boost performance of the unweighted version. In this paper, motivated to explain the reweighting mechanism, we explicate the learning property of those two loss functions by analyzing the necessary condition (e. g. , gradient equals to zero) after training CNNs to converge to a local minimum. The analysis immediately provides us explanations for understanding (1) quantitative effects of the class-wise reweighting mechanism: deterministic effectiveness for binary classiﬁcation using logistic loss yet indeterministic for multi-class classiﬁcation using softmax loss; (2) disadvantage of logistic loss for single-label multi-class classiﬁcation via one-vs. -all approach, which is due to the averaging effect on predicted probabilities for the negative class (e. g. , non-target classes) in the learning process. With the disadvantage and advantage of logistic loss disentangled, we thereafter propose a novel reweighted logistic loss for multi-class classiﬁcation. Our simple yet effective formulation improves ordinary logistic loss by focusing on learning hard non-target classes (target vs. non-target class in one-vs. -all) and turned out to be competitive with softmax loss. We evaluate our method on several benchmark datasets to demonstrate its effectiveness.

PDF Details

YNICL Journal 2018 Journal Article

Identifying first-episode drug naïve patients with schizophrenia with or without auditory verbal hallucinations using whole-brain functional connectivity: A pattern analysis study

Peng Huang
Long-Biao Cui
Xiangrui Li
Zhong-Lin Lu
Xia Zhu
Yibin Xi
Huaning Wang
Baojuan Li

Many studies have focused on patients with schizophrenia with or without auditory verbal hallucinations (AVHs), but due to the complexity of schizophrenia, biologically based diagnosis of patients with schizophrenia remains unsolved. The objectives of this study are to classify between first-episode drug-naïve patients with schizophrenia and healthy controls, and to classify between patients with and without AVHs. Resting state fMRI data from 41 patients with schizophrenia (22 with and 19 without AVHs) and 23 normal controls (NC) were included to compute functional connectivity between brain regions. Classifiers based on support vector machine (SVM) were developed to classify patients with schizophrenia from NC, as well as between the two subgroups of patients. The classification accuracy was evaluated with a leave-one-out cross-validation (LOOCV) strategy. The accuracy in discriminating both subgroups of patients from NC was 81.3%, with 92.0% (sensitivity) and 65.2% (specificity) for the patients and NC, respectively. The classification accuracy in discriminating patients with and without AVHs was 75.6%, with 77.3% (sensitivity) and 73.9% (specificity) for patients with and without AVHs, respectively. The results suggest that functional connectivity provided good discriminative power not only for identifying patients with schizophrenia among NC, but also in discriminating patients with schizophrenia with and without AVHs.

Details DOI

YNIMG Journal 2009 Journal Article

Neural correlates of risk prediction error during reinforcement learning in humans

Mathieu d'Acremont
Zhong-Lin Lu
Xiangrui Li
Martial Van der Linden
Antoine Bechara

Behavioral studies have shown for decades that humans are sensitive to risk when making decisions. More recently, brain activities have been shown to be correlated with risky choices. But an important gap needs to be filled: How does the human brain learn which decisions are risky? In cognitive neuroscience, reinforcement learning has never been used to estimate reward variance, a common measure of risk in economics and psychology. It is thus unknown which brain regions are involved in risk learning. To address this question, participants completed a decision-making task during fMRI. They chose repetitively from four decks of cards and each selection was followed by a stochastic payoff. Expected reward and risk differed among the decks. Participants' aim was to maximize payoffs. Risk and reward prediction errors were calculated after each payoff based on a novel reinforcement learning model. For reward prediction error, the strongest correlation was found with the BOLD response in the striatum. For risk prediction error, the strongest correlation was found with the BOLD responses in the insula and inferior frontal gyrus. We conclude that risk and reward prediction errors are processed by distinct neural circuits during reinforcement learning. Additional analyses revealed that the BOLD response in the inferior frontal gyrus was more pronounced for risk aversive participants, suggesting that this region also serves to inhibit risky choices.

Details DOI