Arrow Research search

Author name cluster

Linjun Zhang

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.

28 papers
2 author rows

Possible papers

28

NeurIPS Conference 2025 Conference Paper

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

  • Ran Xu
  • Yuchen Zhuang
  • Zihan Dong
  • Ruiyu Wang
  • Yue Yu
  • Joyce Ho
  • Linjun Zhang
  • Haoyu Wang

Search-augmented LLMs often struggle with complex reasoning tasks due to ineffective multi-hop retrieval and limited reasoning ability. We propose AceSearcher, a cooperative self-play framework that trains a single large language model (LLM) to alternate between two roles: a decomposer that breaks down complex queries and a solver that integrates retrieved contexts for answer generation. AceSearcher couples supervised fine-tuning on a diverse mixture of search, reasoning, and decomposition tasks with reinforcement fine-tuning optimized for final answer accuracy, eliminating the need for intermediate annotations. Extensive experiments on three reasoning-intensive tasks across 10 datasets show that AceSearcher outperforms state-of-the-art baselines, achieving an average exact match improvement of 7. 6%. Remarkably, on document-level finance reasoning tasks, AceSearcher-32B matches the performance of the giant DeepSeek-V3 model using less than 5% of iits parameters. Even at smaller scales (1. 5B and 8B), AceSearcher often surpasses existing search-augmented LLMs with up to 9× more parameters, highlighting its exceptional efficiency and effectiveness in tackling complex reasoning tasks.

PDF Details

ICML Conference 2025 Conference Paper

FactTest: Factuality Testing in Large Language Models with Finite-Sample and Distribution-Free Guarantees

  • Fan Nie
  • Xiaotian Hou
  • Shuhang Lin
  • James Y. Zou
  • Huaxiu Yao
  • Linjun Zhang

The propensity of large language models (LLMs) to generate hallucinations and non-factual content undermines their reliability in high-stakes domains, where rigorous control over Type I errors (the conditional probability of incorrectly classifying hallucinations as truthful content) is essential. Despite its importance, formal verification of LLM factuality with such guarantees remains largely unexplored. In this paper, we introduce FactTest, a novel framework that statistically assesses whether an LLM can provide correct answers to given questions with high-probability correctness guarantees. We formulate hallucination detection as a hypothesis testing problem to enforce an upper bound of Type I errors at user-specified significance levels. Notably, we prove that FactTest also ensures strong Type II error control under mild conditions and can be extended to maintain its effectiveness when covariate shifts exist. Our approach is distribution-free and works for any number of human-annotated samples. It is model-agnostic and applies to any black-box or white-box LM. Extensive experiments on question-answering (QA) benchmarks demonstrate that FactTest effectively detects hallucinations and enable LLMs to abstain from answering unknown questions, leading to an over 40% accuracy improvement.

Details

ICML Conference 2025 Conference Paper

Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing

  • Tianci Liu 0003
  • Ruirui Li 0002
  • Zihan Dong
  • Hui Liu 0031
  • Xianfeng Tang
  • Qingyu Yin
  • Linjun Zhang
  • Haoyu Wang 0004

Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outdated quickly in the fast-changing world. This motivates the development of knowledge editing (KE) to update specific knowledge in LLMs without changing unrelated others or compromising their pre-trained capabilities. Previous efforts sought to update a small amount of parameters of a LLM and proved effective for making selective updates. Nonetheless, the edited LLM often exhibits degraded ability to reason about the new knowledge. In this work, we identify a key issue: heterogeneous token overfitting (HTO), where the LLM overfits different tokens in the provided knowledge at varying rates. To tackle this, we propose OVERTONE, a token-level smoothing method that mitigates HTO by adaptively refining the target distribution. Theoretically, OVERTONE offers better parameter updates with negligible computation overhead. It also induces an implicit DPO but does not require preference data pairs. Extensive experiments across four editing methods, two LLMs, and diverse scenarios demonstrate the effectiveness and versatility of our method.

Details

ICLR Conference 2025 Conference Paper

MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models

  • Peng Xia 0005
  • Kangyu Zhu
  • Haoran Li 0011
  • Tianze Wang
  • Weijia Shi
  • Sheng Wang
  • Linjun Zhang
  • James Y. Zou

Artificial Intelligence (AI) has demonstrated significant potential in healthcare, particularly in disease diagnosis and treatment planning. Recent progress in Medical Large Vision-Language Models (Med-LVLMs) has opened up new possibilities for interactive diagnostic tools. However, these models often suffer from factual hallucination, which can lead to incorrect diagnoses. Fine-tuning and retrieval-augmented generation (RAG) have emerged as methods to address these issues. However, the amount of high-quality data and distribution shifts between training data and deployment data limit the application of fine-tuning methods. Although RAG is lightweight and effective, existing RAG-based approaches are not sufficiently general to different medical domains and can potentially cause misalignment issues, both between modalities and between the model and the ground truth. In this paper, we propose a versatile multimodal RAG system, MMed-RAG, designed to enhance the factuality of Med-LVLMs. Our approach introduces a domain-aware retrieval mechanism, an adaptive retrieved contexts selection, and a provable RAG-based preference fine-tuning strategy. These innovations make the RAG process sufficiently general and reliable, significantly improving alignment when introducing retrieved contexts. Experimental results across five medical datasets (involving radiology, ophthalmology, pathology) on medical VQA and report generation demonstrate that MMed-RAG can achieve an average improvement of 43.8% in factual accuracy in the factual accuracy of Med-LVLMs.

Details

ICML Conference 2025 Conference Paper

MPO: An Efficient Post-Processing Framework for Mixing Diverse Preference Alignment

  • Tianze Wang
  • Dongnan Gui
  • Yifan Hu
  • Shuhang Lin
  • Linjun Zhang

Reinforcement Learning from Human Feedback (RLHF) has shown promise in aligning large language models (LLMs). Yet its reliance on a singular reward model often overlooks the diversity of human preferences. Recent approaches address this limitation by leveraging multi-dimensional feedback to fine-tune corresponding reward models and train LLMs using reinforcement learning. However, the process is costly and unstable, especially given the competing and heterogeneous nature of human preferences. In this paper, we propose Mixing Preference Optimization (MPO), a post-processing framework for aggregating single-objective policies as an alternative to both multi-objective RLHF (MORLHF) and MaxMin-RLHF. MPO avoids alignment from scratch. Instead, it log-linearly combines existing policies into a unified one with the weight of each policy computed via a batch stochastic mirror descent. Empirical results demonstrate that MPO achieves balanced performance across diverse preferences, outperforming or matching existing models with significantly reduced computational costs.

Details

TMLR Journal 2025 Journal Article

Reliable and Responsible Foundation Models

  • Xinyu Yang
  • Junlin Han
  • Rishi Bommasani
  • Jinqi Luo
  • Wenjie Qu
  • Wangchunshu Zhou
  • Adel Bibi
  • Xiyao Wang

Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with broad applications across various domains such as law, medicine, education, finance, and beyond. As these models see increasing real-world deployment, ensuring their reliability and responsibility has become critical for academia, industry, and government. This survey addresses the reliable and responsible development of foundation models. We explore critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift. Our research also covers model limitations, such as hallucinations, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection. For each area, we review the current state of the field and outline concrete future research directions. Additionally, we discuss the intersections between these areas, highlighting their connections and shared challenges. We hope our survey fosters the development of foundation models that are not only powerful but also ethical, trustworthy, reliable, and socially responsible.

PDF Details

ICLR Conference 2024 Conference Paper

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

  • Yiyang Zhou
  • Chenhang Cui
  • Jaehong Yoon
  • Linjun Zhang
  • Zhun Deng
  • Chelsea Finn
  • Mohit Bansal
  • Huaxiu Yao

Large vision-language models (LVLMs) have shown remarkable abilities in understanding visual information with human languages. However, LVLMs still suffer from object hallucination, which is the problem of generating descriptions that include objects that do not actually exist in the images. This can negatively impact many vision-language tasks, such as visual summarization and reasoning. To address this issue, we propose a simple yet powerful algorithm, LVLM Hallucination Revisor (LURE), to post-hoc rectify object hallucination in LVLMs by reconstructing less hallucinatory descriptions. LURE is grounded in a rigorous statistical analysis of the key factors underlying object hallucination, including co-occurrence (the frequent appearance of certain objects alongside others in images), uncertainty (objects with higher uncertainty during LVLM decoding), and object position (hallucination often appears in the later part of the generated text). LURE can also be seamlessly integrated with any LVLMs. We evaluate LURE on six open-source LVLMs and found it outperforms the previous best approach in both general object hallucination evaluation metrics, GPT, and human evaluations.

Details

NeurIPS Conference 2024 Conference Paper

Calibrated Self-Rewarding Vision Language Models

  • Yiyang Zhou
  • Zhiyuan Fan
  • Dongjie Cheng
  • Sihan Yang
  • Zhaorun Chen
  • Chenhang Cui
  • Xiyao Wang
  • Yun Li

Large Vision-Language Models (LVLMs) have made substantial progress by integrating pre-trained large language models (LLMs) and vision models through instruction tuning. Despite these advancements, LVLMs often exhibit the hallucination phenomenon, where generated text responses appear linguistically plausible but contradict the input image, indicating a misalignment between image and text pairs. This misalignment arises because the model tends to prioritize textual information over visual input, even when both the language model and visual representations are of high quality. Existing methods leverage additional models or human annotations to curate preference data and enhance modality alignment through preference optimization. These approaches are resource-intensive and may not effectively reflect the target LVLM's preferences, making the curated preferences easily distinguishable. Our work addresses these challenges by proposing the Calibrated Self-Rewarding (CSR) approach, which enables the model to self-improve by iteratively generating candidate responses, evaluating the reward for each response, and curating preference data for fine-tuning. In the reward modeling, we employ a step-wise strategy and incorporate visual constraints into the self-rewarding process to place greater emphasis on visual input. Empirical results demonstrate that CSR significantly enhances performance and reduces hallucinations across twelve benchmarks and tasks, achieving substantial improvements over existing methods by 7. 62\%. Our empirical results are further supported by rigorous theoretical analysis, under mild assumptions, verifying the effectiveness of introducing visual constraints into the self-rewarding paradigm. Additionally, CSR shows compatibility with different vision-language models and the ability to incrementally improve performance through iterative fine-tuning.

PDF Details DOI

ICML Conference 2024 Conference Paper

Conformal Prediction for Deep Classifier via Label Ranking

  • Jianguo Huang
  • Huajun Xi
  • Linjun Zhang
  • Huaxiu Yao
  • Yue Qiu
  • Hongxin Wei

Conformal prediction is a statistical framework that generates prediction sets containing ground-truth labels with a desired coverage guarantee. The predicted probabilities produced by machine learning models are generally miscalibrated, leading to large prediction sets in conformal prediction. To address this issue, we propose a novel algorithm named $\textit{Sorted Adaptive Prediction Sets}$ (SAPS), which discards all the probability values except for the maximum softmax probability. The key idea behind SAPS is to minimize the dependence of the non-conformity score on the probability values while retaining the uncertainty information. In this manner, SAPS can produce compact prediction sets and communicate instance-wise uncertainty. Extensive experiments validate that SAPS not only lessens the prediction sets but also broadly enhances the conditional coverage rate of prediction sets.

Details

ICML Conference 2024 Conference Paper

Fair Risk Control: A Generalized Framework for Calibrating Multi-group Fairness Risks

  • Lujing Zhang
  • Aaron Roth 0001
  • Linjun Zhang

This paper introduces a framework for post-processing machine learning models so that their predictions satisfy multi-group fairness guarantees. Based on the celebrated notion of multicalibration, we introduce $(s, g, \alpha)-$GMC (Generalized Multi-Dimensional Multicalibration) for multi-dimensional mappings $s$, constraints $g$, and a pre-specified threshold level $\alpha$. We propose associated algorithms to achieve this notion in general settings. This framework is then applied to diverse scenarios encompassing different fairness concerns, including false negative rate control in image segmentation, prediction set conditional uncertainty quantification in hierarchical classification, and de-biased text generation in language models. We conduct numerical studies on several datasets and tasks.

Details

NeurIPS Conference 2024 Conference Paper

Order-Independence Without Fine Tuning

  • Reid McIlroy-Young
  • Katrina Brown
  • Conlan Olson
  • Linjun Zhang
  • Cynthia Dwork

The development of generative language models that can create long and coherent textual outputs via autoregression has lead to a proliferation of uses and a corresponding sweep of analyses as researches work to determine the limitations of this new paradigm. Unlike humans, these ' Large Language Models ' (LLMs) are highly sensitive to small changes in their inputs, leading to unwanted inconsistency in their behavior. One problematic inconsistency when LLMs are used to answer multiple-choice questions or analyze multiple inputs is order dependency: the output of an LLM can (and often does) change significantly when sub-sequences are swapped, despite both orderings being semantically identical. In this paper we present, a technique that guarantees the output of an LLM will not have order dependence on a specified set of sub-sequences. We show that this method provably eliminates order dependency, and that it can be applied to any transformer-based LLM to enable text generation that is unaffected by re-orderings. Delving into the implications of our method, we show that, despite our inputs being out of distribution, the impact on expected accuracy is small, where the expectation is over the order of uniformly chosen shuffling of the candidate responses, and usually significantly less in practice. Thus, can be used as a ' dropped-in ' method on fully trained models. Finally, we discuss how our method's success suggests that other strong guarantees can be obtained on LLM performance via modifying the input representations. Code is available at github. com/reidmcy/set-based-prompting.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity

  • Xinyu Yang
  • Jixuan Leng
  • Geyang Guo
  • Jiawei Zhao
  • Ryumei Nakada
  • Linjun Zhang
  • Huaxiu Yao
  • Beidi Chen

Current PEFT methods for LLMs can achieve high quality, efficient training, or scalable serving, but not all three simultaneously. To address this limitation, we investigate sparse fine-tuning and observe a remarkable improvement in generalization ability. Utilizing this key insight, we propose a family of Structured Sparse Fine-Tuning (S${^2}$FT) methods for LLMs, which concurrently achieve state-of-the-art fine-tuning performance, training efficiency, and inference scalability. S${^2}$FT accomplishes this by "selecting sparsely and computing densely". Based on the coupled structures in LLMs, \model selects a few attention heads and channels in the MHA and FFN modules for each Transformer block, respectively. Next, it co-permutes the weight matrices on both sides of all coupled structures to connect the selected subsets in each layer into a dense submatrix. Finally, S${^2}$FT performs in-place gradient updates on all selected submatrices. Through theoretical analyses and empirical results, our method prevents forgetting while simplifying optimization, delivers SOTA performance on both commonsense and arithmetic reasoning with 4. 6% and 1. 3% average improvements compared to LoRA, and surpasses full FT by 11. 5% when generalizing to various domains after instruction tuning. Using our partial back-propagation algorithm, S${^2}$FT saves training memory up to 3$\times$ and improves latency by 1. 5-2. 7$\times$ compared to full FT, while achieving an average 10\% improvement over LoRA on both metrics. We further demonstrate that the weight updates in S${^2}$FT can be decoupled into adapters, enabling effective fusion, fast switch, and efficient parallelism when serving multiple fine-tuned models.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Beyond Confidence: Reliable Models Should Also Consider Atypicality

  • Mert Yuksekgonul
  • Linjun Zhang
  • James Y. Zou
  • Carlos Guestrin

While most machine learning models can provide confidence in their predictions, confidence is insufficient to understand a prediction's reliability. For instance, the model may have a low confidence prediction if the input is not well-represented in the training dataset or if the input is inherently ambiguous. In this work, we investigate the relationship between how atypical~(rare) a sample or a class is and the reliability of a model's predictions. We first demonstrate that atypicality is strongly related to miscalibration and accuracy. In particular, we empirically show that predictions for atypical inputs or atypical classes are more overconfident and have lower accuracy. Using these insights, we show incorporating atypicality improves uncertainty quantification and model performance for discriminative neural networks and large language models. In a case study, we show that using atypicality improves the performance of a skin lesion classifier across different skin tone groups without having access to the group attributes. Overall, we propose that models should use not only confidence but also atypicality to improve uncertainty quantification and performance. Our results demonstrate that simple post-hoc atypicality estimators can provide significant value.

PDF Details

ICML Conference 2023 Conference Paper

Discover and Cure: Concept-aware Mitigation of Spurious Correlation

  • Shirley Wu
  • Mert Yüksekgönül
  • Linjun Zhang
  • James Y. Zou

Deep neural networks often rely on spurious correlations to make predictions, which hinders generalization beyond training environments. For instance, models that associate cats with bed backgrounds can fail to predict the existence of cats in other environments without beds. Mitigating spurious correlations is crucial in building trustworthy models. However, the existing works lack transparency to offer insights into the mitigation process. In this work, we propose an interpretable framework, Discover and Cure (DISC), to tackle the issue. With human-interpretable concepts, DISC iteratively 1) discovers unstable concepts across different environments as spurious attributes, then 2) intervenes on the training data using the discovered concepts to reduce spurious correlation. Across systematic experiments, DISC provides superior generalization ability and interpretability than the existing approaches. Specifically, it outperforms the state-of-the-art methods on an object recognition task and a skin-lesion classification task by 7. 5% and 9. 6%, respectively. Additionally, we offer theoretical analysis and guarantees to understand the benefits of models trained by DISC. Code and data are available at https: //github. com/Wuyxin/DISC.

Details

ICLR Conference 2023 Conference Paper

FaiREE: fair classification with finite-sample and distribution-free guarantee

  • Puheng Li
  • James Y. Zou
  • Linjun Zhang

Algorithmic fairness plays an increasingly critical role in machine learning research. Several group fairness notions and algorithms have been proposed. However, the fairness guarantee of existing fair classification methods mainly depend on specific data distributional assumptions, often requiring large sample sizes, and fairness could be violated when there is a modest number of samples, which is often the case in practice. In this paper, we propose FaiREE, a fair classification algorithm which can satisfy group fairness constraints with finite-sample and distribution-free theoretical guarantees. FaiREE can be adapted to satisfying various group fairness notions (e.g., Equality of Opportunity, Equalized Odds, Demographic Parity, etc.) and achieve the optimal accuracy. These theoretical guarantees are further supported by experiments on both synthetic and real data. FaiREE is shown to have favorable performance over state-of-the-art algorithms.

Details

ICLR Conference 2023 Conference Paper

FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data

  • Zhun Deng
  • Jiayao Zhang 0001
  • Linjun Zhang
  • Ting Ye
  • Yates Coley
  • Weijie J. Su
  • James Y. Zou

Algorithmic fairness plays an important role in machine learning and imposing fairness constraints during learning is a common approach. However, many datasets are imbalanced in certain label classes (e.g. "healthy") and sensitive subgroups (e.g. "older patients"). Empirically, this imbalance leads to a lack of generalizability not only of classification but also of fairness properties, especially in over-parameterized models. For example, fairness-aware training may ensure equalized odds (EO) on the training data, but EO is far from being satisfied on new users. In this paper, we propose a theoretically-principled, yet {\bf F}lexible approach that is {\bf I}mbalance-{\bf F}airness-{\bf A}ware ({\bf FIFA}). Specifically, FIFA encourages both classification and fairness generalization and can be flexibly combined with many existing fair learning methods with logits-based losses. While our main focus is on EO, FIFA can be directly applied to achieve equalized opportunity (EqOpt); and under certain conditions, it can also be applied to other fairness notions. We demonstrate the power of FIFA by combining it with a popular fair classification algorithm, and the resulting algorithm achieves significantly better fairness generalization on several real-world datasets.

Details

JMLR Journal 2023 Journal Article

The Power of Contrast for Feature Learning: A Theoretical Analysis

  • Wenlong Ji
  • Zhun Deng
  • Ryumei Nakada
  • James Zou
  • Linjun Zhang

Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart. Despite its empirical success, theoretical understanding of the superiority of contrastive learning is still limited. In this paper, under linear representation settings, (i) we provably show that contrastive learning outperforms the standard autoencoders and generative adversarial networks, two classical generative unsupervised learning methods, for both feature recovery and in-domain downstream tasks; (ii) we also illustrate the impact of labeled data in supervised contrastive learning. This provides theoretical support for recent findings that contrastive learning with labels improves the performance of learned representations in the in-domain downstream task, but it can harm the performance in transfer learning. We verify our theory with numerical experiments. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details

NeurIPS Conference 2022 Conference Paper

C-Mixup: Improving Generalization in Regression

  • Huaxiu Yao
  • Yiping Wang
  • Linjun Zhang
  • James Y. Zou
  • Chelsea Finn

Improving the generalization of deep networks is an important open challenge, particularly in domains without plentiful data. The mixup algorithm improves generalization by linearly interpolating a pair of examples and their corresponding labels. These interpolated examples augment the original training set. Mixup has shown promising results in various classification tasks, but systematic analysis of mixup in regression remains underexplored. Using mixup directly on regression labels can result in arbitrarily incorrect labels. In this paper, we propose a simple yet powerful algorithm, C-Mixup, to improve generalization on regression tasks. In contrast with vanilla mixup, which picks training examples for mixing with uniform probability, C-Mixup adjusts the sampling probability based on the similarity of the labels. Our theoretical analysis confirms that C-Mixup with label similarity obtains a smaller mean square error in supervised regression and meta-regression than vanilla mixup and using feature similarity. Another benefit of C-Mixup is that it can improve out-of-distribution robustness, where the test distribution is different from the training distribution. By selectively interpolating examples with similar labels, it mitigates the effects of domain-associated information and yields domain-invariant representations. We evaluate C-Mixup on eleven datasets, ranging from tabular to video data. Compared to the best prior approach, C-Mixup achieves 6. 56%, 4. 76%, 5. 82% improvements in in-distribution generalization, task generalization, and out-of-distribution robustness, respectively. Code is released at https: //github. com/huaxiuyao/C-Mixup.

PDF Details

ICML Conference 2022 Conference Paper

Improving Out-of-Distribution Robustness via Selective Augmentation

  • Huaxiu Yao
  • Yu Wang 0170
  • Sai Li 0005
  • Linjun Zhang
  • Weixin Liang
  • James Y. Zou
  • Chelsea Finn

Machine learning algorithms typically assume that training and test examples are drawn from the same distribution. However, distribution shift is a common problem in real-world applications and can cause models to perform dramatically worse at test time. In this paper, we specifically consider the problems of subpopulation shifts (e. g. , imbalanced data) and domain shifts. While prior works often seek to explicitly regularize internal representations or predictors of the model to be domain invariant, we instead aim to learn invariant predictors without restricting the model’s internal representations or predictors. This leads to a simple mixup-based technique which learns invariant predictors via selective augmentation called LISA. LISA selectively interpolates samples either with the same labels but different domains or with the same domain but different labels. Empirically, we study the effectiveness of LISA on nine benchmarks ranging from subpopulation shifts to domain shifts, and we find that LISA consistently outperforms other state-of-the-art methods and leads to more invariant predictors. We further analyze a linear setting and theoretically show how LISA leads to a smaller worst-group error.

Details

ICLR Conference 2022 Conference Paper

Meta-Learning with Fewer Tasks through Task Interpolation

  • Huaxiu Yao
  • Linjun Zhang
  • Chelsea Finn

Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge. However, the bottleneck of current meta-learning algorithms is the requirement of a large number of meta-training tasks, which may not be accessible in real-world scenarios. To address the challenge that available tasks may not densely sample the space of tasks, we propose to augment the task set through interpolation. By meta-learning with task interpolation (MLTI), our approach effectively generates additional tasks by randomly sampling a pair of tasks and interpolating the corresponding features and labels. Under both gradient-based and metric-based meta-learning settings, our theoretical analysis shows MLTI corresponds to a data-adaptive meta-regularization and further improves the generalization. Empirically, in our experiments on eight datasets from diverse domains including image recognition, pose prediction, molecule property prediction, and medical image classification, we find that the proposed general MLTI framework is compatible with representative meta-learning algorithms and consistently outperforms other state-of-the-art strategies.

Details

YNIMG Journal 2022 Journal Article

The influence of visual deprivation on the development of the thalamocortical network: Evidence from congenitally blind children and adults

  • Junfeng Lin
  • Linjun Zhang
  • Runhua Guo
  • Saiyi Jiao
  • Xiaomeng Song
  • Suting Feng
  • Ke Wang
  • Mingyang Li

The thalamus is heavily involved in relaying sensory signals to the cerebral cortex. A relevant issue is how the deprivation of congenital visual sensory information modulates the development of the thalamocortical network. The answer is unclear because previous studies on this topic did not investigate network development, structure-function combinations, and cognition-related behaviors in the same study. To overcome these limitations, we recruited 30 congenitally blind subjects (8 children, 22 adults) and 31 sighted subjects (10 children, 21 adults), and conducted multiple analyses [i.e., gray matter volume (GMV) analysis using the voxel-based morphometry (VBM) method, resting-state functional connectivity (FC), and brain-behavior correlation]. We found that congenital blindness elicited significant changes in the development of GMV in visual and somatosensory thalamic regions. Blindness also resulted in significant changes in the development of FC between somatosensory thalamic regions and visual cortical regions as well as advanced information processing regions. Moreover, the somatosensory thalamic regions and their FCs with visual cortical regions were reorganized to process high-level tactile language information in blind individuals. These findings provide a refined understanding of the neuroanatomical and functional plasticity of the thalamocortical network.

Details DOI

ICML Conference 2022 Conference Paper

When and How Mixup Improves Calibration

  • Linjun Zhang
  • Zhun Deng
  • Kenji Kawaguchi
  • James Y. Zou

In many machine learning applications, it is important for the model to provide confidence scores that accurately capture its prediction uncertainty. Although modern learning methods have achieved great success in predictive accuracy, generating calibrated confidence scores remains a major challenge. Mixup, a popular yet simple data augmentation technique based on taking convex combinations of pairs of training examples, has been empirically found to significantly improve confidence calibration across diverse applications. However, when and how Mixup helps calibration is still a mystery. In this paper, we theoretically prove that Mixup improves calibration in high-dimensional settings by investigating natural statistical models. Interestingly, the calibration benefit of Mixup increases as the model capacity increases. We support our theories with experiments on common architectures and datasets. In addition, we study how Mixup improves calibration in semi-supervised learning. While incorporating unlabeled data can sometimes make the model less calibrated, adding Mixup training mitigates this issue and provably improves calibration. Our analysis provides new insights and a framework to understand Mixup and calibration.

Details

NeurIPS Conference 2021 Conference Paper

A Central Limit Theorem for Differentially Private Query Answering

  • Jinshuo Dong
  • Weijie Su
  • Linjun Zhang

Perhaps the single most important use case for differential privacy is to privately answer numerical queries, which is usually achieved by adding noise to the answer vector. The central question is, therefore, to understand which noise distribution optimizes the privacy-accuracy trade-off, especially when the dimension of the answer vector is high. Accordingly, an extensive literature has been dedicated to the question and the upper and lower bounds have been successfully matched up to constant factors (Bun et al. ,2018; Steinke & Ullman, 2017). In this paper, we take a novel approach to address this important optimality question. We first demonstrate an intriguing central limit theorem phenomenon in the high-dimensional regime. More precisely, we prove that a mechanism is approximately Gaussian Differentially Private (Dong et al. , 2021) if the added noise satisfies certain conditions. In particular, densities proportional to $\mathrm{e}^{-\|x\|_p^\alpha}$, where $\|x\|_p$ is the standard $\ell_p$-norm, satisfies the conditions. Taking this perspective, we make use of the Cramer--Rao inequality and show an "uncertainty principle"-style result: the product of privacy parameter and the $\ell_2$-loss of the mechanism is lower bounded by the dimension. Furthermore, the Gaussian mechanism achieves the constant-sharp optimal privacy-accuracy trade-off among all such noises. Our findings are corroborated by numerical experiments.

PDF Details

NeurIPS Conference 2021 Conference Paper

Adversarial Training Helps Transfer Learning via Better Representations

  • Zhun Deng
  • Linjun Zhang
  • Kailas Vodrahalli
  • Kenji Kawaguchi
  • James Y. Zou

Transfer learning aims to leverage models pre-trained on source data to efficiently adapt to target setting, where only limited data are available for model fine-tuning. Recent works empirically demonstrate that adversarial training in the source data can improve the ability of models to transfer to new domains. However, why this happens is not known. In this paper, we provide a theoretical model to rigorously analyze how adversarial training helps transfer learning. We show that adversarial training in the source data generates provably better representations, so fine-tuning on top of this representation leads to a more accurate predictor of the target data. We further demonstrate both theoretically and empirically that semi-supervised learning in the source data can also improve transfer learning by similarly improving the representation. Moreover, performing adversarial training on top of semi-supervised learning can further improve transferability, suggesting that the two approaches have complementary benefits on representations. We support our theories with experiments on popular data sets and deep learning architectures.

PDF Details

ICLR Conference 2021 Conference Paper

How Does Mixup Help With Robustness and Generalization?

  • Linjun Zhang
  • Zhun Deng
  • Kenji Kawaguchi
  • Amirata Ghorbani
  • James Y. Zou

Mixup is a popular data augmentation technique based on on convex combinations of pairs of examples and their labels. This simple technique has shown to substantially improve both the model's robustness as well as the generalization of the trained model. However, it is not well-understood why such improvement occurs. In this paper, we provide theoretical analysis to demonstrate how using Mixup in training helps model robustness and generalization. For robustness, we show that minimizing the Mixup loss corresponds to approximately minimizing an upper bound of the adversarial loss. This explains why models obtained by Mixup training exhibits robustness to several kinds of adversarial attacks such as Fast Gradient Sign Method (FGSM). For generalization, we prove that Mixup augmentation corresponds to a specific type of data-adaptive regularization which reduces overfitting. Our analysis provides new insights and a framework to understand Mixup.

Details

ICML Conference 2021 Conference Paper

Improving Generalization in Meta-learning via Task Augmentation

  • Huaxiu Yao
  • Long-Kai Huang
  • Linjun Zhang
  • Ying Wei 0001
  • Li Tian
  • James Y. Zou
  • Junzhou Huang
  • Zhenhui Li

Meta-learning has proven to be a powerful paradigm for transferring the knowledge from previous tasks to facilitate the learning of a novel task. Current dominant algorithms train a well-generalized model initialization which is adapted to each task via the support set. The crux lies in optimizing the generalization capability of the initialization, which is measured by the performance of the adapted model on the query set of each task. Unfortunately, this generalization measure, evidenced by empirical results, pushes the initialization to overfit the meta-training tasks, which significantly impairs the generalization and adaptation to novel tasks. To address this issue, we actively augment a meta-training task with “more data” when evaluating the generalization. Concretely, we propose two task augmentation methods, including MetaMix and Channel Shuffle. MetaMix linearly combines features and labels of samples from both the support and query sets. For each class of samples, Channel Shuffle randomly replaces a subset of their channels with the corresponding ones from a different class. Theoretical studies show how task augmentation improves the generalization of meta-learning. Moreover, both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets and are compatible with existing meta-learning algorithms.

Details

ICML Conference 2020 Conference Paper

Interpreting Robust Optimization via Adversarial Influence Functions

  • Zhun Deng
  • Cynthia Dwork
  • Jialiang Wang 0001
  • Linjun Zhang

Robust optimization has been widely used in nowadays data science, especially in adversarial training. However, little research has been done to quantify how robust optimization changes the optimizers and the prediction losses comparing to standard training. In this paper, inspired by the influence function in robust statistics, we introduce the Adversarial Influence Function (AIF) as a tool to investigate the solution produced by robust optimization. The proposed AIF enjoys a closed-form and can be calculated efficiently. To illustrate the usage of AIF, we apply it to study model sensitivity — a quantity defined to capture the change of prediction losses on the natural data after implementing robust optimization. We use AIF to analyze how model complexity and randomized smoothing affect the model sensitivity with respect to specific models. We further derive AIF for kernel regressions, with a particular application to neural tangent kernels, and experimentally demonstrate the effectiveness of the proposed AIF. Lastly, the theories of AIF will be extended to distributional robust optimization.

Details

YNIMG Journal 2008 Journal Article

Cortical competition during language discrimination

  • Jingjing Zhao
  • Hua Shu
  • Linjun Zhang
  • Xiaoyi Wang
  • Qiyong Gong
  • Ping Li

How do human listeners differentiate one language from another? In this study we examine the contributions of acoustic and linguistic cues to successful language discrimination. In particular, we report findings that reveal patterns of cortical competition as a function of the competition between prosodic, phonological, and lexical semantic information during language discrimination. We manipulated four types of stimuli in the listening environment: synthesized speech with rhythmic information, synthesized speech with rhythmic plus intonational information, natural speech from Japanese and Italian, and natural speech from Chinese and English. Our study shows that, depending on the amount and the kind of cues available, the listener recruits different areas of the brain for the same language task. Furthermore, brain activations do not monotonically multiply as a function of the complexity of the cues available, but are the outcomes of cue competition as a function of cue validity for the discrimination task. These findings show how acoustic and linguistic cues lead to cortical competition and how cortical activities adapt to the task demand for successful information processing.

Details DOI
v2026.09.13