Author name cluster

Yixing Xu

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.

15 papers

2 author rows

AAAI Conference 2026 Conference Paper

Learnable Permutation for Structured Sparsity on Transformer Models

Zekai Li
Ji Liu
Guanchen Li
Yixing Xu
Ziqiong Liu
Xuanwu Yin
Dong Li
Emad Barsoum

Structured sparsity has emerged as a popular model pruning technique, widely adopted in various architectures, including CNNs, Transformer models, and especially large language models (LLMs) in recent years. A promising direction to further improve post-pruning performance is weight permutation, which reorders model weights into patterns more amenable to pruning. However, the exponential growth of the permutation search space with the scale of Transformer architectures forces most methods to rely on greedy or heuristic algorithms, limiting the effectiveness of reordering. In this work, we propose a novel end-to-end learnable permutation framework. Our method introduces a learnable permutation cost matrix to quantify the cost of swapping any two input channels of a given weight matrix, a differentiable bipartite matching solver to obtain the optimal binary permutation matrix given a cost matrix, and a sparsity optimization loss function to directly optimize the permutation operator. We extensively validate our approach on vision and language Transformers, demonstrating that our method achieves state-of-the-art permutation results for structured sparsity.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning

Huanxuan Liao
Yixing Xu
Shizhu He
Guanchen Li
Xuanwu Yin
Dong Li
Emad Barsoum
Jun Zhao

Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention computation scales quadratically. Existing approaches address this issue by compressing the KV cache along the temporal axis through strategies such as token eviction or merging to reduce memory and computational overhead. However, these methods often neglect fine-grained importance variations across feature dimensions (i.e., the channel axis), thereby limiting their ability to effectively balance efficiency and model accuracy. In reality, we observe that channel saliency varies dramatically across both queries and positions: certain feature channels carry near-zero information for a given query, while others spike in relevance. To address this oversight, we propose SPARK, a training-free plug-and-play method that applies unstructured sparsity by pruning KV at the channel level, while dynamically restoring the pruned entries during attention score computation. Notably, our approach is orthogonal to existing KV compression and quantization techniques, making it compatible for integration with them to achieve further acceleration. By reducing channel-level redundancy, SPARK enables processing of longer sequences within the same memory budget. For sequences of equal length, SPARK not only preserves or improves model accuracy but also reduces KV cache storage by over 30% compared to eviction-based methods. Furthermore, even in an aggressive pruning ratio of 80%, SPARK maintains performance with less degradation than 5% compared to the based eviction method, demonstrating robustness and effectiveness. Our code will be available at \url{https://github.com/AMD-AIG-AIMA/AMD-Spark}.

PDF Details DOI

ICML Conference 2025 Conference Paper

Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding

Jinze Li 0001
Yixing Xu
Haiduo Huang
Xuanwu Yin
Dong Li 0025
Edith C. H. Ngai
Emad Barsoum

Speculative decoding (SPD) aims to accelerate the auto-regressive token generation process of a target Large Language Model (LLM). Some approaches employ a draft model with multiple heads to predict a sequence of future tokens, where each head handles a token in the sequence. The target LLM verifies the predicted sequence and accepts aligned tokens, enabling efficient multi-token generation. However, existing methods assume that all tokens within a sequence are equally important, employing identical head structures and relying on a single-generation paradigm, either serial or parallel. To this end, we theoretically demonstrate that initial tokens in the draft sequence are more important than later ones. Building on this insight, we propose Gumiho, a hybrid model combining serial and parallel heads. Specifically, given the critical importance of early tokens, we employ a sophisticated Transformer architecture for the early draft heads in a serial configuration to improve accuracy. For later tokens, we utilize multiple lightweight MLP heads operating in parallel to enhance efficiency. By allocating more advanced model structures and longer running times to the early heads, Gumiho achieves improved overall performance. The experimental results demonstrate that our method outperforms existing approaches, fully validating its effectiveness. Our code is available at https: //github. com/AMD-AIG-AIMA/Gumiho.

Details

NeurIPS Conference 2025 Conference Paper

Týr-the-Pruner: Structural Pruning LLMs via Global Sparsity Distribution Optimization

Guanchen Li
Yixing Xu
Zeping Li
Ji Liu
Xuanwu Yin
Dong Li
Emad Barsoum

Structural pruning enhances hardware-agnostic inference efficiency for large language models (LLMs) yet often fails to maintain comparable performance. Local pruning performs efficient layer-by-layer compression but ignores global topology. Although global pruning aims to identify an optimal sparse model, intuitive methods typically adopt a two-stage paradigm that first evaluates substructure saliency and then applies global pruning, which ignores inter-structure dependencies and fails to achieve end-to-end optimization. To address these limitations, we propose Týr-the-Pruner, an efficient end-to-end search-based global structural pruning framework. This framework constructs a supernet by repeatedly applying local pruning across a range of sparsity ratios to each layer in an LLM, with the core goal of determining the optimal sparsity distribution under a target overall sparsity ratio. Concretely, we introduce an effective local pruning and an expectation error accumulation approach to improve supernet construction. Furthermore, we employ an iterative prune-and-search strategy with coarse-to-fine sparsity granularity to ensure efficient search convergence. Experimental results show that Týr-the-Pruner achieves state-of-the-art structural pruning, retaining 97% of the dense model's performance while removing a challenging 50% of Llama-3. 1-70B's parameters.

PDF Details

ICML Conference 2024 Conference Paper

Enhancing Vision Transformer: Amplifying Non-Linearity in Feedforward Network Module

Yixing Xu
Chao Li
Dong Li 0025
Xiao Sheng
Fan Jiang
Lu Tian
Ashish Sirasao
Emad Barsoum

Transformer models have been gaining substantial interest in the field of computer vision tasks nowadays. Although a vision transformer contains two important components which are self-attention module and feedforward network (FFN) module, the majority of research tends to concentrate on modifying the former while leaving the latter in its original form. In this paper, we focus on improving the FFN module within the vision transformer. Through theoretical analysis, we demonstrate that the effect of the FFN module primarily lies in providing non-linearity, whose degree corresponds to the hidden dimensions. Thus, the computational cost of the FFN module can be reduced by enhancing the degree of non-linearity in the nonlinear function. Leveraging this insight, we propose an improved FFN (IFFN) module for vision transformers which involves the usage of the arbitrary GeLU (AGeLU) function and integrating multiple instances of it to augment non-linearity so that the number of hidden dimensions can be effectively reduced. Besides, a spatial enhancement part is involved to further enrich the non-linearity in the proposed IFFN module. Experimental results show that we can apply our method to a wide range of state-of-the-art vision transformer models irrespective of how they modify their self-attention part and the overall architecture, and reduce FLOPs and parameters without compromising classification accuracy on the ImageNet dataset.

Details

NeurIPS Conference 2024 Conference Paper

QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion

Yixing Xu
Chao Li
Dong Li
Xiao Sheng
Fan Jiang
Lu Tian
Emad Barsoum

Vision transformer model (ViT) is widely used and performs well in vision tasks due to its ability to capture long-range dependencies. However, the time complexity and memory consumption increase quadratically with the number of input patches which limits the usage of ViT in real-world applications. Previous methods have employed linear attention to mitigate the complexity of the original self-attention mechanism at the expense of effectiveness. In this paper, we propose QT-ViT models that improve the previous linear self-attention using quadratic Taylor expansion. Specifically, we substitute the softmax-based attention with second-order Taylor expansion, and then accelerate the quadratic expansion by reducing the time complexity with a fast approximation algorithm. The proposed method capitalizes on the property of quadratic expansion to achieve superior performance while employing linear approximation for fast inference. Compared to previous studies of linear attention, our approach does not necessitate knowledge distillation or high-order attention residuals to facilitate the training process. Extensive experiments demonstrate the efficiency and effectiveness of the proposed QT-ViTs, showcasing the state-of-the-art results. Particularly, the proposed QT-ViTs consistently surpass the previous SOTA EfficientViTs under different model sizes, and achieve a new Pareto-front in terms of accuracy and speed.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

BiMLP: Compact Binary Architectures for Vision Multi-Layer Perceptrons

Yixing Xu
Xinghao Chen
Yunhe Wang

This paper studies the problem of designing compact binary architectures for vision multi-layer perceptrons (MLPs). We provide extensive analysis on the difficulty of binarizing vision MLPs and find that previous binarization methods perform poorly due to limited capacity of binary MLPs. In contrast with the traditional CNNs that utilizing convolutional operations with large kernel size, fully-connected (FC) layers in MLPs can be treated as convolutional layers with kernel size $1\times1$. Thus, the representation ability of the FC layers will be limited when being binarized, and places restrictions on the capability of spatial mixing and channel mixing on the intermediate features. To this end, we propose to improve the performance of binary MLP (BiMLP) model by enriching the representation ability of binary FC layers. We design a novel binary block that contains multiple branches to merge a series of outputs from the same stage, and also a universal shortcut connection that encourages the information flow from the previous stage. The downsampling layers are also carefully designed to reduce the computational complexity while maintaining the classification performance. Experimental results on benchmark dataset ImageNet-1k demonstrate the effectiveness of the proposed BiMLP models, which achieve state-of-the-art accuracy compared to prior binary CNNs. The MindSpore code is available at \url{https: //gitee. com/mindspore/models/tree/master/research/cv/BiMLP}.

PDF Details

ICML Conference 2022 Conference Paper

Federated Learning with Positive and Unlabeled Data

Xinyang Lin
Hanting Chen
Yixing Xu
Chao Xu 0006
Xiaolin Gui
Yiping Deng
Yunhe Wang 0001

We study the problem of learning from positive and unlabeled (PU) data in the federated setting, where each client only labels a little part of their dataset due to the limitation of resources and time. Different from the settings in traditional PU learning where the negative class consists of a single class, the negative samples which cannot be identified by a client in the federated setting may come from multiple classes which are unknown to the client. Therefore, existing PU learning methods can be hardly applied in this situation. To address this problem, we propose a novel framework, namely Federated learning with Positive and Unlabeled data (FedPU), to minimize the expected risk of multiple negative classes by leveraging the labeled data in other clients. We theoretically analyze the generalization bound of the proposed FedPU. Empirical experiments show that the FedPU can achieve much better performance than conventional supervised and semi-supervised federated learning methods.

Details

NeurIPS Conference 2021 Conference Paper

Learning Frequency Domain Approximation for Binary Neural Networks

Yixing Xu
Kai Han
Chang Xu
Yehui Tang
Chunjing Xu
Yunhe Wang

Binary neural networks (BNNs) represent original full-precision weights and activations into 1-bit with sign function. Since the gradient of the conventional sign function is almost zero everywhere which cannot be used for back-propagation, several attempts have been proposed to alleviate the optimization difficulty by using approximate gradient. However, those approximations corrupt the main direction of factual gradient. To this end, we propose to estimate the gradient of sign function in the Fourier frequency domain using the combination of sine functions for training BNNs, namely frequency domain approximation (FDA). The proposed approach does not affect the low-frequency information of the original sign function which occupies most of the overall energy, and high-frequency coefficients will be ignored to avoid the huge computational overhead. In addition, we embed a noise adaptation module into the training phase to compensate the approximation error. The experiments on several benchmark datasets and neural architectures illustrate that the binary network learned using our method achieves the state-of-the-art accuracy. Code will be available at https: //gitee. com/mindspore/models/tree/master/research/cv/FDA-BNN.

PDF Details

AAAI Conference 2020 Conference Paper

Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks

Yehui Tang
Yunhe Wang
Yixing Xu
Boxin Shi
Chao Xu
Chunjing Xu
Chang Xu

Deep neural networks often consist of a great number of trainable parameters for extracting powerful features from given datasets. One one hand, massive trainable parameters signiﬁcantly enhance the performance of these deep networks. One the other hand, they bring the problem of over-ﬁtting. To this end, dropout based methods disable some elements in the output feature maps during the training phase for reducing the co-adaptation of neurons. Although the generalization ability of the resulting models can be enhanced by these approaches, the conventional binary dropout is not the optimal solution. Therefore, we investigate the empirical Rademacher complexity related to intermediate layers of deep neural networks and propose a feature distortion method for addressing the aforementioned problem. In the training period, randomly selected elements in the feature maps will be replaced with speciﬁc values by exploiting the generalization error bound. The superiority of the proposed feature map distortion for producing deep neural network with higher testing performance is analyzed and demonstrated on several benchmark image datasets.

PDF Details

NeurIPS Conference 2020 Conference Paper

Kernel Based Progressive Distillation for Adder Neural Networks

Yixing Xu
Chang Xu
Xinghao Chen
Wei Zhang
Chunjing Xu
Yunhe Wang

Adder Neural Networks (ANNs) which only contain additions bring us a new way of developing deep neural networks with low energy consumption. Unfortunately, there is an accuracy drop when replacing all convolution filters by adder filters. The main reason here is the optimization difficulty of ANNs using $\ell_1$-norm, in which the estimation of gradient in back propagation is inaccurate. In this paper, we present a novel method for further improving the performance of ANNs without increasing the trainable parameters via a progressive kernel based knowledge distillation (PKKD) method. A convolutional neural network (CNN) with the same architecture is simultaneously initialized and trained as a teacher network, features and weights of ANN and CNN will be transformed to a new space to eliminate the accuracy drop. The similarity is conducted in a higher-dimensional space to disentangle the difference of their distributions using a kernel based method. Finally, the desired ANN is learned based on the information from both the ground-truth and teacher, progressively. The effectiveness of the proposed method for learning ANN with higher performance is then well-verified on several benchmarks. For instance, the ANN-50 trained using the proposed PKKD method obtains a 76. 8\% top-1 accuracy on ImageNet dataset, which is 0. 6\% higher than that of the ResNet-50.

PDF Details

NeurIPS Conference 2020 Conference Paper

SCOP: Scientific Control for Reliable Neural Network Pruning

Yehui Tang
Yunhe Wang
Yixing Xu
Dacheng Tao
Chunjing Xu
Chao Xu
Chang Xu

This paper proposes a reliable neural network pruning algorithm by setting up a scientific control. Existing pruning methods have developed various hypotheses to approximate the importance of filters to the network and then execute filter pruning accordingly. To increase the reliability of the results, we prefer to have a more rigorous research design by including a scientific control group as an essential part to minimize the effect of all factors except the association between the filter and expected network output. Acting as a control group, knockoff feature is generated to mimic the feature map produced by the network filter, but they are conditionally independent of the example label given the real feature map. We theoretically suggest that the knockoff condition can be approximately preserved given the information propagation of network layers. Besides the real feature map on an intermediate layer, the corresponding knockoff feature is brought in as another auxiliary input signal for the subsequent layers. Redundant filters can be discovered in the adversarial process of different features. Through experiments, we demonstrate the superiority of the proposed algorithm over state-of-the-art methods. For example, our method can reduce 57. 8% parameters and 60. 2% FLOPs of ResNet-101 with only 0. 01% top-1 accuracy loss on ImageNet.

PDF Details

ICML Conference 2020 Conference Paper

Training Binary Neural Networks through Learning with Noisy Supervision

Kai Han 0002
Yunhe Wang 0001
Yixing Xu
Chunjing Xu
Enhua Wu
Chang Xu 0002

This paper formalizes the binarization operations over neural networks from a learning perspective. In contrast to classical hand crafted rules (\eg hard thresholding) to binarize full-precision neurons, we propose to learn a mapping from full-precision neurons to the target binary ones. Each individual weight entry will not be binarized independently. Instead, they are taken as a whole to accomplish the binarization, just as they work together in generating convolution features. To help the training of the binarization mapping, the full-precision neurons after taking sign operations is regarded as some auxiliary supervision signal, which is noisy but still has valuable guidance. An unbiased estimator is therefore introduced to mitigate the influence of the supervision noise. Experimental results on benchmark datasets indicate that the proposed binarization technique attains consistent improvements over baselines.

Details

NeurIPS Conference 2019 Conference Paper

Positive-Unlabeled Compression on the Cloud

Yixing Xu
Yunhe Wang
Hanting Chen
Kai Han
Chunjing Xu
Dacheng Tao
Chang Xu

Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providing compression and acceleration service of deep learning models on the cloud is therefore of significance and is attractive for end users. However, existing network compression and acceleration approaches usually fine-tuning the svelte model by requesting the entire original training data (e. g. ImageNet), which could be more cumbersome than the network itself and cannot be easily uploaded to the cloud. In this paper, we present a novel positive-unlabeled (PU) setting for addressing this problem. In practice, only a small portion of the original training set is required as positive examples and more useful training examples can be obtained from the massive unlabeled data on the cloud through a PU classifier with an attention based multi-scale feature extractor. We further introduce a robust knowledge distillation (RKD) scheme to deal with the class imbalance problem of these newly augmented training examples. The superiority of the proposed method is verified through experiments conducted on the benchmark models and datasets. We can use only 8% of uniformly selected data from the ImageNet to obtain an efficient model with comparable performance to the baseline ResNet-34.

PDF Details

IJCAI Conference 2017 Conference Paper

Multi-Positive and Unlabeled Learning

Yixing Xu
Chang Xu
Chao Xu
Dacheng Tao

The positive and unlabeled (PU) learning problem focuses on learning a classifier from positive and unlabeled data. Some methods have been developed to solve the PU learning problem. However, they are often limited in practical applications, since only binary classes are involved and cannot easily be adapted to multi-class data. Here we propose a one-step method that directly enables multi-class model to be trained using the given input multi-class data and that predicts the label based on the model decision. Specifically, we construct different convex loss functions for labeled and unlabeled data to learn a discriminant function F. The theoretical analysis on the generalization error bound shows that it is no worse than k√k times of the fully supervised multi-class classification methods when the size of the data in k classes is of the same order. Finally, our experimental results demonstrate the significance and effectiveness of the proposed algorithm in synthetic and real-world datasets.

PDF Details