Author name cluster

Yubin Shi

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.

5 papers

2 author rows

AAAI Conference 2025 Conference Paper

ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization

Weibo Zhao
Yubin Shi
Xinyu Lyu
Wanchen Sui
Shen Li
Yong Li

Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The limited numerical mapping makes the quantized model produce a non-trivial error, bringing out intolerable performance degration. This paper is anchored in the basic idea of model compression objectives, and delves into the layer-wise error distribution of LLMs during post-training quantization. Subsequently, we introduce ASER, an algorithm consisting of (1) Error Reconstruction: low-rank compensation for quantization error with LoRA-style matrices constructed by whitening SVD; (2) Activation Smoothing: outlier extraction to gain smooth activation and better error compensation. ASER is capable of quantizing typical LLMs to low-bit ones, particularly preserving accuracy even in W4A8 per-channel setup. Experimental results show that ASER is competitive among the state-of-the-art quantization algorithms, showing potential to activation quantization, with minor overhead.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Once Read is Enough: Domain-specific Pretraining-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge

Fang Dong
Mengyi Chen
Jixian Zhou
Yubin Shi
Yixuan Chen
Mingzhi Dong
Yujiang Wang
Dongsheng Li

Language models (LMs) only pretrained on a general and massive corpus usually cannot attain satisfying performance on domain-specific downstream tasks, and hence, applying domain-specific pretraining to LMs is a common and indispensable practice. However, domain-specific pretraining can be costly and time-consuming, hindering LMs' deployment in real-world applications. In this work, we consider the incapability to memorize domain-specific knowledge embedded in the general corpus with rare occurrences and long-tail distributions as the leading cause for pretrained LMs' inferior downstream performance. Analysis of Neural Tangent Kernels (NTKs) reveals that those long-tail data are commonly overlooked in the model's gradient updates and, consequently, are not effectively memorized, leading to poor domain-specific downstream performance. Based on the intuition that data with similar semantic meaning are closer in the embedding space, we devise a Cluster-guided Sparse Expert (CSE) layer to actively learn long-tail domain knowledge typically neglected in previous pretrained LMs. During pretraining, a CSE layer efficiently clusters domain knowledge together and assigns long-tail knowledge to designate extra experts. CSE is also a lightweight structure that only needs to be incorporated in several deep layers. With our training strategy, we found that during pretraining, data of long-tail knowledge gradually formulate isolated, outlier clusters in an LM's representation spaces, especially in deeper layers. Our experimental results show that only pretraining CSE-based LMs is enough to achieve superior performance than regularly pretrained-finetuned LMs on various downstream tasks, implying the prospects of domain-specific-pretraining-free language models.

PDF Details DOI

ICLR Conference 2023 Conference Paper

Over-parameterized Model Optimization with Polyak-Łojasiewicz Condition

Yixuan Chen 0003
Yubin Shi
Mingzhi Dong
Xiaochen Yang
Dongsheng Li 0002
Yujiang Wang 0001
Robert P. Dick
Qin Lv

This work pursues the optimization of over-parameterized deep models for superior training efficiency and test performance. We first theoretically emphasize the importance of two properties of over-parameterized models, i.e., the convergence gap and the generalization gap. Subsequent analyses unveil that these two gaps can be upper-bounded by the ratio of the Lipschitz constant and the Polyak-{\L}ojasiewicz (PL) constant, a crucial term abbreviated as the \emph{condition number}. Such discoveries have led to a structured pruning method with a novel pruning criterion. That is, we devise a gating network that dynamically detects and masks out those poorly-behaved nodes of a deep model during the training session. To this end, this gating network is learned via minimizing the \emph{condition number} of the target model, and this process can be implemented as an extra regularization loss term. Experimental studies demonstrate that the proposed method outperforms the baselines in terms of both training efficiency and test performance, exhibiting the potential of generalizing to a variety of deep network architectures and tasks.

Details

NeurIPS Conference 2023 Conference Paper

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

Yubin Shi
Yixuan Chen
Mingzhi Dong
Xiaochen Yang
Dongsheng Li
Yujiang Wang
Robert Dick
Qin Lv

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized models to attain a more efficient and fruitful training strategy. Empirical evidence reveals that when scaling down into network modules, such as heads in self-attention models, we can observe varying learning patterns implicitly associated with each module's trainability. To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue $\lambda_{\max}$. A large $\lambda_{\max}$ indicates that the module learns features with better convergence, while those miniature ones may impact generalization negatively. Inspired by the discovery, we propose a novel training strategy termed Modular Adaptive Training (MAT) to update those modules with their $\lambda_{\max}$ exceeding a dynamic threshold selectively, concentrating the model on learning common features and ignoring those inconsistent ones. Unlike most existing training schemes with a complete BP cycle across all network modules, MAT can significantly save computations by its partially-updating strategy and can further improve performance. Experiments show that MAT nearly halves the computational cost of model training and outperforms the accuracy of baselines.

PDF Details

ICLR Conference 2022 Conference Paper

Disentangled feature representation is essential for data-efficient learning. The feature space of deep models is inherently compositional. Existing $\beta$-VAE-based methods, which only apply disentanglement regularization to the resulting embedding space of deep models, cannot effectively regularize such compositional feature space, resulting in unsatisfactory disentangled results. In this paper, we formulate the compositional disentanglement learning problem from an information-theoretic perspective and propose a recursive disentanglement network (RecurD) that propagates regulatory inductive bias recursively across the compositional feature space during disentangled representation learning. Experimental studies demonstrate that RecurD outperforms $\beta$-VAE and several of its state-of-the-art variants on disentangled representation learning and enables more data-efficient downstream machine learning tasks.