Searcharxiv⌕ Search

arXiv subjects

Linqi Song

Publications and source records attributed to Linqi Song.

At least 91 records · Page 5Linked to original sources
arXiv2024

Truncated Non-Uniform Quantization for Distributed SGD

To address the communication bottleneck challenge in distributed learning, our work introduces a novel two-stage quantization strategy designed to enhance the communication efficiency of distributed Stochastic Gradient Descent (SGD). The proposed method initially employs truncation to mitigate the impact of long-tail noise, followed by a non-uniform quantization of the post-truncation gradients based on their statistical characteristics. We provide a comprehensive convergence analysis of the quantized distributed SGD, establishing theoretical guarantees for its performance. Furthermore, by minimizing the convergence error, we derive optimal closed-form solutions for the truncation threshold and non-uniform quantization levels under given communication constraints. Both theoretical insights and extensive experimental evaluations demonstrate that our proposed algorithm outperforms existing quantization schemes, striking a superior balance between communication efficiency and convergence performance.

cs.LG↗
arXiv2024

Improved Quantization Strategies for Managing Heavy-tailed Gradients in Distributed Learning

Gradient compression has surfaced as a key technique to address the challenge of communication efficiency in distributed learning. In distributed deep learning, however, it is observed that gradient distributions are heavy-tailed, with outliers significantly influencing the design of compression strategies. Existing parameter quantization methods experience performance degradation when this heavy-tailed feature is ignored. In this paper, we introduce a novel compression scheme specifically engineered for heavy-tailed gradients, which effectively combines gradient truncation with quantization. This scheme is adeptly implemented within a communication-limited distributed Stochastic Gradient Descent (SGD) framework. We consider a general family of heavy-tail gradients that follow a power-law distribution, we aim to minimize the error resulting from quantization, thereby determining optimal values for two critical parameters: the truncation threshold and the quantization density. We provide a theoretical analysis on the convergence error bound under both uniform and non-uniform quantization scenarios. Comparative experiments with other benchmarks demonstrate the effectiveness of our proposed method in managing the heavy-tailed gradients in a distributed learning environment.

cs.LG↗
arXiv2023

Layered Randomized Quantization for Communication-Efficient and Privacy-Preserving Distributed Learning

Next-generation wireless networks, such as edge intelligence and wireless distributed learning, face two critical challenges: communication efficiency and privacy protection. In this work, our focus is on addressing these issues in a distributed learning framework. We consider a new approach that simultaneously achieves communication efficiency and privacy protection by exploiting the privacy advantage offered by quantization. Specifically, we use a quantization scheme called \textbf{Gau}ssian \textbf{L}ayered \textbf{R}andomized \textbf{Q}uantization (Gau-LRQ) that compresses the raw model gradients using a layer multishift coupler. By adjusting the parameters of Gau-LRQ, we shape the quantization error to follow the expected Gaussian distribution, thus ensuring client-level differential privacy (CLDP). We demonstrate the effectiveness of our proposed Gau-LRQ in the distributed stochastic gradient descent (SGD) framework and theoretically quantify the trade-offs between communication, privacy, and convergence performance. We further improve the convergence performance by enabling dynamic private budget and quantization bit allocation. We achieve this by using an optimization formula that minimizes convergence error subject to the privacy budget constraint. We evaluate our approach on multiple datasets, including MNIST, CIFAR-10, and CIFAR-100, and show that our proposed method outperforms the baselines in terms of learning performance under various privacy constraints. Moreover, we observe that dynamic privacy allocation yields additional accuracy improvements for the models compared to the fixed scheme.

cs.DC↗
arXiv2023

Fine-grained Conversational Decoding via Isotropic and Proximal Search

General-purpose text decoding approaches are usually adopted for dialogue response generation. Although the quality of the generated responses can be improved with dialogue-specific encoding methods, conversational decoding methods are still under-explored. Inspired by \citet{wu2023learning} that a good dialogue feature space should follow the rules of locality and isotropy, we present a fine-grained conversational decoding method, termed \textit{isotropic and proximal search (IPS)}. Our method is designed to generate the semantic-concentrated response, while still maintaining informativeness and discrimination against the context. Experiments show that our approach outperforms existing decoding strategies in the dialogue field across both automatic and human evaluation metrics. More in-depth analyses further confirm the effectiveness of our approach.

cs.CL↗
arXiv2023

Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts

Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content. To overcome these challenges, we propose a two-step framework, Reconstruct before Summarize (RbS), for effective and efficient meeting summarization. RbS first leverages a self-supervised paradigm to annotate essential contents by reconstructing the meeting transcripts. Secondly, we propose a relative positional bucketing (RPB) algorithm to equip (conventional) summarization models to generate the summary. Despite the additional reconstruction process, our proposed RPB significantly compressed the input, leading to faster processing and reduced memory consumption compared to traditional summarization methods. We validate the effectiveness and efficiency of our method through extensive evaluations and analysis. On two meeting summarization datasets, AMI and ICSI, our approach outperforms previous state-of-the-art approaches without relying on large-scale pre-training or expert-grade annotating tools.

cs.CL↗
arXiv2023

A Scalable Test Problem Generator for Sequential Transfer Optimization

Sequential transfer optimization (STO), which aims to improve the optimization performance on a task of interest by exploiting the knowledge captured from several previously-solved optimization tasks stored in a database, has been gaining increasing research attention over the years. However, despite the remarkable advances in algorithm design, the development of a systematic benchmark suite for comprehensive comparisons of STO algorithms received far less attention. Existing test problems are either simply generated by assembling other benchmark functions or extended from specific practical problems with limited scalability. The relationships between the optimal solutions of the source and target tasks in these problems are also often manually configured, limiting their ability to model different similarity relationships presented in real-world problems. Consequently, the good performance achieved by an algorithm on these problems might be biased and hard to be generalized to other problems. In light of the above, in this study, we first introduce four concepts for characterizing STO problems and present an important problem feature, namely similarity distribution, which quantitatively delineates the relationship between the optima of the source and target tasks. Then, we present the general design guidelines of STO problems and a particular STO problem generator with good scalability. Specifically, the similarity distribution of a problem can be easily customized, enabling a continuous spectrum of representation of the diverse similarity relationships of real-world problems. Lastly, a benchmark suite with 12 STO problems featured by a variety of customized similarity relationships is developed using the proposed generator. The source code of the problem generator is available at https://github.com/XmingHsueh/STOP-G.

cs.NE↗
arXiv2023

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

The recently released GPT-4 Code Interpreter has demonstrated remarkable proficiency in solving challenging math problems, primarily attributed to its ability to seamlessly reason with natural language, generate code, execute code, and continue reasoning based on the execution output. In this paper, we present a method to fine-tune open-source language models, enabling them to use code for modeling and deriving math equations and, consequently, enhancing their mathematical reasoning abilities. We propose a method of generating novel and high-quality datasets with math problems and their code-based solutions, referred to as MathCodeInstruct. Each solution interleaves natural language, code, and execution results. We also introduce a customized supervised fine-tuning and inference approach. This approach yields the MathCoder models, a family of models capable of generating code-based solutions for solving challenging math problems. Impressively, the MathCoder models achieve state-of-the-art scores among open-source LLMs on the MATH (45.2%) and GSM8K (83.9%) datasets, substantially outperforming other open-source alternatives. Notably, the MathCoder model not only surpasses ChatGPT-3.5 and PaLM-2 on GSM8K and MATH but also outperforms GPT-4 on the competition-level MATH dataset. The dataset and models will be released at https://github.com/mathllm/MathCoder.

cs.CL↗
arXiv2023

Adaptive Top-K in SGD for Communication-Efficient Distributed Learning

Distributed stochastic gradient descent (SGD) with gradient compression has become a popular communication-efficient solution for accelerating distributed learning. One commonly used method for gradient compression is Top-K sparsification, which sparsifies the gradients by a fixed degree during model training. However, there has been a lack of an adaptive approach to adjust the sparsification degree to maximize the potential of the model's performance or training speed. This paper proposes a novel adaptive Top-K in SGD framework that enables an adaptive degree of sparsification for each gradient descent step to optimize the convergence performance by balancing the trade-off between communication cost and convergence error. Firstly, an upper bound of convergence error is derived for the adaptive sparsification scheme and the loss function. Secondly, an algorithm is designed to minimize the convergence error under the communication cost constraints. Finally, numerical results on the MNIST and CIFAR-10 datasets demonstrate that the proposed adaptive Top-K algorithm in SGD achieves a significantly better convergence rate compared to state-of-the-art methods, even after considering error compensation.

cs.LG↗
arXiv2023

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

Recent progress in large language models (LLMs) like GPT-4 and PaLM-2 has brought significant advancements in addressing math reasoning problems. In particular, OpenAI's latest version of GPT-4, known as GPT-4 Code Interpreter, shows remarkable performance on challenging math datasets. In this paper, we explore the effect of code on enhancing LLMs' reasoning capability by introducing different constraints on the \textit{Code Usage Frequency} of GPT-4 Code Interpreter. We found that its success can be largely attributed to its powerful skills in generating and executing code, evaluating the output of code execution, and rectifying its solution when receiving unreasonable outputs. Based on this insight, we propose a novel and effective prompting method, explicit \uline{c}ode-based \uline{s}elf-\uline{v}erification~(CSV), to further boost the mathematical reasoning potential of GPT-4 Code Interpreter. This method employs a zero-shot prompt on GPT-4 Code Interpreter to encourage it to use code to self-verify its answers. In instances where the verification state registers as ``False'', the model shall automatically amend its solution, analogous to our approach of rectifying errors during a mathematics examination. Furthermore, we recognize that the states of the verification result indicate the confidence of a solution, which can improve the effectiveness of majority voting. With GPT-4 Code Interpreter and CSV, we achieve an impressive zero-shot accuracy on MATH dataset \textbf{(53.9\% $\to$ 84.3\%)}.

cs.CL↗
arXiv2023

VCSUM: A Versatile Chinese Meeting Summarization Dataset

Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data. To this end, we introduce a versatile Chinese meeting summarization dataset, dubbed VCSum, consisting of 239 real-life meetings, with a total duration of over 230 hours. We claim our dataset is versatile because we provide the annotations of topic segmentation, headlines, segmentation summaries, overall meeting summaries, and salient sentences for each meeting transcript. As such, the dataset can adapt to various summarization tasks or methods, including segmentation-based summarization, multi-granularity summarization and retrieval-then-generate summarization. Our analysis confirms the effectiveness and robustness of VCSum. We also provide a set of benchmark models regarding different downstream summarization tasks on VCSum to facilitate further research. The dataset and code will be released at https://github.com/hahahawu/VCSum.

cs.CL↗
arXiv2023

PerFedRec++: Enhancing Personalized Federated Recommendation with Self-Supervised Pre-Training

Federated recommendation systems employ federated learning techniques to safeguard user privacy by transmitting model parameters instead of raw user data between user devices and the central server. Nevertheless, the current federated recommender system faces challenges such as heterogeneity and personalization, model performance degradation, and communication bottleneck. Previous studies have attempted to address these issues, but none have been able to solve them simultaneously. In this paper, we propose a novel framework, named PerFedRec++, to enhance the personalized federated recommendation with self-supervised pre-training. Specifically, we utilize the privacy-preserving mechanism of federated recommender systems to generate two augmented graph views, which are used as contrastive tasks in self-supervised graph learning to pre-train the model. Pre-training enhances the performance of federated models by improving the uniformity of representation learning. Also, by providing a better initial state for federated training, pre-training makes the overall training converge faster, thus alleviating the heavy communication burden. We then construct a collaborative graph to learn the client representation through a federated graph neural network. Based on these learned representations, we cluster users into different user groups and learn personalized models for each cluster. Each user learns a personalized model by combining the global federated model, the cluster-level federated model, and its own fine-tuned local model. Experiments on three real-world datasets show that our proposed method achieves superior performance over existing methods.

cs.IR↗
arXiv2023

Byzantine-robust Federated Learning through Collaborative Malicious Gradient Filtering

Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either makes use of auxiliary data at parameter server to verify the received gradients (e.g., by computing validation error rate) or leverages statistic-based methods (e.g. median and Krum) to identify and remove malicious gradients from Byzantine clients. In this paper, we remark that auxiliary data may not always be available in practice and focus on the statistic-based approach. However, recent work on model poisoning attacks has shown that well-crafted attacks can circumvent most of median- and distance-based statistical defense methods, making malicious gradients indistinguishable from honest ones. To tackle this challenge, we show that the element-wise sign of gradient vector can provide valuable insight in detecting model poisoning attacks. Based on our theoretical analysis of the \textit{Little is Enough} attack, we propose a novel approach called \textit{SignGuard} to enable Byzantine-robust federated learning through collaborative malicious gradient filtering. More precisely, the received gradients are first processed to generate relevant magnitude, sign, and similarity statistics, which are then collaboratively utilized by multiple filters to eliminate malicious gradients before final aggregation. Finally, extensive experiments of image and text classification tasks are conducted under recently proposed attacks and defense strategies. The numerical results demonstrate the effectiveness and superiority of our proposed approach. The code is available at \textit{\url{https://github.com/JianXu95/SignGuard}}

cs.LG↗
arXiv2023

Killing Two Birds with One Stone: Quantization Achieves Privacy in Distributed Learning

Communication efficiency and privacy protection are two critical issues in distributed machine learning. Existing methods tackle these two issues separately and may have a high implementation complexity that constrains their application in a resource-limited environment. We propose a comprehensive quantization-based solution that could simultaneously achieve communication efficiency and privacy protection, providing new insights into the correlated nature of communication and privacy. Specifically, we demonstrate the effectiveness of our proposed solutions in the distributed stochastic gradient descent (SGD) framework by adding binomial noise to the uniformly quantized gradients to reach the desired differential privacy level but with a minor sacrifice in communication efficiency. We theoretically capture the new trade-offs between communication, privacy, and learning performance.

cs.LG↗
arXiv2023

Learning Locality and Isotropy in Dialogue Modeling

Existing dialogue modeling methods have achieved promising performance on various dialogue tasks with the aid of Transformer and the large-scale pre-trained language models. However, some recent studies revealed that the context representations produced by these methods suffer the problem of anisotropy. In this paper, we find that the generated representations are also not conversational, losing the conversation structure information during the context modeling stage. To this end, we identify two properties in dialogue modeling, i.e., locality and isotropy, and present a simple method for dialogue representation calibration, namely SimDRC, to build isotropic and conversational feature spaces. Experimental results show that our approach significantly outperforms the current state-of-the-art models on three dialogue tasks across the automatic and human evaluation metrics. More in-depth analyses further confirm the effectiveness of our proposed approach.

cs.CL↗
arXiv2022

Towards Efficient Communications in Federated Learning: A Contemporary Survey

In the traditional distributed machine learning scenario, the user's private data is transmitted between clients and a central server, which results in significant potential privacy risks. In order to balance the issues of data privacy and joint training of models, federated learning (FL) is proposed as a particular distributed machine learning procedure with privacy protection mechanisms, which can achieve multi-party collaborative computing without revealing the original data. However, in practice, FL faces a variety of challenging communication problems. This review seeks to elucidate the relationship between these communication issues by methodically assessing the development of FL communication research from three perspectives: communication efficiency, communication environment, and communication resource allocation. Firstly, we sort out the current challenges existing in the communications of FL. Second, we have collated FL communications-related papers and described the overall development trend of the field based on their logical relationship. Ultimately, we discuss the future directions of research for communications in FL.

cs.DC↗
arXiv2022

Hiding Images in Deep Probabilistic Models

Data hiding with deep neural networks (DNNs) has experienced impressive successes in recent years. A prevailing scheme is to train an autoencoder, consisting of an encoding network to embed (or transform) secret messages in (or into) a carrier, and a decoding network to extract the hidden messages. This scheme may suffer from several limitations regarding practicability, security, and embedding capacity. In this work, we describe a different computational framework to hide images in deep probabilistic models. Specifically, we use a DNN to model the probability density of cover images, and hide a secret image in one particular location of the learned distribution. As an instantiation, we adopt a SinGAN, a pyramid of generative adversarial networks (GANs), to learn the patch distribution of one cover image. We hide the secret image by fitting a deterministic mapping from a fixed set of noise maps (generated by an embedding key) to the secret image during patch distribution learning. The stego SinGAN, behaving as the original SinGAN, is publicly communicated; only the receiver with the embedding key is able to extract the secret image. We demonstrate the feasibility of our SinGAN approach in terms of extraction accuracy and model security. Moreover, we show the flexibility of the proposed method in terms of hiding multiple images for different receivers and obfuscating the secret image.

cs.CR↗
arXiv2022

Towards Communication Efficient and Fair Federated Personalized Sequential Recommendation

Federated recommendations leverage the federated learning (FL) techniques to make privacy-preserving recommendations. Though recent success in the federated recommender system, several vital challenges remain to be addressed: (i) The majority of federated recommendation models only consider the model performance and the privacy-preserving ability, while ignoring the optimization of the communication process; (ii) Most of the federated recommenders are designed for heterogeneous systems, causing unfairness problems during the federation process; (iii) The personalization techniques have been less explored in many federated recommender systems. In this paper, we propose a Communication efficient and Fair personalized Federated personalized Sequential Recommendation algorithm (CF-FedSR) to tackle these challenges. CF-FedSR introduces a communication-efficient scheme that employs adaptive client selection and clustering-based sampling to accelerate the training process. A fairness-aware model aggregation algorithm that can adaptively capture the data and performance imbalance among different clients to address the unfairness problems is proposed. The personalization module assists clients in making personalized recommendations and boosts the recommendation performance via local fine-tuning and model adaption. Extensive experimental results show the effectiveness and efficiency of our proposed method.

cs.IR↗
arXiv2022

HySAGE: A Hybrid Static and Adaptive Graph Embedding Network for Context-Drifting Recommendations

The recent popularity of edge devices and Artificial Intelligent of Things (AIoT) has driven a new wave of contextual recommendations, such as location based Point of Interest (PoI) recommendations and computing resource-aware mobile app recommendations. In many such recommendation scenarios, contexts are drifting over time. For example, in a mobile game recommendation, contextual features like locations, battery, and storage levels of mobile devices are frequently drifting over time. However, most existing graph-based collaborative filtering methods are designed under the assumption of static features. Therefore, they would require frequent retraining and/or yield graphical models burgeoning in sizes, impeding their suitability for context-drifting recommendations. In this work, we propose a specifically tailor-made Hybrid Static and Adaptive Graph Embedding (HySAGE) network for context-drifting recommendations. Our key idea is to disentangle the relatively static user-item interaction and rapidly drifting contextual features. Specifically, our proposed HySAGE network learns a relatively static graph embedding from user-item interaction and an adaptive embedding from drifting contextual features. These embeddings are incorporated into an interest network to generate the user interest in some certain context. We adopt an interactive attention module to learn the interactions among static graph embeddings, adaptive contextual embeddings, and user interest, helping to achieve a better final representation. Extensive experiments on real-world datasets demonstrate that HySAGE significantly improves the performance of the existing state-of-the-art recommendation algorithms.

cs.IR↗