Jinyang Gao

Daoyuan Chen, Yilun Huang, Zhijian Ma et al.

The immense evolution in Large Language Models (LLMs) has underscored the importance of massive, heterogeneous, and high-quality data. A data recipe is a mixture of data from different sources for training LLMs, which plays a vital role in LLMs' performance. Existing open-source tools for LLM data processing are mostly tailored for specific data recipes. To continuously uncover the potential of LLMs, incorporate data from new sources, and improve LLMs' performance, we build a new system named Data-Juicer, with which we can efficiently generate diverse data recipes, explore different possibilities in forming data mixtures, and evaluate their effects on model performance. Different from traditional data-analytics pipelines, Data-Juicer faces some unique challenges. Firstly, the possible data sources for forming data recipes are truly heterogeneous and massive with various qualities. Secondly, it is extremely expensive to precisely evaluate data recipes' impact on LLMs' performance. Thirdly, the end users of Data-Juicer, model developers, need sufficient flexibility to configure and evaluate different data recipes. Data-Juicer features a fine-grained abstraction of pipelines for constructing data recipes, with over 50 built-in operators for easy composition and extension. By incorporating visualization and auto-evaluation capabilities, Data-Juicer enables a timely feedback loop for both LLM pre-training and fine-tuning. Further, Data-Juicer is optimized and integrated with ecosystems for LLM training, evaluation, and distributed computing. The data recipes derived with Data-Juicer gain notable improvements on state-of-the-art LLMs, by up to 7.45% increase in averaged score across 16 LLM benchmarks and 17.5% higher win rate in pair-wise GPT-4 evaluations. Our system, data recipes, and tutorials are released, calling for broader data-centric research on training and understanding LLMs.

Tao Wu, Mengze Li, Jingyuan Chen et al.

Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g., change captioning). Existing MLLMs typically follow a two-step process in their pipelines: first, extracting visual tokens independently for each input image, and then aligning these visual tokens from different images with the Large Language Model (LLM) in its textual feature space. However, the independent extraction of visual tokens for each image may result in different semantics being prioritized for different images in the first step, leading to a lack of preservation of linking information among images for subsequent LLM analysis. This issue becomes more serious in scenarios where significant variations exist among the images (e.g., visual storytelling). To address this challenge, we introduce Semantic Alignment for Multi-modal large language models (SAM). By involving the bidirectional semantic guidance between different images in the visual-token extraction process, SAM aims to enhance the preservation of linking information for coherent analysis and align the semantics of different images before feeding them into LLM. As the test bed, we propose a large-scale dataset named MmLINK consisting of 69K samples. Different from most existing datasets for MLLMs fine-tuning, our MmLINK dataset comprises multi-modal instructions with significantly diverse images. Extensive experiments on the group captioning task and the storytelling task prove the effectiveness of our SAM model, surpassing the state-of-the-art methods by a large margin (+37% for group captioning and +22% for storytelling on CIDEr score). Project page: https://mccartney01.github.io/SAM.

Xue Wang, Tian Zhou, Jinyang Gao et al.

We present a joint forecasting framework for time series prediction that contrasts with traditional direct or recursive methods. This framework achieves state-of-the-art performance for our designed foundation model, YingLong, and reveals a novel scaling effect: longer outputs significantly enhance model accuracy due to delayed chain-of-thought reasoning in our non-causal approach. YingLong is a non-causal, bidirectional attention encoder-only transformer trained through masked token recovery, aligning more effectively with language understanding tasks than with generation tasks. Additionally, we boost performance by tackling output variance with a multi-input ensemble. We release four foundation models ranging from 6M to 300M parameters, demonstrating superior results in zero-shot tasks on the ETT and Weather datasets. YingLong achieves more than 60% best performance. To ensure generalizability, we assessed the models using the GIFT-Eval benchmark, which comprises 23 time series datasets across 7 domains. Yinglong significantly outperformed the best time-series foundation models, end-to-end trained models by 14% and 44% in rank respectively.The pretrained 300M model is available at https://huggingface.co/qcw1314/YingLong_300m

Wang Xue, Tian Zhou, Qingsong Wen et al.

Recent studies have demonstrated the great power of Transformer models for time series forecasting. One of the key elements that lead to the transformer's success is the channel-independent (CI) strategy to improve the training robustness. However, the ignorance of the correlation among different channels in CI would limit the model's forecasting capacity. In this work, we design a special Transformer, i.e., Channel Aligned Robust Blend Transformer (CARD for short), that addresses key shortcomings of CI type Transformer in time series forecasting. First, CARD introduces a channel-aligned attention structure that allows it to capture both temporal correlations among signals and dynamical dependence among multiple variables over time. Second, in order to efficiently utilize the multi-scale knowledge, we design a token blend module to generate tokens with different resolutions. Third, we introduce a robust loss function for time series forecasting to alleviate the potential overfitting issue. This new loss function weights the importance of forecasting over a finite horizon based on prediction uncertainties. Our evaluation of multiple long-term and short-term forecasting datasets demonstrates that CARD significantly outperforms state-of-the-art time series forecasting methods. The code is available at the following repository:https://github.com/wxie9/CARD

Shuchang Tao, Liuyi Yao, Hanxing Ding et al.

Despite the success of large language models (LLMs) in natural language generation, much evidence shows that LLMs may produce incorrect or nonsensical text. This limitation highlights the importance of discerning when to trust LLMs, especially in safety-critical domains. Existing methods often express reliability by confidence level, however, their effectiveness is limited by the lack of objective guidance. To address this, we propose CONfidence-Quality-ORDer-preserving alignment approach (CONQORD), which leverages reinforcement learning guided by a tailored dual-component reward function. This function integrates quality reward and order-preserving alignment reward functions. Specifically, the order-preserving reward incentivizes the model to verbalize greater confidence for responses of higher quality to align the order of confidence and quality. Experiments demonstrate that CONQORD significantly improves the alignment performance between confidence and response accuracy, without causing over-cautious. Furthermore, the aligned confidence provided by CONQORD informs when to trust LLMs, and acts as a determinant for initiating the retrieval process of external knowledge. Aligning confidence with response quality ensures more transparent and reliable responses, providing better trustworthiness.

Shen Li, Liuyi Yao, Jinyang Gao et al.

To support various applications, a prevalent and efficient approach for business owners is leveraging their valuable datasets to fine-tune a pre-trained LLM through the API provided by LLM owners or cloud servers. However, this process carries a substantial risk of model misuse, potentially resulting in severe economic consequences for business owners. Thus, safeguarding the copyright of these customized models during LLM fine-tuning has become an urgent practical requirement, but there are limited existing solutions to provide such protection. To tackle this pressing issue, we propose a novel watermarking approach named ``Double-I watermark''. Specifically, based on the instruct-tuning data, two types of backdoor data paradigms are introduced with trigger in the instruction and the input, respectively. By leveraging LLM's learning capability to incorporate customized backdoor samples into the dataset, the proposed approach effectively injects specific watermarking information into the customized model during fine-tuning, which makes it easy to inject and verify watermarks in commercial scenarios. We evaluate the proposed "Double-I watermark" under various fine-tuning methods, demonstrating its harmlessness, robustness, uniqueness, imperceptibility, and validity through both quantitative and qualitative analyses.

Yuan Gao, Haokun Chen, Xiang Wang et al.

Machine learning models have demonstrated remarkable efficacy and efficiency in a wide range of stock forecasting tasks. However, the inherent challenges of data scarcity, including low signal-to-noise ratio (SNR) and data homogeneity, pose significant obstacles to accurate forecasting. To address this issue, we propose a novel approach that utilizes artificial intelligence-generated samples (AIGS) to enhance the training procedures. In our work, we introduce the Diffusion Model to generate stock factors with Transformer architecture (DiffsFormer). DiffsFormer is initially trained on a large-scale source domain, incorporating conditional guidance so as to capture global joint distribution. When presented with a specific downstream task, we employ DiffsFormer to augment the training procedure by editing existing samples. This editing step allows us to control the strength of the editing process, determining the extent to which the generated data deviates from the target domain. To evaluate the effectiveness of DiffsFormer augmented training, we conduct experiments on the CSI300 and CSI800 datasets, employing eight commonly used machine learning models. The proposed method achieves relative improvements of 7.2% and 27.8% in annualized return ratio for the respective datasets. Furthermore, we perform extensive experiments to gain insights into the functionality of DiffsFormer and its constituent components, elucidating how they address the challenges of data scarcity and enhance the overall model performance. Our research demonstrates the efficacy of leveraging AIGS and the DiffsFormer architecture to mitigate data scarcity in stock forecasting tasks.

Hanxing Ding, Shuchang Tao, Liang Pang et al.

Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools. Existing approaches face significant challenges, including reliance on hand-crafted prompts, difficulty in multi-step planning, and lack of precise error diagnosis and reflection mechanisms. We propose ToolCoder, a novel framework that reformulates tool learning as a code generation task. Inspired by software engineering principles, ToolCoder transforms natural language queries into structured Python function scaffold and systematically breaks down tasks with descriptive comments, enabling LLMs to leverage coding paradigms for complex reasoning and planning. It then generates and executes function implementations to obtain final responses. Additionally, ToolCoder stores successfully executed functions in a repository to promote code reuse, while leveraging error traceback mechanisms for systematic debugging, optimizing both execution efficiency and robustness. Experiments demonstrate that ToolCoder achieves superior performance in task completion accuracy and execution reliability compared to existing approaches, establishing the effectiveness of code-centric approaches in tool learning.

Kexin Huang, Junkang Wu, Ziqian Chen et al.

Preference learning is critical for aligning large language models (LLMs) with human values, with the quality of preference datasets playing a crucial role in this process. While existing metrics primarily assess data quality based on either explicit or implicit reward margins, they often provide contradictory evaluations for the same data. To address this issue, we introduce the alignment potential metric, which quantifies the gap from the model's current implicit reward margin to the target explicit reward margin, thereby estimating the model's potential to align with the preference data. Empirical results demonstrate that training on data selected by this metric consistently enhances alignment performance, surpassing existing metrics across different base models and optimization objectives. Furthermore, our method extends to self-play data generation frameworks, where the metric is used to identify high-quality data within the self-generated content by LLMs. Under this data generation scenario, our method surpasses current state-of-the-art (SOTA) results across various training settings and demonstrates continuous improvements in alignment performance as dataset size and training iterations increase.

Cheng Chen, Yunpeng Zhai, Yifan Zhao et al. · pku

In-context learning (ICL), a predominant trend in instruction learning, aims at enhancing the performance of large language models by providing clear task guidance and examples, improving their capability in task understanding and execution. This paper investigates ICL on Large Vision-Language Models (LVLMs) and explores the policies of multi-modal demonstration selection. Existing research efforts in ICL face significant challenges: First, they rely on pre-defined demonstrations or heuristic selecting strategies based on human intuition, which are usually inadequate for covering diverse task requirements, leading to sub-optimal solutions; Second, individually selecting each demonstration fails in modeling the interactions between them, resulting in information redundancy. Unlike these prevailing efforts, we propose a new exploration-exploitation reinforcement learning framework, which explores policies to fuse multi-modal information and adaptively select adequate demonstrations as an integrated whole. The framework allows LVLMs to optimize themselves by continually refining their demonstrations through self-exploration, enabling the ability to autonomously identify and generate the most effective selection policies for in-context learning. Experimental results verify the superior performance of our approach on four Visual Question-Answering (VQA) datasets, demonstrating its effectiveness in enhancing the generalization capability of few-shot LVLMs.

Yang Li, Jiawei Jiang, Jinyang Gao et al.

The Combined Algorithm Selection and Hyperparameter optimization (CASH) is one of the most fundamental problems in Automatic Machine Learning (AutoML). The existing Bayesian optimization (BO) based solutions turn the CASH problem into a Hyperparameter Optimization (HPO) problem by combining the hyperparameters of all machine learning (ML) algorithms, and use BO methods to solve it. As a result, these methods suffer from the low-efficiency problem due to the huge hyperparameter space in CASH. To alleviate this issue, we propose the alternating optimization framework, where the HPO problem for each ML algorithm and the algorithm selection problem are optimized alternately. In this framework, the BO methods are used to solve the HPO problem for each ML algorithm separately, incorporating a much smaller hyperparameter space for BO methods. Furthermore, we introduce Rising Bandits, a CASH-oriented Multi-Armed Bandits (MAB) variant, to model the algorithm selection in CASH. This framework can take the advantages of both BO in solving the HPO problem with a relatively small hyperparameter space and the MABs in accelerating the algorithm selection. Moreover, we further develop an efficient online algorithm to solve the Rising Bandits with provably theoretical guarantees. The extensive experiments on 30 OpenML datasets demonstrate the superiority of the proposed approach over the competitive baselines.

Yang Li, Yu Shen, Jiawei Jiang et al.

Hyperparameter optimization (HPO) is a fundamental problem in automatic machine learning (AutoML). However, due to the expensive evaluation cost of models (e.g., training deep learning models or training models on large datasets), vanilla Bayesian optimization (BO) is typically computationally infeasible. To alleviate this issue, Hyperband (HB) utilizes the early stopping mechanism to speed up configuration evaluations by terminating those badly-performing configurations in advance. This leads to two kinds of quality measurements: (1) many low-fidelity measurements for configurations that get early-stopped, and (2) few high-fidelity measurements for configurations that are evaluated without being early stopped. The state-of-the-art HB-style method, BOHB, aims to combine the benefits of both BO and HB. Instead of sampling configurations randomly in HB, BOHB samples configurations based on a BO surrogate model, which is constructed with the high-fidelity measurements only. However, the scarcity of high-fidelity measurements greatly hampers the efficiency of BO to guide the configuration search. In this paper, we present MFES-HB, an efficient Hyperband method that is capable of utilizing both the high-fidelity and low-fidelity measurements to accelerate the convergence of HPO tasks. Designing MFES-HB is not trivial as the low-fidelity measurements can be biased yet informative to guide the configuration search. Thus we propose to build a Multi- Fidelity Ensemble Surrogate (MFES) based on the generalized Product of Experts framework, which can integrate useful information from multi-fidelity measurements effectively. The empirical studies on the real-world AutoML tasks demonstrate that MFES-HB can achieve 3.3-8.9x speedups over the state-of-the-art approach - BOHB.

Haoji Hu, Xiangnan He, Jinyang Gao et al.

Next-basket recommendation (NBR) is prevalent in e-commerce and retail industry. In this scenario, a user purchases a set of items (a basket) at a time. NBR performs sequential modeling and recommendation based on a sequence of baskets. NBR is in general more complex than the widely studied sequential (session-based) recommendation which recommends the next item based on a sequence of items. Recurrent neural network (RNN) has proved to be very effective for sequential modeling and thus been adapted for NBR. However, we argue that existing RNNs cannot directly capture item frequency information in the recommendation scenario. Through careful analysis of real-world datasets, we find that {\em personalized item frequency} (PIF) information (which records the number of times that each item is purchased by a user) provides two critical signals for NBR. But, this has been largely ignored by existing methods. Even though existing methods such as RNN based methods have strong representation ability, our empirical results show that they fail to learn and capture PIF. As a result, existing methods cannot fully exploit the critical signals contained in PIF. Given this inherent limitation of RNNs, we propose a simple item frequency based k-nearest neighbors (kNN) method to directly utilize these critical signals. We evaluate our method on four public real-world datasets. Despite its relative simplicity, our method frequently outperforms the state-of-the-art NBR methods -- including deep learning based methods using RNNs -- when patterns associated with PIF play an important role in the data.

Shaofeng Cai, Gang Chen, Beng Chin Ooi et al.

Deep learning models have been used to support analytics beyond simple aggregation, where deeper and wider models have been shown to yield great results. These models consume a huge amount of memory and computational operations. However, most of the large-scale industrial applications are often computational budget constrained. In practice, the peak workload of inference service could be 10x higher than the average cases, with the presence of unpredictable extreme cases. Lots of computational resources could be wasted during off-peak hours and the system may crash when the workload exceeds system capacity. How to support deep learning services with a dynamic workload cost-efficiently remains a challenging problem. In this paper, we address the challenge with a general and novel training scheme called model slicing, which enables deep learning models to provide predictions within the prescribed computational resource budget dynamically. Model slicing could be viewed as an elastic computation solution without requiring more computational resources. Succinctly, each layer in the model is divided into groups of a contiguous block of basic components (i.e. neurons in dense layers and channels in convolutional layers), and then partially ordered relation is introduced to these groups by enforcing that groups participated in each forward pass always starts from the first group to the dynamically-determined rightmost group. Trained by dynamically indexing the rightmost group with a single parameter slice rate, the network is engendered to build up group-wise and residual representation. Then during inference, a sub-model with fewer groups can be readily deployed for efficiency whose computation is roughly quadratic to the width controlled by the slice rate. Extensive experiments show that models trained with model slicing can effectively support on-demand workload with elastic inference cost.

Xiangrui Cai, Jinyang Gao, Kee Yuan Ngiam et al.

Embeddings of medical concepts such as medication, procedure and diagnosis codes in Electronic Medical Records (EMRs) are central to healthcare analytics. Previous work on medical concept embedding takes medical concepts and EMRs as words and documents respectively. Nevertheless, such models miss out the temporal nature of EMR data. On the one hand, two consecutive medical concepts do not indicate they are temporally close, but the correlations between them can be revealed by the time gap. On the other hand, the temporal scopes of medical concepts often vary greatly (e.g., \textit{common cold} and \textit{diabetes}). In this paper, we propose to incorporate the temporal information to embed medical codes. Based on the Continuous Bag-of-Words model, we employ the attention mechanism to learn a "soft" time-aware context window for each medical concept. Experiments on public and proprietary datasets through clustering and nearest neighbour search tasks demonstrate the effectiveness of our model, showing that it outperforms five state-of-the-art baselines.

Jinyang Gao, Wei Wang, Meihui Zhang et al.

Recent advances in artificial intelligence (AI) and machine learning have created a general perception that AI could be used to solve complex problems, and in some situations over-hyped as a tool that can be so easily used. Unfortunately, the barrier to realization of mass adoption of AI on various business domains is too high because most domain experts have no background in AI. Developing AI applications involves multiple phases, namely data preparation, application modeling, and product deployment. The effort of AI research has been spent mostly on new AI models (in the model training stage) to improve the performance of benchmark tasks such as image recognition. Many other factors such as usability, efficiency and security of AI have not been well addressed, and therefore form a barrier to democratizing AI. Further, for many real world applications such as healthcare and autonomous driving, learning via huge amounts of possibility exploration is not feasible since humans are involved. In many complex applications such as healthcare, subject matter experts (e.g. Clinicians) are the ones who appreciate the importance of features that affect health, and their knowledge together with existing knowledge bases are critical to the end results. In this paper, we take a new perspective on developing AI solutions, and present a solution for making AI usable. We hope that this resolution will enable all subject matter experts (eg. Clinicians) to exploit AI like data scientists.

Wei Wang, Sheng Wang, Jinyang Gao et al.

Big data analytics is gaining massive momentum in the last few years. Applying machine learning models to big data has become an implicit requirement or an expectation for most analysis tasks, especially on high-stakes applications.Typical applications include sentiment analysis against reviews for analyzing on-line products, image classification in food logging applications for monitoring user's daily intake and stock movement prediction. Extending traditional database systems to support the above analysis is intriguing but challenging. First, it is almost impossible to implement all machine learning models in the database engines. Second, expertise knowledge is required to optimize the training and inference procedures in terms of efficiency and effectiveness, which imposes heavy burden on the system users. In this paper, we develop and present a system, called Rafiki, to provide the training and inference service of machine learning models, and facilitate complex analytics on top of cloud platforms. Rafiki provides distributed hyper-parameter tuning for the training service, and online ensemble modeling for the inference service which trades off between latency and accuracy. Experimental results confirm the efficiency, effectiveness, scalability and usability of Rafiki.

Wei Wang, Gang Chen, Haibo Chen et al.

Recently, deep learning techniques have enjoyed success in various multimedia applications, such as image classification and multi-modal data analysis. Large deep learning models are developed for learning rich representations of complex data. There are two challenges to overcome before deep learning can be widely adopted in multimedia and other applications. One is usability, namely the implementation of different models and training algorithms must be done by non-experts without much effort especially when the model is large and complex. The other is scalability, that is the deep learning system must be able to provision for a huge demand of computing resources for training large models with massive datasets. To address these two challenges, in this paper, we design a distributed deep learning platform called SINGA which has an intuitive programming model based on the common layer abstraction of deep learning models. Good scalability is achieved through flexible distributed training architecture and specific optimization techniques. SINGA runs on GPUs as well as on CPUs, and we show that it outperforms many other state-of-the-art deep learning systems. Our experience with developing and training deep learning models for real-life multimedia applications in SINGA shows that the platform is both usable and scalable.

Jinyang Gao, H. V. Jagadish, Beng Chin Ooi

Recent years have witnessed amazing outcomes from "Big Models" trained by "Big Data". Most popular algorithms for model training are iterative. Due to the surging volumes of data, we can usually afford to process only a fraction of the training data in each iteration. Typically, the data are either uniformly sampled or sequentially accessed. In this paper, we study how the data access pattern can affect model training. We propose an Active Sampler algorithm, where training data with more "learning value" to the model are sampled more frequently. The goal is to focus training effort on valuable instances near the classification boundaries, rather than evident cases, noisy data or outliers. We show the correctness and optimality of Active Sampler in theory, and then develop a light-weight vectorized implementation. Active Sampler is orthogonal to most approaches optimizing the efficiency of large-scale data analytics, and can be applied to most analytics models trained by stochastic gradient descent (SGD) algorithm. Extensive experimental evaluations demonstrate that Active Sampler can speed up the training procedure of SVM, feature selection and deep learning, for comparable training quality by 1.6-2.2x.