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.

Junkang Wu, Yuexiang Xie, Zhengyi Yang et al.

Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO is sensitive to the fine-tuning of its trade-off parameter $β$, as well as to the quality of the preference data. We analyze the impact of $β$ and data quality on DPO, uncovering that optimal $β$ values vary with the informativeness of pairwise data. Addressing the limitations of static $β$ values, we introduce a novel framework that dynamically calibrates $β$ at the batch level, informed by data quality considerations. Additionally, our method incorporates $β$-guided data filtering to safeguard against the influence of outliers. Through empirical evaluation, we demonstrate that our dynamic $β$ adjustment technique significantly improves DPO's performance across a range of models and datasets, offering a more robust and adaptable training paradigm for aligning LLMs with human feedback. The code is available at \url{https://github.com/junkangwu/beta-DPO}.

Junkang Wu, Yuexiang Xie, Zhengyi Yang et al.

This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences. We categorize noise into pointwise noise, which includes low-quality data points, and pairwise noise, which encompasses erroneous data pair associations that affect preference rankings. Utilizing Distributionally Robust Optimization (DRO), we enhance DPO's resilience to these types of noise. Our theoretical insights reveal that DPO inherently embeds DRO principles, conferring robustness to pointwise noise, with the regularization coefficient $β$ playing a critical role in its noise resistance. Extending this framework, we introduce Distributionally Robustifying DPO (Dr. DPO), which integrates pairwise robustness by optimizing against worst-case pairwise scenarios. The novel hyperparameter $β'$ in Dr. DPO allows for fine-tuned control over data pair reliability, providing a strategic balance between exploration and exploitation in noisy training environments. Empirical evaluations demonstrate that Dr. DPO substantially improves the quality of generated text and response accuracy in preference datasets, showcasing enhanced performance in both noisy and noise-free settings. The code is available at https://github.com/junkangwu/Dr_DPO.

Yige Yuan, Teng Xiao, Shuchang Tao et al.

Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on either reinforcement learning (RL) with verifiable signals or supervised fine-tuning (SFT) with high-quality long chain-of-thought (CoT) demonstrations, both of which are expensive. In this paper, we study a novel problem of incentivizing the reasoning capacity of LLMs without expensive high-quality demonstrations and reinforcement learning. We investigate whether the reasoning capabilities of LLMs can be effectively incentivized via supervision from significantly weaker models. We further analyze when and why such weak supervision succeeds in eliciting reasoning abilities in stronger models. Our findings show that supervision from significantly weaker reasoners can substantially improve student reasoning performance, recovering close to 94% of the gains of expensive RL at a fraction of the cost. Experiments across diverse benchmarks and model architectures demonstrate that weak reasoners can effectively incentivize reasoning in stronger student models, consistently improving performance across a wide range of reasoning tasks. Our results suggest that this simple weak-to-strong paradigm is a promising and generalizable alternative to costly methods for incentivizing strong reasoning capabilities at inference-time in LLMs. The code is publicly available at https://github.com/yuanyige/w2sr.

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.

Lizhe Fang, Yifei Wang, Zhaoyang Liu et al.

Handling long-context inputs is crucial for large language models (LLMs) in tasks such as extended conversations, document summarization, and many-shot in-context learning. While recent approaches have extended the context windows of LLMs and employed perplexity (PPL) as a standard evaluation metric, PPL has proven unreliable for assessing long-context capabilities. The underlying cause of this limitation has remained unclear. In this work, we provide a comprehensive explanation for this issue. We find that PPL overlooks key tokens, which are essential for long-context understanding, by averaging across all tokens and thereby obscuring the true performance of models in long-context scenarios. To address this, we propose \textbf{LongPPL}, a novel metric that focuses on key tokens by employing a long-short context contrastive method to identify them. Our experiments demonstrate that LongPPL strongly correlates with performance on various long-context benchmarks (e.g., Pearson correlation of -0.96), significantly outperforming traditional PPL in predictive accuracy. Additionally, we introduce \textbf{LongCE} (Long-context Cross-Entropy) loss, a re-weighting strategy for fine-tuning that prioritizes key tokens, leading to consistent improvements across diverse benchmarks. In summary, these contributions offer deeper insights into the limitations of PPL and present effective solutions for accurately evaluating and enhancing the long-context capabilities of LLMs. Code is available at https://github.com/PKU-ML/LongPPL.

Junkang Wu, Xue Wang, Zhengyi Yang et al.

Aligning large language models (LLMs) with human values and intentions is crucial for their utility, honesty, and safety. Reinforcement learning from human feedback (RLHF) is a popular approach to achieve this alignment, but it faces challenges in computational efficiency and training stability. Recent methods like Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO) have proposed offline alternatives to RLHF, simplifying the process by reparameterizing the reward function. However, DPO depends on a potentially suboptimal reference model, and SimPO's assumption of a fixed target reward margin may lead to suboptimal decisions in diverse data settings. In this work, we propose $α$-DPO, an adaptive preference optimization algorithm designed to address these limitations by introducing a dynamic reward margin. Specifically, $α$-DPO employs an adaptive preference distribution, balancing the policy model and the reference model to achieve personalized reward margins. We provide theoretical guarantees for $α$-DPO, demonstrating its effectiveness as a surrogate optimization objective and its ability to balance alignment and diversity through KL divergence control. Empirical evaluations on AlpacaEval 2 and Arena-Hard show that $α$-DPO consistently outperforms DPO and SimPO across various model settings, establishing it as a robust approach for fine-tuning LLMs. Our method achieves significant improvements in win rates, highlighting its potential as a powerful tool for LLM alignment. The code is available at https://github.com/junkangwu/alpha-DPO

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

Zhisheng Lin, Yifu Liu, Zhiling Luo et al.

The improvement in translating natural language to structured query language (SQL) can be attributed to the advancements in large language models (LLMs). Open-source LLMs, tailored for specific database dialects such as MySQL, have shown great performance. However, cloud service providers are looking for a unified database manager service (e.g., Cosmos DB from Azure, Amazon Aurora from AWS, Lindorm from AlibabaCloud) that can support multiple dialects. This requirement has led to the concept of multi-dialect query generation, which presents challenges to LLMs. These challenges include syntactic differences among dialects and imbalanced data distribution across multiple dialects. To tackle these challenges, we propose MoMQ, a novel Mixture-of-Experts-based multi-dialect query generation framework across both relational and non-relational databases. MoMQ employs a dialect expert group for each dialect and a multi-level routing strategy to handle dialect-specific knowledge, reducing interference during query generation. Additionally, a shared expert group is introduced to address data imbalance, facilitating the transfer of common knowledge from high-resource dialects to low-resource ones. Furthermore, we have developed a high-quality multi-dialect query generation benchmark that covers relational and non-relational databases such as MySQL, PostgreSQL, Cypher for Neo4j, and nGQL for NebulaGraph. Extensive experiments have shown that MoMQ performs effectively and robustly even in resource-imbalanced scenarios.

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

Yang Li, Yu Shen, Wentao Zhang et al.

Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, engineering, physics, and experimental design. However, it remains a challenge for users to apply BBO methods to their problems at hand with existing software packages, in terms of applicability, performance, and efficiency. In this paper, we build OpenBox, an open-source and general-purpose BBO service with improved usability. The modular design behind OpenBox also facilitates flexible abstraction and optimization of basic BBO components that are common in other existing systems. OpenBox is distributed, fault-tolerant, and scalable. To improve efficiency, OpenBox further utilizes "algorithm agnostic" parallelization and transfer learning. Our experimental results demonstrate the effectiveness and efficiency of OpenBox compared to existing systems.

Yingqi Gao, Yifu Liu, Xiaoxia Li et al.

To tackle the challenges of large language model performance in natural language to SQL tasks, we introduce XiYan-SQL, an innovative framework that employs a multi-generator ensemble strategy to improve candidate generation. We introduce M-Schema, a semi-structured schema representation method designed to enhance the understanding of database structures. To enhance the quality and diversity of generated candidate SQL queries, XiYan-SQL integrates the significant potential of in-context learning (ICL) with the precise control of supervised fine-tuning. On one hand, we propose a series of training strategies to fine-tune models to generate high-quality candidates with diverse preferences. On the other hand, we implement the ICL approach with an example selection method based on named entity recognition to prevent overemphasis on entities. The refiner optimizes each candidate by correcting logical or syntactical errors. To address the challenge of identifying the best candidate, we fine-tune a selection model to distinguish nuances of candidate SQL queries. The experimental results on multiple dialect datasets demonstrate the robustness of XiYan-SQL in addressing challenges across different scenarios. Overall, our proposed XiYan-SQL achieves the state-of-the-art execution accuracy of 75.63% on Bird benchmark, 89.65% on the Spider test set, 69.86% on SQL-Eval, 41.20% on NL2GQL. The proposed framework not only enhances the quality and diversity of SQL queries but also outperforms previous methods.

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.

Yifu Liu, Yin Zhu, Yingqi Gao et al.

To leverage the advantages of LLM in addressing challenges in the Text-to-SQL task, we present XiYan-SQL, an innovative framework effectively generating and utilizing multiple SQL candidates. It consists of three components: 1) a Schema Filter module filtering and obtaining multiple relevant schemas; 2) a multi-generator ensemble approach generating multiple highquality and diverse SQL queries; 3) a selection model with a candidate reorganization strategy implemented to obtain the optimal SQL query. Specifically, for the multi-generator ensemble, we employ a multi-task fine-tuning strategy to enhance the capabilities of SQL generation models for the intrinsic alignment between SQL and text, and construct multiple generation models with distinct generation styles by fine-tuning across different SQL formats. The experimental results and comprehensive analysis demonstrate the effectiveness and robustness of our framework. Overall, XiYan-SQL achieves a new SOTA performance of 75.63% on the notable BIRD benchmark, surpassing all previous methods. It also attains SOTA performance on the Spider test set with an accuracy of 89.65%.

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.

Junkang Wu, Kexin Huang, Xue Wang et al.

Aligning large language models (LLMs) with human preferences is critical for real-world deployment, yet existing methods like RLHF face computational and stability challenges. While DPO establishes an offline paradigm with single hyperparameter $β$, subsequent methods like SimPO reintroduce complexity through dual parameters ($β$, $γ$). We propose {ReLU-based Preference Optimization (RePO)}, a streamlined algorithm that eliminates $β$ via two advances: (1) retaining SimPO's reference-free margins but removing $β$ through gradient analysis, and (2) adopting a ReLU-based max-margin loss that naturally filters trivial pairs. Theoretically, RePO is characterized as SimPO's limiting case ($β\to \infty$), where the logistic weighting collapses to binary thresholding, forming a convex envelope of the 0-1 loss. Empirical results on AlpacaEval 2 and Arena-Hard show that RePO outperforms DPO and SimPO across multiple base models, requiring only one hyperparameter to tune.

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.

Xu Xie, Zhaoyang Liu, Shiwen Wu et al.

To improve user experience and profits of corporations, modern industrial recommender systems usually aim to select the items that are most likely to be interacted with (e.g., clicks and purchases). However, they overlook the fact that users may purchase the items even without recommendations. To select these effective items, it is essential to estimate the causal effect of recommendations. The real effective items are the ones which can contribute to purchase probability uplift. Nevertheless, it is difficult to obtain the real causal effect since we can only recommend or not recommend an item to a user at one time. Furthermore, previous works usually rely on the randomized controlled trial~(RCT) experiment to evaluate their performance. However, it is usually not practicable in the recommendation scenario due to its unavailable time consuming. To tackle these problems, in this paper, we propose a causal collaborative filtering~(CausCF) method inspired by the widely adopted collaborative filtering~(CF) technique. It is based on the idea that similar users not only have a similar taste on items, but also have similar treatment effect under recommendations. CausCF extends the classical matrix factorization to the tensor factorization with three dimensions -- user, item, and treatment. Furthermore, we also employs regression discontinuity design (RDD) to evaluate the precision of the estimated causal effects from different models. With the testable assumptions, RDD analysis can provide an unbiased causal conclusion without RCT experiments. Through dedicated experiments on both the public datasets and the industrial application, we demonstrate the effectiveness of our proposed CausCF on the causal effect estimation and ranking performance improvement.

Xu Xie, Fei Sun, Xiaoyong Yang et al.

Recommender systems play a vital role in modern online services, such as Amazon and Taobao. Traditional personalized methods, which focus on user-item (UI) relations, have been widely applied in industrial settings, owing to their efficiency and effectiveness. Despite their success, we argue that these approaches ignore local information hidden in similar users. To tackle this problem, user-based methods exploit similar user relations to make recommendations in a local perspective. Nevertheless, traditional user-based methods, like userKNN and matrix factorization, are intractable to be deployed in the real-time applications since such transductive models have to be recomputed or retrained with any new interaction. To overcome this challenge, we propose a framework called self-complementary collaborative filtering~(SCCF) which can make recommendations with both global and local information in real time. On the one hand, it utilizes UI relations and user neighborhood to capture both global and local information. On the other hand, it can identify similar users for each user in real time by inferring user representations on the fly with an inductive model. The proposed framework can be seamlessly incorporated into existing inductive UI approach and benefit from user neighborhood with little additional computation. It is also the first attempt to apply user-based methods in real-time settings. The effectiveness and efficiency of SCCF are demonstrated through extensive offline experiments on four public datasets, as well as a large scale online A/B test in Taobao.

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.

Xu Xie, Fei Sun, Zhaoyang Liu et al.

Sequential recommendation methods play a crucial role in modern recommender systems because of their ability to capture a user's dynamic interest from her/his historical interactions. Despite their success, we argue that these approaches usually rely on the sequential prediction task to optimize the huge amounts of parameters. They usually suffer from the data sparsity problem, which makes it difficult for them to learn high-quality user representations. To tackle that, inspired by recent advances of contrastive learning techniques in the computer version, we propose a novel multi-task model called \textbf{C}ontrastive \textbf{L}earning for \textbf{S}equential \textbf{Rec}ommendation~(\textbf{CL4SRec}). CL4SRec not only takes advantage of the traditional next item prediction task but also utilizes the contrastive learning framework to derive self-supervision signals from the original user behavior sequences. Therefore, it can extract more meaningful user patterns and further encode the user representation effectively. In addition, we propose three data augmentation approaches to construct self-supervision signals. Extensive experiments on four public datasets demonstrate that CL4SRec achieves state-of-the-art performance over existing baselines by inferring better user representations.

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.

Chen Xu, Quan Li, Junfeng Ge et al.

Features play an important role in the prediction tasks of e-commerce recommendations. To guarantee the consistency of off-line training and on-line serving, we usually utilize the same features that are both available. However, the consistency in turn neglects some discriminative features. For example, when estimating the conversion rate (CVR), i.e., the probability that a user would purchase the item if she clicked it, features like dwell time on the item detailed page are informative. However, CVR prediction should be conducted for on-line ranking before the click happens. Thus we cannot get such post-event features during serving. We define the features that are discriminative but only available during training as the privileged features. Inspired by the distillation techniques which bridge the gap between training and inference, in this work, we propose privileged features distillation (PFD). We train two models, i.e., a student model that is the same as the original one and a teacher model that additionally utilizes the privileged features. Knowledge distilled from the more accurate teacher is transferred to the student to improve its accuracy. During serving, only the student part is extracted and it relies on no privileged features. We conduct experiments on two fundamental prediction tasks at Taobao recommendations, i.e., click-through rate (CTR) at coarse-grained ranking and CVR at fine-grained ranking. By distilling the interacted features that are prohibited during serving for CTR and the post-event features for CVR, we achieve significant improvements over their strong baselines. During the on-line A/B tests, the click metric is improved by +5.0% in the CTR task. And the conversion metric is improved by +2.3% in the CVR task. Besides, by addressing several issues of training PFD, we obtain comparable training speed as the baselines without any distillation.

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.