Vision-language retrieval (VLR), which uses text or image queries to retrieve corresponding cross-modal content, plays a crucial role in multimedia and computer vision tasks. However, challenging concepts in queries often confuse retrievers, limiting their ability to align concepts with visual content. Existing query optimization methods neglect retrievers’ preferences (i.e., text descriptions that better match their corresponding visual content), resulting in unadapted to the retriever and leading to suboptimal performance. To address this, we propose the Retriever-Adaptive Query Optimization (RAQO), an interpretable framework that rewrites queries based on retriever-specific preferences. Specifically, we first leverages multimodal large language Models (MLLMs) and retrieval's feedback to construct the MLLMs-Driven Preference-Aware Dataset Engine (MPADE), which automatically refine queries offline, capturing the retriever’s implicit preferences. Then, we introduce a ``detect-then-rewrite" chain-of-thought rewriting (ReCoT) strategy equipped with a progressive preference alignment pipeline, including three stages: ambiguity detection fine-tuning, query rewriting fine-tuning, and preference rank optimization. This design enables the rewriter to focus on confusing concepts and produce retriever-adapted, high-quality queries. Extensive VLR benchmark experiments have demonstrated the superiority of RAQO in cross-modal retrieval, as well as its interpretability, generalizability and transferability.

User behavior sequences in modern recommendation systems exhibit significant length heterogeneity, ranging from sparse short-term interactions to rich long-term histories. While longer sequences provide more context, we observe that increasing the maximum input sequence length in existing CTR models paradoxically degrades performance for short-sequence users due to attention polarization and length imbalance in training data. To address this, we propose LAIN (Length-Adaptive Interest Network), a plug-and-play framework that explicitly incorporates sequence length as a conditioning signal to balance long- and short-sequence modeling. LAIN consists of three lightweight components: a Spectral Length Encoder that maps length into continuous representations, Length-Conditioned Prompting that injects global contextual cues into both long- and short-term behavior branches, and Length-Modulated Attention that adaptively adjusts attention sharpness based on sequence length. Extensive experiments on three real-world benchmarks across five strong CTR backbones show that LAIN consistently improves overall performance, achieving up to 1.15% AUC gain and 2.25% log loss reduction. Notably, our method significantly improves accuracy for short-sequence users without sacrificing long-sequence effectiveness. Our work offers a general, efficient, and deployable solution to mitigate length-induced bias in sequential recommendation.

Large-scale online marketplaces and recommender systems are crucial technological foundations for the development of e-commerce. In industrial recommender systems, features play a vital role as they carry essential information for downstream models. Accurate estimation of feature importance is critical, as it helps identify the most useful feature subsets from thousands of candidates for online services. Such a selection enables optimization of online performance while reducing computational burden. To address the feature selection challenges in deep learning, trainable gate-based and sensitivity-based methods have been proposed and proven effective in the industry. However, by analyzing real-world examples, we identified three bias issues that cause feature importance estimation to rely on partial model layers, samples, or gradients, ultimately leading to inaccurate feature importance estimates. We refer to these biases as layer bias, baseline bias, and approximation bias. To mitigate these biases, we propose FairFS, a fair and accurate feature selection algorithm. On one hand, FairFS directly regularizes feature importance estimation across all non-linear transformational layers to avoid layer bias. On the other hand, it employs a smooth baseline feature close to the classifier's decision boundary and an aggregated approximation method to mitigate bias issues. Extensive experiments demonstrate how FairFS mitigates these three biases and achieves state-of-the-art feature selection results.

In music streaming applications, next music tracks are typically played automatically and require less consumption time than many other contents (e.g., books and movies). These characteristics potentially lead to long and noisy user listening history, making generic sequential recommendation models more error-prone when modeling user interests. To bridge the gap, we propose to retrieve representative music tracks from the original listening history for recommendation. Differing from existing user behavior retrieval techniques, we pursue a fine-grained, content-based, and temporal user behavior retrieval framework, namely FactUBR, to better exploit music track content and the fine-grained connections between temporally dependent tracks in the listening history. Technically, FactUBR consists of a reinforced content-based retrieval module (RCB) and a differentiable temporal-channel (DTC) retrieval module. RCB follows a reinforcement-learning procedure to optimize sequential retrieval decisions based on content differences between the state and the observation, maximizing rewards of retrieval diversity and recommendation performance. DTC evaluates the fine-grained correlations between temporal listening segments and the candidate music track, and employs the perturbed maximum technique for hard retrieval optimization. Extensive experiments on two public music recommendation benchmarks demonstrate that FactUBR can enhance various representative sequential recommendation models and outperform state-of-the-art (SOTA) behavior retrieval techniques.

With the rise of generative paradigms, generative recommendation has garnered increasing attention. The core component is the item code , generally derived by quantizing collaborative or semantic representations to serve as candidate items identifiers in the context. However, existing methods typically construct separate codes for each modality, leading to higher computational and storage costs and hindering the integration of their complementary strengths. Considering this limitation, we seek to integrate two different modalities into a unified code , fully unleashing the potential of complementary nature among modalities. Nevertheless, the integration remains challenging: the integrated embedding obtained by the common concatenation method would lead to underutilization of collaborative knowledge, thereby resulting in limited effectiveness. To address this, we propose a novel method, named UNGER, which integrates semantic and collaborative knowledge into a UNified code for Generative Recommendation . Specifically, we propose to adaptively learn an integrated embedding through the joint optimization of cross-modality knowledge alignment and next-item prediction tasks. Subsequently, to mitigate the information loss caused by the quantization process, we introduce an intra-modality knowledge distillation task, using the integrated embeddings as supervised signals to compensate. Extensive experiments on three widely used benchmarks demonstrate the superiority of our approach compared to existing methods.

Recommender system plays a pervasive role in today’s online services, yet its closed-loop nature, i.e., training and deploying within a specific closed domain, constrains its access to open-world knowledge. Recently, the emergence of large language models (LLMs) has shown promise in bridging this gap by encoding extensive world knowledge and demonstrating advanced reasoning capabilities. However, previous attempts to directly implement LLMs as recommenders fall short in meeting the demanding requirements of industrial recommender systems, particularly in terms of online inference latency and offline resource efficiency. In this work, we propose an Open-World R ecommendation Framework with E fficient and Deployable K nowledge I nfusion from Large Language Models, dubbed REKI , to acquire two types of external knowledge about users and items from LLMs. Specifically, we introduce factorization prompting to elicit accurate knowledge reasoning on user preferences and items. With factorization prompting, we develop individual knowledge extraction and collective knowledge extraction tailored for different scales of recommendation scenarios, effectively reducing offline resource consumption. Subsequently, the generated user and item knowledge undergoes efficient transformation and condensation into augmented vectors through a hybridized expert-integrated network , ensuring its compatibility with the recommendation task. The obtained vectors can then be directly used to enhance the performance of any conventional recommendation model. We also ensure efficient inference by preprocessing and prestoring the knowledge from the LLM. Extensive experiments demonstrate that REKI significantly outperforms the state-of-the-art baselines and is compatible with a diverse array of recommendation algorithms and tasks. Now, REKI has been deployed to Huawei’s news and music recommendation platforms and gained a 7% and 1.99% improvement during the online A/B test.

Vision-language retrieval (VLR) has attracted significant attention in both academia and industry, which involves using text (or images) as queries to retrieve corresponding images (or text). However, existing methods often neglect the rich visual semantics knowledge of entities, thus leading to incorrect retrieval results. To address this problem, we propose the Entity Visual Description enhanced CLIP (EvdCLIP), designed to leverage the visual knowledge of entities to enrich queries. Specifically, since humans recognize entities through visual cues, we employ a large language model (LLM) to generate Entity Visual Descriptions (EVDs) as alignment cues to complement textual data. These EVDs are then integrated into raw queries to create visually-rich, EVD-enhanced queries. Furthermore, recognizing that EVD-enhanced queries may introduce noise or low-quality expansions, we develop a novel, trainable EVD-aware Rewriter (EaRW) for vision-language retrieval tasks. EaRW utilizes EVD knowledge and the generative capabilities of the language model to effectively rewrite queries. With our specialized training strategy, EaRW can generate high-quality and low-noise EVD-enhanced queries. Extensive quantitative and qualitative experiments on image-text retrieval benchmarks validate the superiority of EvdCLIP on vision-language retrieval tasks.

Minghui Fang, Shengpeng Ji, Jialong Zuo, Hai Huang, Yan Xia, Jieming Zhu, Xize Cheng, Xiaoda Yang, Wenrui Liu, Gang Wang, Zhenhua Dong, Zhou Zhao. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

We introduce a novel, training-free approach for enhancing alignment in Transformer-based Text-Guided Diffusion Models (TGDMs). Existing TGDMs often struggle to generate semantically aligned images, particularly when dealing with complex text prompts or multi-concept attribute binding challenges. Previous U-Net-based methods primarily optimized the latent space, but their direct application to Transformer-based architectures has shown limited effectiveness. Our method addresses these challenges by directly optimizing cross-attention maps during the generation process. Specifically, we introduce Self-Coherence Guidance, a method that dynamically refines attention maps using masks derived from previous denoising steps, ensuring precise alignment without additional training. To validate our approach, we constructed more challenging benchmarks for evaluating coarse-grained attribute binding, fine-grained attribute binding, and style binding. Experimental results demonstrate the superior performance of our method, significantly surpassing other state-of-the-art methods across all evaluated tasks. Our code is available at https://scg-diffusion.github.io/scg-diffusion.

Zhipeng Bian, Jieming Zhu, Qijiong Liu, Wang Lin, Guohao Cai, Zhaocheng Du, Jiacheng Sun, Zhou Zhao, Zhenhua Dong. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Sashuai Zhou, Weinan Gan, Qijiong Liu, Ke Lei, Jieming Zhu, Hai Huang, Yan Xia, Ruiming Tang, Zhenhua Dong, Zhou Zhao. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

With the rapid development of recommendation models and device computing power, device-based recommendation has become an important research area due to its better real-time performance and privacy protection. Previously, Transformer-based sequential recommendation models have been widely applied in this field because they outperform Recurrent Neural Network (RNN)-based recommendation models in terms of performance. However, as the length of interaction sequences increases, Transformer-based models introduce significantly more space and computational overhead compared to RNN-based models, posing challenges for device-based recommendation. To balance real-time performance and high performance on devices, we propose Device-Cloud Collaborative Correction Framework for On-Device Recommendation (CoCorrRec). CoCorrRec uses a self-correction network (SCN) to correct parameters with extremely low time cost. By updating model parameters during testing based on the input token, it achieves performance comparable to current optimal but more complex Transformer-based models. Furthermore, to prevent SCN from overfitting, we design a global correction network (GCN) that processes hidden states uploaded from devices and provides a global correction solution. Extensive experiments on multiple datasets show that CoCorrRec outperforms existing Transformer-based and RNN-based device recommendation models in terms of performance, with fewer parameters and lower FLOPs, thereby achieving a balance between real-time performance and high efficiency. Code is available at https: //github.com/Yuzt-zju/CoCorrRec.

Sequential recommendation (SR) aims to capture dynamic user preferences from users' historical behaviors. Recently, benefiting from astonishing understanding ability of pre-trained language models (PLMs), text-enhanced sequential recommender becomes a promising direction, which employs PLMs to extract semantic information for user/item representation. Although promising in improving performance and transferability, few existing text-enhanced SR studies have analyzed the differences between PLMs and recommenders, restricting the ability of PLMs for recommendation. In this paper, we make an in-depth comparison and conclude their discrepancies in representation and knowledge level, respectively, caused by different multi-modal content and task-oriented capabilities. Based on this, we propose a Recommendation-Oriented Language Model Adaptation framework (named ROMA) using multi-modal multi-domain item sequences. To empower PLMs with a rational understanding of user/item modeling and the recommendation task, ROMA partitions a PLM into bottom and top layers, respectively, allowing representation-level and task-level adaptation with elaborately designed architectures, transferring strategy and learning framework. Our experimental results on public benchmarks demonstrate the effectiveness and transferability of our framework. Additionally, we showcase the application value of ROMA on the recommender system of Huawei's AppGallery through online A/B testing, which shows significant improvements in online metrics.

Graph neural networks (GNNs) have emerged as state-of-the-art methods to learn from graph-structured data for recommendation. However, most existing GNN-based recommendation methods focus on the optimization of model structures and learning strategies based on pre-defined graphs, neglecting the importance of the graph construction stage. Earlier works for graph construction usually rely on specific rules or crowdsourcing, which are either too simplistic or too labor-intensive. Recent works start to utilize large language models (LLMs) to automate the graph construction, in view of their abundant open-world knowledge and remarkable reasoning capabilities. Nevertheless, they generally suffer from two limitations: (1) invisibility of global view (e.g., overlooking contextual information) and (2) construction inefficiency. To this end, we introduce AutoGraph, an automatic graph construction framework based on LLMs for recommendation. Specifically, we first use LLMs to infer the user preference and item knowledge, which is encoded as semantic vectors. Next, we employ vector quantization to extract the latent factors from the semantic vectors. The latent factors are then incorporated as extra nodes to link the user/item nodes, resulting in a graph with in-depth global-view semantics. We further design metapath-based message aggregation to effectively aggregate the semantic and collaborative information. The framework is model-agnostic and compatible with different backbone models. Extensive experiments on three real-world datasets demonstrate the efficacy and efficiency of AutoGraph compared to existing baseline methods. We have deployed AutoGraph in Huawei advertising platform, and gain a 2.69% improvement on RPM and a 7.31% improvement on eCPM in the online A/B test. Currently AutoGraph has been used as the main traffic model, serving hundreds of millions of people.

Feature interaction modeling is crucial for deep recommendation models. A common and effective approach is to construct explicit feature combinations to enhance model performance. However, in practice, only a small fraction of these combinations are truly informative. Thus it is essential to select useful feature combinations to reduce noise and manage memory consumption. While feature selection methods have been extensively studied, they are typically limited to selecting individual features. Extending these methods for high-order feature combination selection presents a significant challenge due to the exponential growth in time complexity when evaluating feature combinations one by one. In this paper, we propose TayFCS, a lightweight feature combination selection method that significantly improves model performance. Specifically, we propose the Taylor Expansion Scorer (TayScorer) module for field-wise Taylor expansion on the base model. Instead of evaluating all potential feature combinations' importance by repeatedly running experiments with feature adding and removal, this scorer only needs to approximate them based on their sub-components' gradients. They can be simply computed with one backward pass based on a trained recommendation model. To further reduce information redundancy between feature combinations and their sub-components, we introduce Logistic Regression Elimination (LRE) that estimates the information gain of feature combinations over their sub-components based on the above importance scores. Experimental results on three benchmark datasets validate both the effectiveness and efficiency of our approach. Furthermore, online A/B test results demonstrate its practical applicability and commercial value.

With the advancement of mobile device capabilities, deploying reranking models directly on devices has become feasible, enabling real-time contextual recommendations. When migrating models from cloud to devices, resource heterogeneity inevitably necessitates model compression. Recent quantization methods show promise for efficient deployment, yet they overlook device-specific user interests, resulting in compromised recommendation accuracy. While on-device finetuning captures personalized user preference, it imposes additional computational burden through local retraining. To address these challenges, we propose a framework for \underline{\textbf{C}}ustomizing \underline{\textbf{H}}ybrid-precision \underline{\textbf{O}}n-device model for sequential \underline{\textbf{R}}ecommendation with \underline{\textbf{D}}evice-cloud collaboration (\textbf{CHORD}), leveraging channel-wise mixed-precision quantization to simultaneously achieve personalization and resource-adaptive deployment. CHORD distributes randomly initialized models across heterogeneous devices and identifies user-specific critical parameters through auxiliary hypernetwork modules on the cloud. Our parameter sensitivity analysis operates across multiple granularities (layer, filter, and element levels), enabling precise mapping from user profiles to quantization strategy. Through on-device mixed-precision quantization, CHORD delivers dynamic model adaptation and accelerated inference without backpropagation, eliminating costly retraining cycles. We minimize communication overhead by encoding quantization strategies using only 2 bits per channel instead of 32-bit weights. Experiments on three real-world datasets with two popular backbones (SASRec and Caser) demonstrate the accuracy, efficiency, and adaptivity of CHORD.

Integrating large language models (LLMs) into recommender systems has created new opportunities for improving recommendation quality. However, a comprehensive benchmark is needed to thoroughly evaluate and compare the recommendation capabilities of LLMs with traditional recommender systems. In this paper, we introduce \recbench{}, which systematically investigates various item representation forms (including unique identifier, text, semantic embedding, and semantic identifier) and evaluates two primary recommendation tasks, i.e., click-through rate prediction (CTR) and sequential recommendation (SeqRec). Our extensive experiments cover up to 17 large models and are conducted across five diverse datasets from fashion, news, video, books, and music domains. Our findings indicate that LLM-based recommenders outperform conventional recommenders, achieving up to a 5% AUC improvement in CTR and up to a 170% NDCG@10 improvement in SeqRec. However, these substantial performance gains come at the expense of significantly reduced inference efficiency, rendering LLMs impractical as real-time recommenders. We have released our code and data to enable other researchers to reproduce and build upon our experimental results.

With the rapid progress of large language models (LLMs) and diffusion models, there has been growing interest in personalized content generation. However, current conversational systems often present the same recommended content to all users, falling into the dilemma of "one-size-fits-all." To break this limitation and boost user engagement, in this paper, we introduce PCG (**P**ersonalized Visual **C**ontent **G**eneration), a unified framework for personalizing item images within conversational systems. We tackle two key bottlenecks: the depth of personalization and the fidelity of generated images. Specifically, an LLM-powered Inclinations Analyzer is adopted to capture user likes and dislikes from context to construct personalized prompts. Moreover, we design a dual-stage LoRA mechanism—Global LoRA for understanding task-specific visual style, and Local LoRA for capturing preferred visual elements from conversation history. During training, we introduce the visual content condition method to ensure LoRA learns both historical visual context and maintains fidelity to the original item images. Extensive experiments on benchmark conversational datasets—including objective metrics and GPT-based evaluations—demonstrate that our framework outperforms strong baselines, which highlight its potential to redefine personalization in visual content generation for conversational scenarios like e-commerce and real-world recommendation.

LLM-based agents have been widely applied as personal assistants, capable of memorizing information from user messages and responding to personal queries. However, there still lacks an objective and automatic evaluation on their memory capability, largely due to the challenges in constructing reliable questions and answers (QAs) according to user messages. In this paper, we propose MemSim, a Bayesian simulator designed to automatically construct reliable QAs from generated user messages, simultaneously keeping their diversity and scalability. Specifically, we introduce the Bayesian Relation Network (BRNet) and a causal generation mechanism to mitigate the impact of LLM hallucinations on factual information, facilitating the automatic creation of an evaluation dataset. Based on MemSim, we generate a dataset in the daily-life scenario, named MemDaily, and conduct extensive experiments to assess the effectiveness of our approach. We also provide a benchmark for evaluating different memory mechanisms in LLM-based agents with the MemDaily dataset.

Unsupervised domain adaptation (UDA) for visual question answering (VQA) has attracted research interest. However, with Multi-modal Large Language Models (MLLMs) showing great performance on VQA datasets, UDA for VQA based on MLLMs remains unexplored. To fill this gap, we propose the first systematic approach to Unsupervised Domain Adaptation VQA based on MLLMs (UDAM). First, we introduce semantic context feature alignment and domain query feature alignment, which utilize a single token embedding for each modality to capture contextual domain information from unimodal inputs and conduct coarsegrained feature alignment on it, thus alleviating domain shifts in the unimodal feature space. Second, we propose the novel semantics-guided query feature alignment, which differentiates important domain-specific queries from learnable query outputs and conducts fine-grained feature alignment controlled by a semantics-guided weight map to reduce domain shifts in the cross-modal feature space. Third, we devise a pair-wise domain-aware prompt strategy, which aids UDA by prompting MLLMs to discern the commonality of tasks and the distinctiveness of domains in multi-modal inputs. Extensive experiments demonstrate UDAM's effectiveness in adapting MLLMs to unlabeled new domains.

In online advertising, uncertainty calibration aims to adjust a ranking model's probability predictions to better approximate the true likelihood of an event, e.g., a click or a conversion. However, existing calibration approaches may lack the ability to effectively model complex nonlinear relations, consider context features, and achieve balanced performance across different data subsets. To tackle these challenges, we introduce a novel model called Monotonic Calibration Networks, featuring three key designs: a monotonic calibration function (MCF), an order-preserving regularizer, and a field-balance regularizer. The nonlinear MCF is capable of naturally modeling and universally approximating the intricate relations between uncalibrated predictions and the posterior probabilities, thus being much more expressive than existing methods. MCF can also integrate context features using a flexible model architecture, thereby achieving context awareness. The order-preserving and field-balance regularizers promote the monotonic relationship between adjacent bins and the balanced calibration performance on data subsets, respectively. Experimental results on both public and industrial datasets demonstrate the superior performance of our method in generating well-calibrated probability predictions.

Large language models (LLMs) are increasingly leveraged as foundational backbones in the development of advanced recommender systems, offering enhanced capabilities through their extensive knowledge and reasoning.Existing llm-based recommender systems (RSs) often face challenges due to the significant differences between the linguistic semantics of pre-trained LLMs and the collaborative semantics essential for RSs.These systems use pre-trained linguistic semantics but learn collaborative semantics from scratch via the llm-Backbone.However, LLMs are not designed for recommendations, leading to inefficient collaborative learning, weak result correlations, and poor integration of traditional RS features.To address these challenges, we propose EAGER-LLM, a decoder-only llm-based generative recommendation framework that integrates endogenous and exogenous behavioral and semantic information in a non-intrusive manner.Specifically, we propose 1) dual-source knowledge-rich item indices that integrates indexing sequences * Both authors contributed equally to this research.

Large language model (LLM)-based agents have recently attracted much attention from the research and industry communities. Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems that need long-term and complex agent-environment interactions. The key component to support agent-environment interactions is the memory of the agents. While previous studies have proposed many promising memory mechanisms, they are scattered in different papers, and there lacks a systematical review to summarize and compare these works from a holistic perspective, failing to abstract common and effective designing patterns for inspiring future studies. To bridge this gap, in this article, we propose a comprehensive survey on the memory mechanism of LLM-based agents. In specific, we first discuss “what is” and “why do we need” the memory in LLM-based agents. Then, we systematically review previous studies on how to design and evaluate the memory module. In addition, we also present many agent applications, where the memory module plays an important role. At last, we analyze the limitations of existing work and show important future directions. To keep up with the latest advances in this field, we create a repository at https://github.com/nuster1128/LLM_Agent_Memory_Survey .

Learning high-quality item embeddings is crucial for recommendation tasks such as matching and ranking. However, existing methods often rely on ID-based item embeddings learned end-to-end with downstream recommendation models, which may suffer from overfitting and limited generalizability. In this paper, we aim to learn universal item embeddings (dubbed UniEmbedding) that capture multi-modal semantics, generalize across multiple domains, and serve different downstream tasks. To achieve this goal, we introduce the UniEmbedding pretraining framework, which includes three modules: a domain-aware multi-modal adapter, a user-view projection module, and contrastive learning objectives across domains. Compared to naive ID embeddings, UniEmbedding provides rich semantic information that generalizes more effectively across domains. Unlike multi-modal embeddings directly extracted from off-the-shelf pretrained models, UniEmbedding achieves better alignment between content semantics and behaviors. We evaluated UniEmbedding on both public and industrial datasets, demonstrating its effectiveness in matching and ranking tasks. Furthermore, UniEmbedding has been deployed in multiple recommendation applications at Huawei, resulting in significant gains in user engagement metrics.

Recent studies highlight the potential of large language models (LLMs) to enhance content integration in recommender systems by leveraging their semantic understanding capabilities. However, directly incorporating LLMs into an online inference pipeline significantly increases computation costs for large-scale deployment, posing a practical challenge in balancing their benefits and costs. In this work, we propose the EASE framework, which enriches and aligns semantic feature embeddings using LLMs during the training phase while establishing a lightweight inference pipeline that does not directly involve LLMs. Specifically, we train a semantic adapter to align item features with LLMs and simultaneously enrich semantic embeddings through reconstruction tasks from LLMs. During inference, we retain only the item feature encoder and lightweight semantic adapter, thereby eliminating the computation overhead of resource-intensive LLMs. Our EASE framework is flexible, supporting not only text and visual features but also other pre-processed embedding features. Extensive experiments on both public and industrial datasets demonstrate that enriching semantic feature embeddings with our EASE framework yields consistent improvements in downstream click-through rate prediction tasks.

With the popularity of online music services, personalized music recommendation has garnered much research interest. Recommendation models are typically trained on datasets constructed from user feedback, which includes both the active feedback (e.g., clicking the Like or Skip buttons) and passive feedback (e.g., auto-play), with passive feedback comprising the majority. Due to the unavailability of user attention, the massive amount of passive feedback is unreliable, significantly compromising the quality of the training data. How to estimate the user's attention on the target music has become a critical problem in music recommendation. Heuristic methods such as exponential decay and negative sampling have been proposed. However, they either neglect the sequential dependencies between feedback actions or utilize only a small fraction of passive samples, leading to inaccurate and biased attention estimation. In this paper, we naturally propose modeling user attention prediction as a positive-unlabeled (PU) learning problem, where active feedback is treated as positive samples and passive feedback is treated as unlabeled samples, as we can only ensure that the user's attention is focused when she provides active feedback. Then we propose an extended PU-learning model with sequential dependencies, called UAE, which contains an unbiased user attention estimator and an unbiased propensity estimator. Subsequently, a joint learning algorithm is developed in which the attention and propensity estimators are optimized in alternating fashion. Theoretical analysis shows the unbiasedness and variance of the attention estimator and the propensity estimator. Extensive experiments on two large-scale datasets demonstrate the proposed UAE's effectiveness and generality in enhancing downstream music recommendation. One week online A/B testing on Huawei Music App manifests that UAE can significantly increase the users' play count and time over 2%, further demonstrating the effectiveness of UAE in real-world music recommendation products.

Log data have facilitated various tasks of software development and maintenance, such as testing, debugging and diagnosing. Due to the unstructured nature of logs, log parsing is typically required to transform log messages into structured data for automated log analysis. Given the abundance of log parsers that employ various techniques, evaluating these tools to comprehend their characteristics and performance becomes imperative. Loghub serves as a commonly used dataset for benchmarking log parsers, but it suffers from limited scale and representativeness, posing significant challenges for studies to comprehensively evaluate existing log parsers or develop new methods. This limitation is particularly pronounced when assessing these log parsers for production use. To address these limitations, we provide a new collection of annotated log datasets, denoted Loghub-2.0, which can better reflect the characteristics of log data in real-world software systems. Loghub-2.0 comprises 14 datasets with an average of 3.6 million log lines in each dataset. Based on Loghub-2.0, we conduct a thorough re-evaluation of 15 state-of-the-art log parsers in a more rigorous and practical setting. Particularly, we introduce a new evaluation metric to mitigate the sensitivity of existing metrics to imbalanced data distributions. We are also the first to investigate the granular performance of log parsers on logs that represent rare system events, offering in-depth details for software diagnosis. Accurately parsing such logs is essential, yet it remains a challenge. We believe this work could shed light on the evaluation and design of log parsers in practical settings, thereby facilitating their deployment in production systems.

Personalized recommendation serves as a ubiquitous channel for users to discover information tailored to their interests. However, traditional recommendation models primarily rely on unique IDs and categorical features for user-item matching, potentially overlooking the nuanced essence of raw item contents across multiple modalities such as text, image, audio, and video. This underutilization of multimodal data poses a limitation to recommender systems, especially in multimedia services like news, music, and short-video platforms. The recent advancements in large multimodal models offer new opportunities and challenges in developing content-aware recommender systems. This survey seeks to provide a comprehensive exploration of the latest advancements and future trajectories in multimodal pretraining, adaptation, and generation techniques, as well as their applications in enhancing recommender systems. Furthermore, we discuss current open challenges and opportunities for future research in this dynamic domain. We believe that this survey, alongside the curated resources, will provide valuable insights to inspire further advancements in this evolving landscape.

Generative retrieval has recently emerged as a promising approach to sequential recommendation, framing candidate item retrieval as an autoregressive sequence generation problem. However, existing generative methods typically focus solely on either behavioral or semantic aspects of item information, neglecting their complementary nature and thus resulting in limited effectiveness. To address this limitation, we introduce EAGER, a novel generative recommendation framework that seamlessly integrates both behavioral and semantic information. Specifically, we identify three key challenges in combining these two types of information: a unified generative architecture capable of handling two feature types, ensuring sufficient and independent learning for each type, and fostering subtle interactions that enhance collaborative information utilization. To achieve these goals, we propose (1) a two-stream generation architecture leveraging a shared encoder and two separate decoders to decode behavior tokens and semantic tokens with a confidence-based ranking strategy; (2) a global contrastive task with summary tokens to achieve discriminative decoding for each type of information; and (3) a semantic-guided transfer task designed to implicitly promote cross-interactions through reconstruction and estimation objectives. We validate the effectiveness of EAGER on four public benchmarks, demonstrating its superior performance compared to existing methods. Our source code will be publicly available on PapersWithCode.com.

In video recommendation, an ongoing effort is to satisfy users' personalized information needs by leveraging their logged watch time. However, watch time prediction suffers from duration bias, hindering its ability to reflect users' interests accurately. Existing label-correction approaches attempt to uncover user interests through grouping and normalizing observed watch time according to video duration. Although effective to some extent, we found that these approaches regard completely played records (i.e., a user watches the entire video) as equally high interest, which deviates from what we observed on real datasets: users have varied explicit feedback proportion when completely playing videos. In this paper, we introduce the counterfactual watch time (CWT), the potential watch time a user would spend on the video if its duration is sufficiently long. Analysis shows that the duration bias is caused by the truncation of CWT due to the video duration limitation, which usually occurs on those completely played records. Besides, a Counterfactual Watch Model (CWM) is proposed, revealing that CWT equals the time users get the maximum benefit from video recommender systems. Moreover, a cost-based transform function is defined to transform the CWT into the estimation of user interest, and the model can be learned by optimizing a counterfactual likelihood function defined over observed user watch times. Extensive experiments on three real video recommendation datasets and online A/B testing demonstrated that CWM effectively enhanced video recommendation accuracy and counteracted the duration bias.

Data-driven techniques have greatly empowered recommender systems in different scenarios. However, many mainstream algorithms rely on black-box models, making them difficult to interpret, debug, and evolve. Therefore, effectively and efficiently interpreting the behaviors and impacts of features in different stages of recommendation pipelines is essential in industrial recommender systems to master a clear picture of the features they use and bring new insights to system improvement and product design. In this tutorial, we present a systematic overview of feature interpretation technologies in the recommendation field from various aspects including algorithms, applications, and challenges. We first provide a systematic taxonomy of previous feature interpretation methods based on their interpretation perspectives, then introduce the experience and lessons of feature interpretation in large-scale and real-time industrial recommender systems. Finally, we summarize several remaining theoretical and practical challenges in feature interpretation and present corresponding future directions to help feature interpretation better empower recommender systems. From this tutorial, the RecSys community can obtain insights into the methodology and real-world applications of feature interpretation to make more transparent, targeted, and intelligent system optimization.

Recommender system plays a vital role in various online services. However, its insulated nature of training and deploying separately within a specific closed domain limits its access to open-world knowledge. Recently, the emergence of large language models (LLMs) has shown promise in bridging this gap by encoding extensive world knowledge and demonstrating reasoning capabilities. Nevertheless, previous attempts to directly use LLMs as recommenders cannot meet the inference latency demand of industrial recommender systems. In this work, we propose an Open-World Knowledge Augmented Recommendation Framework with Large Language Models, dubbed KAR, to acquire two types of external knowledge from LLMs — the reasoning knowledge on user preferences and the factual knowledge on items. We introduce factorization prompting to elicit accurate reasoning on user preferences. The generated reasoning and factual knowledge are effectively transformed and condensed into augmented vectors by a hybrid-expert adaptor in order to be compatible with the recommendation task. The obtained vectors can then be directly used to enhance the performance of any recommendation model. We also ensure efficient inference by preprocessing and prestoring the knowledge from the LLM. Extensive experiments show that KAR significantly outperforms the state-of-the-art baselines and is compatible with a wide range of recommendation algorithms. We deploy KAR to Huawei’s news and music recommendation platforms and gain a 7% and 1.7% improvement in the online A/B test, respectively.

Embedding-based retrieval serves as a dominant approach to candidate item matching for industrial recommender systems. With the success of generative AI, generative retrieval has recently emerged as a new retrieval paradigm for recommendation, which casts item retrieval as a generation problem. Its model consists of two stages: semantic tokenization and autoregressive generation. The first stage involves item tokenization that constructs discrete semantic tokens to index items, while the second stage autoregressively generates semantic tokens of candidate items. Therefore, semantic tokenization serves as a crucial preliminary step for training generative recommendation models. Existing research usually employs a vector quantizier with reconstruction loss (e.g., RQ-VAE) to obtain semantic tokens of items, but this method fails to capture the essential neighborhood relationships that are vital for effective item modeling in recommender systems. In this paper, we propose a contrastive quantization-based semantic tokenization approach, named CoST, which harnesses both item relationships and semantic information to learn semantic tokens. Our experimental results highlight the significant impact of semantic tokenization on generative recommendation performance, with CoST achieving up to a 43% improvement in Recall@5 and 44% improvement in NDCG@5 on the MIND dataset over previous baselines.

Category information plays a crucial role in enhancing the quality and personalization of recommender systems. Nevertheless, the availability of item category information is not consistently present, particularly in the context of ID-based recommendations. In this work, we propose a novel approach to automatically learn and generate entity (i.e., user or item) category trees for ID-based recommendation. Specifically, we devise a differentiable vector quantization framework for automatic category tree generation, namely CAGE, which enables the simultaneous learning and refinement of categorical code representations and entity embeddings in an end-to-end manner, starting from the randomly initialized states. With its high adaptability, CAGE can be easily integrated into both sequential and non-sequential recommender systems. We validate the effectiveness of CAGE on various recommendation tasks including list completion, collaborative filtering, and click-through rate prediction, across different recommendation models. We release the code and data for others to reproduce the reported results.

The emergence of large language models (LLMs) has revolutionized the capabilities of text comprehension and generation. Multi-modal generation attracts great attention from both the industry and academia, but there is little work on personalized generation, which has important applications such as recommender systems. This paper proposes the first method for personalized multimodal generation using LLMs, showcases its applications and validates its performance via an extensive experimental study on two datasets. The proposed method, Personalized Multimodal Generation (PMG for short) first converts user behaviors (e.g., clicks in recommender systems or conversations with a virtual assistant) into natural language to facilitate LLM understanding and extract user preference descriptions. Such user preferences are then fed into a generator, such as a multimodal LLM or diffusion model, to produce personalized content. To capture user preferences comprehensively and accurately, we propose to let the LLM output a combination of explicit keywords and implicit embeddings to represent user preferences. Then the combination of keywords and embeddings are used as prompts to condition the generator. We optimize a weighted sum of the accuracy and preference scores so that the generated content has a good balance between them. Compared to a baseline method without personalization, PMG has a significant improvement on personalization for up to 8% in terms of LPIPS while retaining the accuracy of generation.

Click-through rate (CTR) prediction is one of the fundamental tasks in online advertising and recommendation. Multi-layer perceptron (MLP) serves as a core component in many deep CTR prediction models, but it has been widely shown that applying a vanilla MLP network alone is ineffective in learning complex feature interactions. As such, many two-stream models (e.g., Wide&Deep, DeepFM, and DCN) have recently been proposed, aiming to integrate two parallel sub-networks to learn feature interactions from two different views for enhanced CTR prediction. In addition to one MLP stream that learns feature interactions implicitly, most of the existing research focuses on designing another stream to complement the MLP stream with explicitly enhanced feature interactions. Instead, this paper presents a simple two-stream feature interaction model, namely FinalMLP, which employs only MLPs in both streams yet achieves surprisingly strong performance. In contrast to sophisticated network design in each stream, our work enhances CTR modeling through a feature selection module, which produces differentiated feature inputs to two streams, and a group-wise bilinear fusion module, which effectively captures stream-level interactions across two streams. We show that FinalMLP achieves competitive or even better performance against many existing two-stream CTR models on four open benchmark datasets and also brings significant CTR improvements during an online A/B test in our industrial news recommender system. We envision that the simple yet effective FinalMLP model could serve as a new strong baseline for future development of two-stream CTR models. Our source code will be available at MindSpore/models and FuxiCTR/model_zoo.

Logs have been widely adopted in software system development and maintenance because of the rich runtime information they record. In recent years, the increase of software size and complexity leads to the rapid growth of the volume of logs. To handle these large volumes of logs efficiently and effectively, a line of research focuses on developing intelligent and automated log analysis techniques. However, only a few of these techniques have reached successful deployments in industry due to the lack of public log datasets and open benchmarking upon them. To fill this significant gap and facilitate more research on AI-driven log analytics, we have collected and released loghub, a large collection of system log datasets. In particular, loghub provides 19 real-world log datasets collected from a wide range of software systems, including distributed systems, supercomputers, operating systems, mobile systems, server applications, and standalone software. In this paper, we summarize the statistics of these datasets, introduce some practical usage scenarios of the loghub datasets, and present our benchmarking results on loghub to benefit the researchers and practitioners in this field. Up to the time of this paper writing, the loghub datasets have been downloaded for roughly 90,000 times in total by hundreds of organizations from both industry and academia. The loghub datasets are available at https://github.com/logpai/loghub.

Industrial recommender systems face the challenge of operating in non-stationary environments, where data distribution shifts arise from evolving user behaviors over time. To tackle this challenge, a common approach is to periodically re-train or incrementally update deployed deep models with newly observed data, resulting in a continual learning process. However, the conventional learning paradigm of neural networks relies on iterative gradient-based updates with a small learning rate, making it slow for large recommendation models to adapt. In this paper, we introduce ReLoop2, a self-correcting learning loop that facilitates fast model adaptation in online recommender systems through responsive error compensation. Inspired by the slow-fast complementary learning system observed in human brains, we propose an error memory module that directly stores error samples from incoming data streams. These stored samples are subsequently leveraged to compensate for model prediction errors during testing, particularly under distribution shifts. The error memory module is designed with fast access capabilities and undergoes continual refreshing with newly observed data samples during the model serving phase to support fast model adaptation. We evaluate the effectiveness of ReLoop2 on three open benchmark datasets as well as a real-world production dataset. The results demonstrate the potential of ReLoop2 in enhancing the responsiveness and adaptiveness of recommender systems operating in non-stationary environments.

In recent years, the deployment of large-scale pre-trained models in audio-visual downstream tasks has yielded remarkable outcomes. However, these models, primarily trained on single-modality unconstrained datasets, still encounter challenges in feature extraction for multi-modal tasks, leading to suboptimal performance. This limitation arises due to the introduction of irrelevant modality-specific information during encoding, which adversely affects the performance of downstream tasks. To address this challenge, this paper proposes a novel Dual-Guided Spatial-Channel-Temporal (DG-SCT) attention mechanism. This mechanism leverages audio and visual modalities as soft prompts to dynamically adjust the parameters of pre-trained models based on the current multi-modal input features. Specifically, the DG-SCT module incorporates trainable cross-modal interaction layers into pre-trained audio-visual encoders, allowing adaptive extraction of crucial information from the current modality across spatial, channel, and temporal dimensions, while preserving the frozen parameters of large-scale pre-trained models. Experimental evaluations demonstrate that our proposed model achieves state-of-the-art results across multiple downstream tasks, including AVE, AVVP, AVS, and AVQA. Furthermore, our model exhibits promising performance in challenging few-shot and zero-shot scenarios. The source code and pre-trained models are available at https://github.com/haoyi-duan/DG-SCT.

This paper introduces a novel task called Cross Modal Generalization (CMG), which addresses the challenge of learning a unified discrete representation from paired multimodal data during pre-training. Then in downstream tasks, the model can achieve zero-shot generalization ability in other modalities when only one modal is labeled. Existing approaches in multimodal representation learning focus more on coarse-grained alignment or rely on the assumption that information from different modalities is completely aligned, which is impractical in real-world scenarios. To overcome this limitation, we propose \textbf{Uni-Code}, which contains two key contributions: the Dual Cross-modal Information Disentangling (DCID) module and the Multi-Modal Exponential Moving Average (MM-EMA). These methods facilitate bidirectional supervision between modalities and align semantically equivalent information in a shared discrete latent space, enabling fine-grained unified representation of multimodal sequences. During pre-training, we investigate various modality combinations, including audio-visual, audio-text, and the tri-modal combination of audio-visual-text. Extensive experiments on various downstream tasks, i.e., cross-modal event classification, localization, cross-modal retrieval, query-based video segmentation, and cross-dataset event localization, demonstrate the effectiveness of our proposed methods. The code is available at https://github.com/haihuangcode/CMG.

A common practice to keep the freshness of an offline Recommender System (RS) is to train models that fit the user’s most recent behaviour while directly replacing the outdated historical model. However, many feature engineering and computing resources are used to train these historical models, but they are underutilized in the downstream RS model training. In this paper, to turn these historical models into treasures, we introduce a model inversed data synthesis framework, which can recover training data information from the historical model and use it for knowledge transfer. This framework synthesizes a new form of data from the historical model. Specifically, we ’invert’ an off-the-shield pretrained model to synthesize binary class user-item pairs beginning from random noise without requiring any additional information from the training dataset. To synthesize informative data from a pretrained model, we propose a new continuous data type rather than the original one- or multi-hot vectors. An additional statistical regularization is added to further improve the quality of the synthetic data inverted from the deep model with batch normalization. The experimental results show that our framework can generalize across different types of models. We can efficiently train different types of classical Click-Through-Rate (CTR) prediction models from scratch with significantly few inversed synthetic data (2 orders of magnitude). Moreover, our framework can also work well in the knowledge transfer scenarios such as model retraining and data-free knowledge distillation.

Two-tower models are a prevalent matching framework for recommendation, which have been widely deployed in industrial applications. The success of two-tower matching attributes to its efficiency in retrieval among a large number of items, since the item tower can be precomputed and used for fast Approximate Nearest Neighbor (ANN) search. However, it suffers two main challenges, including limited feature interaction capability and reduced accuracy in online serving. Existing approaches attempt to design novel late interactions instead of dot products, but they still fail to support complex feature interactions or lose retrieval efficiency. To address these challenges, we propose a new matching paradigm named SparCode, which supports not only sophisticated feature interactions but also efficient retrieval. Specifically, SparCode introduces an all-to-all interaction module to model fine-grained query-item interactions. Besides, we design a discrete code-based sparse inverted index jointly trained with the model to achieve effective and efficient model inference. Extensive experiments have been conducted on open benchmark datasets to demonstrate the superiority of our framework. The results show that SparCode significantly improves the accuracy of candidate item matching while retaining the same level of retrieval efficiency with two-tower models.

In the field of music information retrieval (MIR), cover song identification (CSI) is a challenging task that aims to identify cover versions of a query song from a massive collection. Existing works still suffer from high intra-song variances and inter-song correlations, due to the entangled nature of version-specific and version-invariant factors in their modeling. In this work, we set the goal of disentangling version-specific and version-invariant factors, which could make it easier for the model to learn invariant music representations for unseen query songs. We analyze the CSI task in a disentanglement view with the causal graph technique, and identify the intra-version and inter-version effects biasing the invariant learning. To block these effects, we propose the disentangled music representation learning framework (DisCover) for CSI. DisCover consists of two critical components: (1) Knowledge-guided Disentanglement Module (KDM) and (2) Gradient-based Adversarial Disentanglement Module (GADM), which block intra-version and inter-version biased effects, respectively. KDM minimizes the mutual information between the learned representations and version-variant factors that are identified with prior domain knowledge. GADM identifies version-variant factors by simulating the representation transitions between intra-song versions, and exploits adversarial distillation for effect blocking. Extensive comparisons with best-performing methods and in-depth analysis demonstrate the effectiveness of DisCover and the and necessity of disentanglement for CSI.

Multi-layer perceptron (MLP) serves as a core component in many deep models for click-through rate (CTR) prediction. However, vanilla MLP networks are inefficient in learning multiplicative feature interactions, making feature interaction learning an essential topic for CTR prediction. Existing feature interaction networks are effective in complementing the learning of MLPs, but they often fall short of the performance of MLPs when applied alone. Thus, their integration with MLP networks is necessary to achieve improved performance. This situation motivates us to explore a better alternative to the MLP backbone that could potentially replace MLPs. Inspired by factorization machines, in this paper, we propose FINAL, a factorized interaction layer that extends the widely-used linear layer and is capable of learning 2nd-order feature interactions. Similar to MLPs, multiple FINAL layers can be stacked into a FINAL block, yielding feature interactions with an exponential degree growth. We unify feature interactions and MLPs into a single FINAL block and empirically show its effectiveness as a replacement for the MLP block. Furthermore, we explore the ensemble of two FINAL blocks as an enhanced two-stream CTR model, setting a new state-of-the-art on open benchmark datasets. FINAL can be easily adopted as a building block and has achieved business metric gains in multiple applications at Huawei. Our source code will be made available at MindSpore/models and FuxiCTR/model_zoo.

User-curated item lists, such as video-based playlists on Youtube and book-based lists on Goodreads, have become prevalent for content sharing on online platforms. Item list continuation is proposed to model the overall trend of a list and predict subsequent items. Recently, Transformer-based models have shown promise in comprehending contextual information and capturing item relationships in a list. However, deploying them in real-time industrial applications is challenging, mainly because the autoregressive generation mechanism used in them is time-consuming. In this paper, we propose a novel fast non-autoregressive sequence generation model, namely FANS, to enhance inference efficiency and quality for item list continuation. First, we use a non-autoregressive generation mechanism to decode next K items simultaneously instead of one by one in existing models. Then, we design a two-stage classifier to replace the vanilla classifier used in current transformer-based models to further reduce the decoding time. Moreover, to improve the quality of non-autoregressive generation, we employ a curriculum learning strategy to optimize training. Experimental results on four real-world item list continuation datasets including Zhihu, Spotify, AotM, and Goodreads show that our FANS model can significantly improve inference efficiency (up to 8.7x) while achieving competitive or better generation quality for item list continuation compared with the state-of-the-art autoregressive models. We also validate the efficiency of FANS in an industrial setting. Our source code and data will be available at MindSpore/models1 and Github2.

Music recommendation is usually modeled as a Click-Through Rate (CTR) prediction problem, which estimates the probability of a user listening a recommended song. CTR prediction can be formulated as a binary classification problem where the played songs are labeled as positive samples and the skipped songs are labeled as negative samples. However, such naively defined labels are noisy and biased in practice, causing inaccurate model predictions. In this work, we first identify serious label noise issues in an industrial music App, and then propose an adaptive Label Correction method for Denoising (LCD) music recommendation by ensembling the noisy labels and the model outputs to encourage a consensus prediction. Extensive offline experiments are conducted to evaluate the effectiveness of LCD on both industrial and public datasets. Furthermore, in a one-week online AB test, LCD also significantly increases both the music play count and time per user by 1% to 5%.

Understanding news content is critical to improving the quality of news recommendation. To achieve this goal, recent studies have attempted to apply pre-trained language models (PLMs) such as BERT for semantic-enhanced news recommendation. Despite their great success in offline evaluation, it is still a challenge to apply such large PLMs in real-time ranking model due to the stringent requirement in inference and updating time. To bridge this gap, we propose a plug-and-play pre-trainer, namely PREC, to learn both user and news encoders through multi-task pre-training. Instead of directly leveraging sophisticated PLMs for end-to-end inference, we focus on how to use the derived user and item representations to boost the performance of conventional lightweight models for click-through-rate prediction. This enables efficient online inference as well as compatibility to conventional models, which would significantly ease the practical deployment. We validate the effectiveness of PREC through both offline evaluation on public datasets and online A/B testing in an industrial application.

Audio-Guided video object segmentation is a challenging problem in visual analysis and editing, which automatically separates foreground objects from the background in a video sequence according to the referring audio expressions. However, existing referring video object segmentation works mainly focus on the guidance of text-based referring expressions, due to the lack of modeling the semantic representations of audio-video interaction contents. In this paper, we consider the problem of audio-guided video semantic segmentation from the viewpoint of end-to-end denoising encoder-decoder network learning. We propose the wavelet-based encoder network to learn the cross-modal representations of the video contents with audio-form queries. Specifically, we adopt the multi-head cross-modal attention layers to explore the potential relations of video and query contents. A 2-dimension discrete wavelet trans-form is merged into the transformer encoder to decompose the audio-video features. Next, we maximize mutual information between the encoded features and multi-modal features after cross-modal attention layers to enhance the au-dio guidance. Then, a self attention-free decoder network is developed to generate the target masks with frequency-domain transforms. In addition, we construct the first large-scale audio-guided video semantic segmentation dataset. The extensive experiments show the effectiveness of our method11Code is available at: https://github.com/asudahkzj/Wnet.git.

The lack of publicly available high-quality and accurately labeled datasets has long been a major bottleneck for singing voice synthesis (SVS). To tackle this problem, we present M4Singer, a free-to-use Multi-style, Multi-singer Mandarin singing collection with elaborately annotated Musical scores as well as its benchmarks. Specifically, 1) we construct and release a large high-quality Chinese singing voice corpus, which is recorded by 20 professional singers, covering 700 Chinese pop songs as well as all the four SATB types (i.e., soprano, alto, tenor, and bass); 2) we take extensive efforts to manually compose the musical scores for each recorded song, which are necessary to the study of the prosody modeling for SVS. 3) To facilitate the use and demonstrate the quality of M4Singer, we conduct four different benchmark experiments: score-based SVS, controllable singing voice (CSV), singing voice conversion (SVC) and automatic music transcription (AMT).

Deep learning-based recommendation has become a widely adopted technique in various online applications. Typically, a deployed model undergoes frequent re-training to capture users' dynamic behaviors from newly collected interaction logs. However, the current model training process only acquires users' feedbacks as labels, but fails to take into account the errors made in previous recommendations. Inspired by the intuition that humans usually reflect and learn from mistakes, in this paper, we attempt to build a self-correction continual learning loop (dubbed ReLoop) for recommender systems. In particular, a new customized loss is employed to encourage every new model version to reduce prediction errors over the previous model version during training. Our ReLoop learning framework enables a continual self-correction process in the long run and thus is expected to obtain better performance over existing training strategies. Both offline experiments and an online A/B test have been conducted to validate the effectiveness of ReLoop.

As the final stage of the multi-stage recommender system (MRS), reranking directly affects users' experience and satisfaction, thus playing a critical role in MRS. Despite the improvement achieved in the existing work, three issues are yet to be solved. First, users' historical behaviors contain rich preference information, such as users' long and short-term interests, but are not fully exploited in reranking. Previous work typically treats items in history equally important, neglecting the dynamic interaction between the history and candidate items. Second, existing reranking models focus on learning interactions at the item level while ignoring the fine-grained feature-level interactions. Lastly, estimating the reranking score on the ordered initial list before reranking may lead to the early scoring problem, thereby yielding suboptimal reranking performance. To address the above issues, we propose a framework named Multi-level Interaction Reranking (MIR). MIR combines low-level cross-item interaction and high-level set-to-list interaction, where we view the candidate items to be reranked as a set and the users' behavior history in chronological order as a list. We design a novel SLAttention structure for modeling the set-to-list interactions with personalized long-short term interests. Moreover, feature-level interactions are incorporated to capture the fine-grained influence among items. We design MIR in such a way that any permutation of the input items would not change the output ranking, and we theoretically prove it. Extensive experiments on three public and proprietary datasets show that MIR significantly outperforms the state-of-the-art models using various ranking and utility metrics.

The past two decades have witnessed the rapid development of personalized recommendation techniques. Despite the significant progress made in both research and practice of recommender systems, to date, there is a lack of a widely-recognized benchmarking standard in this field. Many of the existing studies perform model evaluations and comparisons in an ad-hoc manner, for example, by employing their own private data splits or using a different experimental setting. However, such conventions not only increase the difficulty in reproducing existing studies, but also lead to inconsistent experimental results among them. This largely limits the credibility and practical value of research results in this field. To tackle these issues, we present an initiative project aimed for open benchmarking for recommender systems. In contrast to some earlier attempts towards this goal, we take one further step by setting up a standardized benchmarking pipeline for reproducible research, which integrates all the details about datasets, source code, hyper-parameter settings, running logs, and evaluation results. The benchmark is designed with comprehensiveness and sustainability in mind. It spans both matching and ranking tasks, and also allows anyone to easily follow and contribute. We believe that our benchmark could not only reduce the redundant efforts of researchers to re-implement or re-run existing baselines, but also drive more solid and reproducible research on recommender systems.

Self-supervised learning, especially contrastive learning, has made an outstanding contribution to the development of many deep learning research fields. Recently, researchers in the acoustic signal processing field noticed its success and leveraged contrastive learning for better music representation. Typically, existing approaches maximize the similarity between two distorted audio segments sampled from the same music. In other words, they ensure a semantic agreement at the music level. However, those coarse-grained methods neglect some inessential or noisy elements at the frame level, which may be detrimental to the model to learn the effective representation of music. Towards this end, this paper proposes a novel Positive-nEgative frame mask for Music Representation based on the contrastive learning framework, abbreviated as PEMR. Concretely, PEMR incorporates a Positive-Negative Mask Generation module, which leverages transformer blocks to generate frame masks on Log-Mel spectrogram. We can generate self-augmented negative and positive samples by masking important components or inessential components, respectively. We devise a novel contrastive learning objective to accommodate both self-augmented positives/negatives sampled from the same music. We conduct experiments on four public datasets. The experimental results of two music-related downstream tasks, music classification and cover song identification, demonstrate the generalization ability and transferability of music representation learned by PEMR.

Personalized recommendation system has become pervasive in various video platform.Many effective methods have been proposed, but most of them didn’t capture the user’s multilevel interest trait and dependencies between their viewed micro-videos well. To solve these problems, we propose a Self-over-Co Attention module to enhance user’s interest representation. In particular, we first use co-attention to model correlation patterns across different levels and then use self attention to modelcorrelation patterns within a specific level. Experimental results on filtered public datasets verify that our presented module is useful.

Collaborative filtering (CF) is a widely studied research topic in recommender systems. The learning of a CF model generally depends on three major components, namely interaction encoder, loss function, and negative sampling. While many existing studies focus on the design of more powerful interaction encoders, the impacts of loss functions and negative sampling ratios have not yet been well explored. In this work, we show that the choice of loss function as well as negative sampling ratio is equivalently important. More specifically, we propose the cosine contrastive loss (CCL) and further incorporate it to a simple unified CF model, dubbed SimpleX. Extensive experiments have been conducted on 10 benchmark datasets and compared with 28 existing CF models in total. Surprisingly, the results show that, under our CCL loss and a large negative sampling ratio, SimpleX can surpass most sophisticated state-of-the-art models by a large margin (e.g., max 48.5% improvement in [email protected] over LightGCN). We believe that SimpleX could not only serve as a simple strong baseline to foster future research on CF, but also shed light on the potential research direction towards improving loss function and negative sampling.

With the recent success of graph convolutional networks (GCNs), they have been widely applied for recommendation, and achieved impressive performance gains. The core of GCNs lies in its message passing mechanism to aggregate neighborhood information. However, we observed that message passing largely slows down the convergence of GCNs during training, especially for large-scale recommender systems, which hinders their wide adoption. LightGCN makes an early attempt to simplify GCNs for collaborative filtering by omitting feature transformations and nonlinear activations. In this paper, we take one step further to propose an ultra-simplified formulation of GCNs (dubbed UltraGCN), which skips infinite layers of message passing for efficient recommendation. Instead of explicit message passing, UltraGCN resorts to directly approximate the limit of infinite-layer graph convolutions via a constraint loss. Meanwhile, UltraGCN allows for more appropriate edge weight assignments and flexible adjustment of the relative importances among different types of relationships. This finally yields a simple yet effective UltraGCN model, which is easy to implement and efficient to train. Experimental results on four benchmark datasets show that UltraGCN not only outperforms the state-of-the-art GCN models but also achieves more than 10x speedup over LightGCN.

Click-through rate (CTR) prediction is a critical task for many applications, as its accuracy has a direct impact on user experience and platform revenue. In recent years, CTR prediction has been widely studied in both academia and industry, resulting in a wide variety of CTR prediction models. Unfortunately, there is still a lack of standardized benchmarks and uniform evaluation protocols for CTR prediction research. This leads to non-reproducible or even inconsistent experimental results among existing studies, which largely limit the practical value and potential impact of their research. In this work, we aim to perform open benchmarking for CTR prediction and present a rigorous comparison of different models in a reproducible manner. To this end, we ran over 7,000 experiments for more than 12,000 GPU hours in total to re-evaluate 24 existing models on multiple dataset settings. Surprisingly, our experiments show that with sufficient hyper-parameter search and model tuning, many deep models have smaller differences than expected. The results also reveal that making real progress on the modeling of CTR prediction is indeed a very challenging research task. We believe that our benchmarking work could not only allow researchers to gauge the effectiveness of new models conveniently but also make them fairly compare with the state of the arts. We have publicly released the benchmarking tools, evaluation protocols, and experimental settings of our work to promote reproducible research in this field.

Nowadays, news recommendation has become a popular channel for users to access news of their interests. How to represent rich textual contents of news and precisely match users' interests and candidate news lies in the core of news recommendation. However, existing recommendation methods merely learn textual representations from in-domain news data, which limits their generalization ability to new news that are common in cold-start scenarios. Meanwhile, many of these methods represent each user by aggregating the historically browsed news into a single vector and then compute the matching score with the candidate news vector, which may lose the low-level matching signals. In this paper, we explore the use of the successful BERT pre-training technique in NLP for news recommendation and propose a BERT-based user-news matching model, called UNBERT. In contrast to existing research, our UNBERT model not only leverages the pre-trained model with rich language knowledge to enhance textual representation, but also captures multi-grained user-news matching signals at both word-level and news-level. Extensive experiments on the Microsoft News Dataset (MIND) demonstrate that our approach constantly outperforms the state-of-the-art methods.

There is a soaring interest in the news recommendation research scenario due to the information overload. To accurately capture users' interests, we propose to model multi-modal features, in addition to the news titles that are widely used in existing works, for news recommendation. Besides, existing research pays little attention to the click decision-making process in designing multi-modal modeling modules. In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation. In this paper, we refer to visual impression as the region of the news displayed on the user interface of a news application, which delivers both content and layout information to users. Specifically, we devise the local impression modeling module to simultaneously attend to decomposed details in the impression when understanding the semantic meaning of news title, which could explicitly get close to the process of users reading news. In addition, we inspect the impression from a global view and take structural information, such as the arrangement of different fields and spatial position of different words on the impression, into the modeling of multiple modalities. To accommodate the research of visual impression-aware news recommendation, we extend the text-dominated news recommendation dataset MIND by adding snapshot impression images and will release it to nourish the research field. Extensive comparisons with the state-of-the-art news recommenders along with the in-depth analyses demonstrate the effectiveness of the proposed method and the promising capability of modeling visual impressions for the content-based recommenders.

Personalized news recommendation aims to alleviate information overload and help users find news of their interests. Accurately matching candidate news and users' interests is the key to news recommendation. Most existing methods separately encode each user and news into vectors by news contents and then match the two vectors. However, a user's interest may differ in each news or each topic of one news. It's necessary to dynamically learn user and news vector and model their interaction. In this work, we present Recurrent Reasoning Memory Network over BERT (RMBERT) for news recommendation. Compared with other methods, our approach can leverage the ability of content modeling from BERT. Moreover, the recurrent reasoning memory network which performs a series of attention based reasoning steps can dynamically learn user and news vector and model their interaction in each step. As a result, our approach can better model user's interests. We conduct extensive experiments on a real-world news recommendation dataset and the results show that our approach significantly outperforms existing state-of-the-art methods.

Due to the popularity of video contents on the Internet, the information retrieval between videos and texts has attracted broad interest from researchers, which is a challenging cross-modal retrieval task. A common solution is to learn a joint embedding space to measure the cross-modal similarity. However, many existing approaches either pay more attention to textual information, video information, or cross-modal matching methods, but less to all three. We believe that a good video-text retrieval system should take into account all three points, fully exploiting the semantic information of both modalities and considering a comprehensive match. In this paper, we propose a Hierarchical Cross-Modal Graph Consistency Learning Network (HCGC) for video-text retrieval task, which considers multi-level graph consistency for video-text matching. Specifically, we first construct a hierarchical graph representation for the video, which includes three levels from global to local: video, clips and objects. Similarly, the corresponding text graph is constructed according to the semantic relationships among sentence, actions and entities. Then, in order to learn a better match between the video and text graph, we design three types of graph consistency (both direct and indirect): inter-graph parallel consistency, inter-graph cross consistency and intra-graph cross consistency. Extensive experimental results on different video-text datasets demonstrate the effectiveness of our approach on both text-to-video and video-to-text retrieval.

The two-tower architecture has been widely applied for learning item and user representations, which is important for large-scale recommender systems. Many two-tower models are trained using various in-batch negative sampling strategies, where the effects of such strategies inherently rely on the size of mini-batches. However, training two-tower models with a large batch size is inefficient, as it demands a large volume of memory for item and user contents and consumes a lot of time for feature encoding. Interestingly, we find that neural encoders can output relatively stable features for the same input after warming up in the training process. Based on such facts, we propose a simple yet effective sampling strategy called Cross-Batch Negative Sampling (CBNS), which takes advantage of the encoded item embeddings from recent mini-batches to boost the model training. Both theoretical analysis and empirical evaluations demonstrate the effectiveness and the efficiency of CBNS.

Vision-language research has become very popular, which focuses on understanding of visual contents, language semantics and relationships between them. Video question answering (Video QA) is one of the typical tasks. Recently, several BERT style pre-training methods have been proposed and shown effectiveness on various vision-language tasks. In this work, we leverage the successful vision-language transformer structure to solve the Video QA problem. However, we do not pre-train it with any video data, because video pre-training requires massive computing resources and is hard to perform with only a few GPUs. Instead, our work aims to leverage image-language pre-training to help with video-language modeling, by sharing a common module design. We further introduce an adaptive spatio-temporal graph to enhance the vision-language representation learning. That is, we adaptively refine the spatio-temporal tubes of salient objects according to their spatio-temporal relations learned through a hierarchical graph convolution process. Finally, we can obtain a number of fine-grained tube-level video object representations, as the visual inputs of the vision-language transformer module. Experiments on three widely used Video QA datasets show that our model achieves the new state-of-the-art results.

Recently, deep learning-based models have been widely studied for click-through rate (CTR) prediction and lead to improved prediction accuracy in many industrial applications. However, current research focuses primarily on building complex network architectures to better capture sophisticated feature interactions and dynamic user behaviors. The increased model complexity may slow down online inference and hinder its adoption in real-time applications. Instead, our work targets at a new model training strategy based on knowledge distillation (KD). KD is a teacher-student learning framework to transfer knowledge learned from a teacher model to a student model. The KD strategy not only allows us to simplify the student model as a vanilla DNN model but also achieves significant accuracy improvements over the state-of-the-art teacher models. The benefits thus motivate us to further explore the use of a powerful ensemble of teachers for more accurate student model training. We also propose some novel techniques to facilitate ensembled CTR prediction, including teacher gating and early stopping by distillation loss. We conduct comprehensive experiments against 12 existing models and across three industrial datasets. Both offline and online A/B testing results show the effectiveness of our KD-based training strategy.

Video moment retrieval aims to localize the target moment in an video according to the given sentence. The weak-supervised setting only provides the video-level sentence annotations during training. Most existing weak-supervised methods apply a MIL-based framework to develop inter-sample confrontment, but ignore the intra-sample confrontment between moments with semantically similar contents. Thus, these methods fail to distinguish the target moment from plausible negative moments. In this paper, we propose a novel Regularized Two-Branch Proposal Network to simultaneously consider the inter-sample and intra-sample confrontments. Concretely, we first devise a language-aware filter to generate an enhanced video stream and a suppressed video stream. We then design the sharable two-branch proposal module to generate positive proposals from the enhanced stream and plausible negative proposals from the suppressed one for sufficient confrontment. Further, we apply the proposal regularization to stabilize the training process and improve model performance. The extensive experiments show the effectiveness of our method. Our code is released at here.

Weakly-supervised vision-language grounding aims to localize a target moment in a video or a specific region in an image according to the given sentence query, where only video-level or image-level sentence annotations are provided during training. Most existing approaches employ the MIL-based or reconstruction-based paradigms for the WSVLG task, but the former heavily depends on the quality of randomly-selected negative samples and the latter cannot directly optimize the visual-textual alignment score. In this paper, we propose a novel Counterfactual Contrastive Learning (CCL) to develop sufficient contrastive training between counterfactual positive and negative results, which are based on robust and destructive counterfactual transformations. Concretely, we design three counterfactual transformation strategies from the feature-, interaction- and relation-level, where the feature-level method damages the visual features of selected proposals, interaction-level approach confuses the vision-language interaction and relation-level strategy destroys the context clues in proposal relationships. Extensive experiments on five vision-language grounding datasets verify the effectiveness of our CCL paradigm.

Tagging has been recognized as a successful practice to boost relevance matching for information retrieval (IR), especially when items lack rich textual descriptions. A lot of research has been done for either multi-label text categorization or image annotation. However, there is a lack of published work that targets at item tagging specifically for IR. Directly applying a traditional multi-label classification model for item tagging is sub-optimal, due to the ignorance of unique characteristics in IR. In this work, we propose to formulate item tagging as a link prediction problem between item nodes and tag nodes. To enrich the representation of items, we leverage the query logs available in IR tasks, and construct a query-item-tag tripartite graph. This formulation results in a TagGNN model that utilizes heterogeneous graph neural networks with multiple types of nodes and edges. Different from previous research, we also optimize both full tag prediction and partial tag completion cases in a unified framework via a primary-dual loss mechanism. Experimental results on both open and industrial datasets show that our TagGNN approach outperforms the state-of-the-art multi-label classification approaches.

System logs record detailed runtime information of software systems and are used as the main data source for many tasks around software engineering. As modern software systems are evolving into large scale and complex structures, logs have become one type of fast-growing big data in industry. In particular, such logs often need to be stored for a long time in practice (e.g., a year), in order to analyze recurrent problems or track security issues. However, archiving logs consumes a large amount of storage space and computing resources, which in turn incurs high operational cost. Data compression is essential to reduce the cost of log storage. Traditional compression tools (e.g., gzip) work well for general texts, but are not tailed for system logs. In this paper, we propose a novel and effective log compression method, namely logzip. Logzip is capable of extracting hidden structures from raw logs via fast iterative clustering and further generating coherent intermediate representations that allow for more effective compression. We evaluate logzip on five large log datasets of different system types, with a total of 63.6 GB in size. The results show that logzip can save about half of the storage space on average over traditional compression tools. Meanwhile, the design of logzip is highly parallel and only incurs negligible overhead. In addition, we share our industrial experience of applying logzip to Huawei's real products.

Bug tracking systems are widely used to track bugs from users during the lifecycle of software systems for reliability maintenance. When software systems have a large user base, which is common in practice, different users may encounter a same bug and then generate many duplicate bug reports. In a large project, each bug report is usually assigned to a different developer or team to parallelize the bug debugging and fixing activities. The presence of duplicate bug reports thus leads to many unnecessary efforts of developers spending on debugging a same issue. To speed up the bug fixing process and save the cost of developers, there is a high demand for automated detection of duplicate bug reports. In this paper, we explore the use of powerful deep learning techniques, including word embedding and Convolution Neural Networks, to calculate the similarity between a pair of bug reports and thus identify possible duplicates. In contrast to previous work that consider only common words between bug descriptions for lexical similarity computation, our approach is able to better capture semantic similarity between words. We further improve traditional CNN models by combining some domain-specific features extracted from bug reports. Evaluation results on the bug reports from four popular open-source projects show that DBR-CNN has made a significant improvement on duplicate detection accuracy over traditional approaches.

Logs are widely used in system management for dependability assurance because they are often the only data available that record detailed system runtime behaviors in production. Because the size of logs is constantly increasing, developers (and operators) intend to automate their analysis by applying data mining methods, therefore structured input data (e.g., matrices) are required. This triggers a number of studies on log parsing that aims to transform free-text log messages into structured events. However, due to the lack of open-source implementations of these log parsers and benchmarks for performance comparison, developers are unlikely to be aware of the effectiveness of existing log parsers and their limitations when applying them into practice. They must often reimplement or redesign one, which is time-consuming and redundant. In this paper, we first present a characterization study of the current state of the art log parsers and evaluate their efficacy on five real-world datasets with over ten million log messages. We determine that, although the overall accuracy of these parsers is high, they are not robust across all datasets. When logs grow to a large scale (e.g., 200 million log messages), which is common in practice, these parsers are not efficient enough to handle such data on a single computer. To address the above limitations, we design and implement a parallel log parser (namely POP) on top of Spark, a large-scale data processing platform. Comprehensive experiments have been conducted to evaluate POP on both synthetic and real-world datasets. The evaluation results demonstrate the capability of POP in terms of accuracy, efficiency, and effectiveness on subsequent log mining tasks.

Logs, which record valuable system runtime information, have been widely employed in Web service management by service providers and users. A typical log analysis based Web service management procedure is to first parse raw log messages because of their unstructured format; and then apply data mining models to extract critical system behavior information, which can assist Web service management. Most of the existing log parsing methods focus on offline, batch processing of logs. However, as the volume of logs increases rapidly, model training of offline log parsing methods, which employs all existing logs after log collection, becomes time consuming. To address this problem, we propose an online log parsing method, namely Drain, that can parse logs in a streaming and timely manner. To accelerate the parsing process, Drain uses a fixed depth parse tree, which encodes specially designed rules for parsing. We evaluate Drain on five real-world log data sets with more than 10 million raw log messages. The experimental results show that Drain has the highest accuracy on four data sets, and comparable accuracy on the remaining one. Besides, Drain obtains 51.85%~81.47% improvement in running time compared with the state-of-the-art online parser. We also conduct a case study on an anomaly detection task using Drain in the parsing step, which determines the effectiveness of Drain in log analysis.

Reliability prediction is an important task in software reliability engineering, which has been widely studied in the last decades. However, modelling and predicting user-perceived reliability of black-box services remain an open research problem. Software services, such as Web services and Web APIs, generally provide black-box functionalities to users through the Internet, thus leading to a lack of their internal information for reliability analysis. Furthermore, the user-perceived service reliability depends not only on the service itself, but also heavily on the invocation context (e.g., service workloads, network conditions), whereby traditional reliability models become ineffective and inappropriate. To address these new challenges posed by blackbox services, in this paper, we propose CARP, a new contextaware reliability prediction approach, which leverages historical usage data from users to construct context-aware reliability models and further provides online reliability prediction results to users. Through context-aware reliability modelling, CARP is able to alleviate the data sparsity problem that heavily limits the prediction accuracy of other existing approaches. The preliminary evaluation results show that CARP can make a significant improvement in reliability prediction accuracy, e.g., about 41% in MAE and 38% in RMSE when only 5% of the data are available.

To improve software reliability, software defect prediction is utilized to assist developers in finding potential bugs and allocating their testing efforts. Traditional defect prediction studies mainly focus on designing hand-crafted features, which are input into machine learning classifiers to identify defective code. However, these hand-crafted features often fail to capture the semantic and structural information of programs. Such information is important in modeling program functionality and can lead to more accurate defect prediction. In this paper, we propose a framework called Defect Prediction via Convolutional Neural Network (DP-CNN), which leverages deep learning for effective feature generation. Specifically, based on the programs' Abstract Syntax Trees (ASTs), we first extract token vectors, which are then encoded as numerical vectors via mapping and word embedding. We feed the numerical vectors into Convolutional Neural Network to automatically learn semantic and structural features of programs. After that, we combine the learned features with traditional hand-crafted features, for accurate software defect prediction. We evaluate our method on seven open source projects in terms of F-measure in defect prediction. The experimental results show that in average, DP-CNN improves the state-of-the-art method by 12%.

Cloud applications built on service-oriented architectures generally integrate a number of component services to fulfill certain application logic. The changing cloud environment highlights the need for these applications to keep resilient against QoS variations of their component services so that end-to-end quality-of-service (QoS) can be guaranteed. Runtime service adaptation is a key technique to achieve this goal. To support timely and accurate adaptation decisions, effective and efficient QoS prediction is needed to obtain real-time QoS information of component services. However, current research has focused mostly on QoS prediction of working services that are being used by a cloud application, but little on predicting QoS values of candidate services that are equally important in determining optimal adaptation actions. In this paper, we propose an adaptive matrix factorization (namely AMF) approach to perform online QoS prediction for candidate services. AMF is inspired from the widely-used collaborative filtering techniques in recommender systems, but significantly extends the conventional matrix factorization model with new techniques of data transformation, online learning, and adaptive weights. Comprehensive experiments, as well as a case study, have been conducted based on a real-world QoS dataset of Web services (with over 40 million QoS records). The evaluation results demonstrate AMF's superiority in achieving accuracy, efficiency, and robustness, which are essential to enable optimal runtime service adaptation.

Logs, which record runtime information of modern systems, are widely utilized by developers (and operators) in system development and maintenance. Due to the ever-increasing size of logs, data mining models are often adopted to help developers extract system behavior information. However, before feeding logs into data mining models, logs need to be parsed by a log parser because of their unstructured format. Although log parsing has been widely studied in recent years, users are still unaware of the advantages of different log parsers nor the impact of them on subsequent log mining tasks. Thus they often re-implement or even re-design a new log parser, which would be time-consuming yet redundant. To address this issue, in this paper, we study four log parsers and package them into a toolkit to allow their reuse. In addition, we obtain six insightful findings by evaluating the performance of the log parsers on five datasets with over ten million raw log messages, while their effectiveness on a real-world log mining task has been thoroughly examined.

Web service recommendation has recently drawn much attention with the growing amount of Web services. Previous work usually exploits the collaborative filtering techniques for Web service recommendation, but suffers from the data sparsity problem that leads to inaccurate results. Our analysis on a real-world Quality of Service (QoS) dataset shows that there is a hidden correlation among users and services. We define such hidden correlation with an asymmetric matrix (namely asymmetric correlation), in which each entry presents the hidden correlation between a user pair or between a service pair. The goal of this work is to employ such asymmetric correlation among users and services to alleviate the data sparsity problem and further enhance the prediction accuracy in service recommendation. Specifically, we propose an asymmetric correlation regularized matrix factorization (MF) framework, in which asymmetric correlation and asymmetric correlation propagation have been naturally integrated. Finally, experimental results on a well-known real-world QoS dataset validate that the use of asymmetric correlation among users and services is effective in improving prediction accuracy for Web service recommendation.

Anomaly detection plays an important role in management of modern large-scale distributed systems. Logs, which record system runtime information, are widely used for anomaly detection. Traditionally, developers (or operators) often inspect the logs manually with keyword search and rule matching. The increasing scale and complexity of modern systems, however, make the volume of logs explode, which renders the infeasibility of manual inspection. To reduce manual effort, many anomaly detection methods based on automated log analysis are proposed. However, developers may still have no idea which anomaly detection methods they should adopt, because there is a lack of a review and comparison among these anomaly detection methods. Moreover, even if developers decide to employ an anomaly detection method, re-implementation requires a nontrivial effort. To address these problems, we provide a detailed review and evaluation of six state-of-the-art log-based anomaly detection methods, including three supervised methods and three unsupervised methods, and also release an open-source toolkit allowing ease of reuse. These methods have been evaluated on two publicly-available production log datasets, with a total of 15,923,592 log messages and 365,298 anomaly instances. We believe that our work, with the evaluation results as well as the corresponding findings, can provide guidelines for adoption of these methods and provide references for future development.

Logging is a common programming practice of practical importance to collect system runtime information for postmortem analysis. Strategic logging placement is desired to cover necessary runtime information without incurring unintended consequences (e.g., Performance overhead, trivial logs). However, in current practice, there is a lack of rigorous specifications for developers to govern their logging behaviours. Logging has become an important yet tough decision which mostly depends on the domain knowledge of developers. To reduce the effort on making logging decisions, in this paper, we propose a "learning to log" framework, which aims to provide informative guidance on logging during development. As a proof of concept, we provide the design and implementation of a logging suggestion tool, Log Advisor, which automatically learns the common logging practices on where to log from existing logging instances and further leverages them for actionable suggestions to developers. Specifically, we identify the important factors for determining where to log and extract them as structural features, textual features, and syntactic features. Then, by applying machine learning techniques (e.g., Feature selection and classifier learning) and noise handling techniques, we achieve high accuracy of logging suggestions. We evaluate Log Advisor on two industrial software systems from Microsoft and two open-source software systems from Git Hub (totally 19.1M LOC and 100.6K logging statements). The encouraging experimental results, as well as a user study, demonstrate the feasibility and effectiveness of our logging suggestion tool. We believe our work can serve as an important first step towards the goal of "learning to log".

QoS-based Web service recommendation has recently gained much attention for providing a promising way to help users find high-quality services. To facilitate such recommendations, existing studies suggest the use of collaborative filtering techniques for personalized QoS prediction. These approaches, by leveraging partially observed QoS values from users, can achieve high accuracy of QoS predictions on the unobserved ones. However, the requirement to collect users' QoS data likely puts user privacy at risk, thus making them unwilling to contribute their usage data to a Web service recommender system. As a result, privacy becomes a critical challenge in developing practical Web service recommender systems. In this paper, we make the first attempt to cope with the privacy concerns for Web service recommendation. Specifically, we propose a simple yet effective privacy-preserving framework by applying data obfuscation techniques, and further develop two representative privacy-preserving QoS prediction approaches under this framework. Evaluation results from a publicly-available QoS dataset of real-world Web services demonstrate the feasibility and effectiveness of our privacy-preserving QoS prediction approaches. We believe our work can serve as a good starting point to inspire more research efforts on privacy-preserving Web service recommendation.

User review analysis is critical to the bug-fixing and version-modification process for app developers. Many research efforts have been put to user review mining in discovering app issues, including laggy user interface, high memory overhead, privacy leakage, etc. Existing exploration of app reviews generally depends on static collections. As a result, they largely ignore the fact that user reviews are tightly related to app versions. Furthermore, the previous approaches require a developer to spend much time on filtering out trivial comments and digesting the informative textual data. This would be labor-intensive especially to popular apps with tremendous reviews. In the paper, we target at designing a framework in Prioritizing App Issues for Developers (PAID) with minimal manual power and good accuracy. The PAID design is based on the fact that the issues presented in the level of phrase, i.e., a couple of consecutive words, can be more easily understood by developers than in long sentences. Hence, we aim at recommending phrase-level issues of an app to its developers by tracking reviews over the release versions of the app. To assist developers in better comprehending the app issues, PAID employs ThemeRiver to visualize the analytical results to developers. Finally, PAID also allows the developers to check the most related reviews, when they want to obtain a deep insight of a certain issue. In contrast to the traditional evaluation methods such as manual labeling or examining the discussion forum, our experimental study exploits the first-hand information from developers, i.e., app changelogs, to measure the performance of PAID. We analyze millions of user reviews from 18 apps with 117 app versions and the results show that the prioritized issues generated by PAID match the official changelogs with high precision.

Service-based cloud applications are typically built on component services to fulfill certain application logic. To meet quality-of-service (QoS) guarantees, these applications have to become resilient against the QoS variations of their component services. Runtime service adaptation has been recognized as a key solution to achieve this goal. To make timely and accurate adaptation decisions, effective QoS prediction is desired to obtain the QoS values of component services. However, current research has focused mostly on QoS prediction of the working services that are being used by a cloud application, but little on QoS prediction of candidate services that are also important for making adaptation decisions. To bridge this gap, in this paper, we propose a novel QoS prediction approach, namely adaptive matrix factorization (AMF), which is inspired from the collaborative filtering model used in recommender systems. Specifically, our AMF approach extends conventional matrix factorization into an online, accurate, and scalable model by employing techniques of data transformation, online learning, and adaptive weights. Comprehensive experiments have been conducted based on a real-world large-scale QoS dataset of Web services to evaluate our approach. The evaluation results provide good demonstration for our approach in achieving accuracy, efficiency, and scalability.

Web service recommendation is of great importance when users face a large number of functionally-equivalent candidate services. To recommend Web services that best fit a user's need, QoS values which characterize the non-functional properties of those candidate services are in demand. But in reality, the QoS information of Web service is not easy to obtain, because only limited historical invocation records exist. To tackle this challenge, in recent literature, a number of QoS prediction methods are proposed, but they still demonstrate disadvantages on prediction accuracy. In this paper, we design a location-based hierarchical matrix factorization (HMF) method to perform personalized QoS prediction, whereby effective service recommendation can be made. We cluster users and services into several user-service groups based on their location information, each of which contains a small set of users and services. To better characterize the QoS data, our HMF model is trained in a hierarchical way by using the global QoS matrix as well as several location-based local QoS matrices generated from user-service clusters. Then the missing QoS values can be predicted by compactly combining the results from local matrix factorization and global matrix factorization. Comprehensive experiments are conducted on a real-world Web service QoS dataset with 1,974,675 real Web service invocation records. The experimental results show that our HMF method achieves higher prediction accuracy than the state-of-the-art methods.

Application latency is one significant user metric for evaluating the performance of online cloud applications. However, as applications are migrated to the cloud and deployed across a wide-area network, the application latency usually presents high variability over time. Among lots of subtleties that influence the latency, one important factor is relying on the Internet for application connectivity, which introduces a high degree of variability and uncertainty on user-perceived application latency. As a result, a key challenge faced by application designers is how to build consistently low-latency cloud applications with the large number of geo-distributed and latency-varying cloud components. In this paper, we propose a dynamic request routing framework, DR2, by taking full advantage of redundant components in the clouds to tolerate latency variability. In practice, many functionally-equivalent components have been already deployed redundantly for load balancing and fault tolerance, thus resulting in low additional overhead for DR2. To evaluate the performance of our approach, we conduct a set of experiments based on two large-scale real-world datasets and a synthetic dataset. The results show the effectiveness and efficiency of our approach.

With the rapid growth of Web services in recent years, the optimal service selection from functionally-equivalent service candidates has become more critical for building high quality service-oriented systems. To provide accurate QoSvalues for service selection, user-side QoS prediction thus becomes an important research problem. Although collaborative filtering based prediction approaches have been studied in several previous works, these methods suffer from the limitation of the sparsity of available historical QoS data, which greatly degrades the prediction accuracy. To address this problem, this paper proposes a Web service positioning (WSP)framework for response time prediction, which is one of the most important QoS properties. In our approach, a small set of landmarks are deployed to periodically monitor the response times of the Web service candidates and provide references to the numerous service users. By combining the advantages of network coordinate based approaches and collaborative filtering based approaches, the response times between users and Web services can be accurately predicted using their corresponding Euclidean distances. Extensive experiments are conducted based on our real-world QoS dataset collected on PlanetLab, comprising about 359,400 response time values from 200 users on 1,597 Web services. The experimental results show that our WSP approach outperforms the other existing approaches, especially when the historical data is sparse.