Interest modeling in recommender system has been a constant topic for improving user experience, and typical interest modeling tasks (e.g. multi-interest, long-tail interest and long-term interest) have been investigated in many existing works. However, most of them only consider one interest in isolation, while neglecting their interrelationships. In this paper, we argue that these tasks suffer from a common "interest amnesia" problem, and a solution exists to mitigate it simultaneously. We propose a novel and unified framework in the retrieval stage, "Trinity", to solve interest amnesia problem and improve multiple interest modeling tasks. We construct a real-time clustering system that enables us to project items into enumerable clusters, and calculate statistical interest histograms over these clusters. Based on these histograms, Trinity recognizes underdelivered themes and remains stable when facing emerging hot topics. Its derived retrievers have been deployed on the recommender system of Douyin, significantly improving user experience and retention. We believe that such practical experience can be well generalized to other scenarios.
论文检索
输入标题、作者或关键词，从 642 篇学术成果中精准定位
The prevailing issue of factual inconsistency errors in conventional Retrieval Augmented Generation (RAG) motivates the study of Factual Consistency Evaluation (FCE). Despite the various FCE methods proposed earlier, these methods are evaluated on datasets generated by specific Large Language Models (LLMs). Without a comprehensive benchmark, it remains unexplored how these FCE methods perform on other LLMs with different error distributions or even unseen error types, as these methods may fail to detect the error types generated by other LLMs. To fill this gap, in this paper, we propose the first comprehensive FCE benchmark Face4RAG for RAG independent of the underlying LLM. Our benchmark consists of a synthetic dataset built upon a carefully designed typology for factuality inconsistency error and a real-world dataset constructed from six commonly used LLMs, enabling evaluation of FCE methods on specific error types or real-world error distributions. On the proposed benchmark, we discover the failure of existing FCE methods to detect the logical fallacy, which refers to a mismatch of logic structures between the answer and the retrieved reference. To fix this issue, we further propose a new method called L-Face4RAG with two novel designs of logic-preserving answer decomposition and fact-logic FCE. Extensive experiments show L-Face4RAG substantially outperforms previous methods for factual inconsistency detection on a wide range of tasks, notably beyond the RAG task from which it is originally motivated. Both the benchmark and our proposed method are publicly available. https://huggingface.co/datasets/yq27/Face4RAG
Reinforcement Learning (RL) has demonstrated substantial potential across diverse fields, yet understanding its decision-making process, especially in real-world scenarios where rationality and safety are paramount, is an ongoing challenge. This paper delves in to Explainable RL (XRL), a subfield of Explainable AI (XAI) aimed at unravelling the complexities of RL models. Our focus rests on state-explaining techniques, a crucial subset within XRL methods, as they reveal the underlying factors influencing an agent's actions at any given time. Despite their significant role, the lack of a unified evaluation framework hinders assessment of their accuracy and effectiveness. To address this, we introduce XRL-Bench, a unified standardized benchmark tailored for the evaluation and comparison of XRL methods, encompassing three main modules: standard RL environments, explainers based on state importance, and standard evaluators. XRL-Bench supports both tabular and image data for state explanation. We also propose TabularSHAP, an innovative and competitive XRL method. We demonstrate the practical utility of TabularSHAP in real-world online gaming services and offer an open-source benchmark platform for the straightforward implementation and evaluation of XRL methods. Our contributions facilitate the continued progression of XRL technology.
Understanding the Weakness of Large Language Model Agents within a Complex Android Environment
PDF ↗Large language models (LLMs) have empowered intelligent agents to execute intricate tasks within domain-specific software such as browsers and games. However, when applied to general-purpose software systems like operating systems, LLM agents face three primary challenges. Firstly, the action space is vast and dynamic, posing difficulties for LLM agents to maintain an up-to-date understanding and deliver accurate responses. Secondly, real-world tasks often require inter-application cooperation, demanding farsighted planning from LLM agents. Thirdly, agents need to identify optimal solutions aligning with user constraints, such as security concerns and preferences. These challenges motivate AndroidArena, an environment and benchmark designed to evaluate LLM agents on a modern operating system. To address high-cost of manpower, we design a scalable and semi-automated method to construct the benchmark. In the task evaluation, AndroidArena incorporates accurate and adaptive metrics to address the issue of non-unique solutions. Our findings reveal that even state-of-the-art LLM agents struggle in cross-APP scenarios and adhering to specific constraints. Additionally, we identify a lack of four key capabilities, i.e. understanding, reasoning, exploration, and reflection, as primary reasons for the failure of LLM agents. Furthermore, we provide empirical analysis on the failure of reflection, and improve the success rate by 27% with our proposed exploration strategy. This work is the first to present valuable insights in understanding fine-grained weakness of LLM agents, and offers a path forward for future research in this area. Environment, benchmark, prompt, and evaluation code for AndroidArena are released at https://github.com/AndroidArenaAgent/AndroidArena.
Microservice Root Cause Analysis With Limited Observability Through Intervention Recognition in the Latent Space
PDF ↗Many failure root cause analysis (RCA) algorithms for microservices have been proposed with the widespread adoption of microservices systems. Existing algorithms generally focus on RCA with ranking single-level (e.g. metric-level or service-level) root cause candidates (RCCs) with comprehensive monitoring metrics. However, many heterogeneous RCCs exist with limited observability in real-world microservices systems. Further, we find that the limited observability may result in inaccurate RCA through real-world failures in eBay. In this paper, for the first time, we propose to "model RCCs as latent variables". The core idea is to infer the status of RCCs as latent variables with related monitoring metrics instead of directly extracting features from only the observable metrics. Based on this, we propose LatentScope, an unsupervised RCA framework with heterogeneous RCCs under limited observability. A dual-space graph is proposed to model both observable and unobservable variables, with many-to-many relationships between spaces. To achieve fast inference of latent variables and RCA, we propose the LatentRegressor algorithm, which includes Regression-based Latent-space Intervention Recognition (RLIR) to achieve intervention recognition-based RCA in latent space. LatentScope has been deployed in eBay's production environment and evaluated on both eBay's real-world failures and a testbed dataset. The evaluation results show that, compared with baseline algorithms, our model significantly improves the Top-1 recall by 9.7%-57.9%. The source code of LatentScope and the dataset are available at https://github.com/NetManAIOps/LatentScope.
Urban public nuisance events, like garbage exposure, illegal parking, facilities damage, and etc., impair the quality of life for city residents. Predicting and controlling these nuisances is crucial but complicated due to their ties to subjective and psychological factors. In this study, we reveal a significant correlation between such nuisances and meteorological indicators, influenced by the impact of climate on people's psychological states. We employ meteorology predictions that are integrated in Hawkes processes to enhance the accuracy of predicting the category and timing of these nuisances. To this end, we propose Spatial-Temporal Two-Tower Transformer (ST-T3), which simultaneously considers spatial data and further improves the prediction accuracy. Evaluated by about three-year data from both downtown and suburban Shanghai, our method outperforms both traditional and advanced prediction systems. We share a portion of the de-identified dataset for open research.
Fraud detection presents a challenging task characterized by ever-evolving fraud patterns and scarce labeled data. Existing methods predominantly rely on graph-based or sequence-based approaches. While graph-based approaches connect users through shared entities to capture structural information, they remain vulnerable to fraudsters who can disrupt or manipulate these connections. In contrast, sequence-based approaches analyze users' behavioral patterns, offering robustness against tampering but overlooking the interactions between similar users. Inspired by cohort analysis in retention and healthcare, this paper introduces VecAug, a novel cohort-augmented learning framework that addresses these challenges by enhancing the representation learning of target users with personalized cohort information. To this end, we first propose a vector burn-in technique for automatic cohort identification, which retrieves a task-specific cohort for each target user. Then, to fully exploit the cohort information, we introduce an attentive cohort aggregation technique for augmenting target user representations. To improve the robustness of such cohort augmentation, we also propose a novel label-aware cohort neighbor separation mechanism to distance negative cohort neighbors and calibrate the aggregated cohort information. By integrating this cohort information with target user representations, VecAug enhances the modeling capacity and generalization capabilities of the model to be augmented. Our framework is flexible and can be seamlessly integrated with existing fraud detection models. We deploy our framework on e-commerce platforms and evaluate it on three fraud detection datasets, and results show that VecAug improves the detection performance of base models by up to 2.48% in AUC and 22.5% in R@P0.9, outperforming state-of-the-art methods significantly.
Generating city-scale lane-level maps faces significant challenges due to the intricate urban environments, such as blurred or absent lane markings. Additionally, a standard lane-level map requires a comprehensive organization of lane groupings, encompassing lane direction, style, boundary, and topology, yet has not been thoroughly examined in prior research. These obstacles result in labor-intensive human annotation and high maintenance costs. This paper overcomes these limitations and presents an industrial-grade solution named DuMapNet that outputs standardized, vectorized map elements and their topology in an end-to-end paradigm. To this end, we propose a group-wise lane prediction (GLP) system that outputs vectorized results of lane groups by meticulously tailoring a transformer-based network. Meanwhile, to enhance generalization in challenging scenarios, such as road wear and occlusions, as well as to improve global consistency, a contextual prompts encoder (CPE) module is proposed, which leverages the predicted results of spatial neighborhoods as contextual information. Extensive experiments conducted on large-scale real-world datasets demonstrate the superiority and effectiveness of DuMapNet. Additionally, DuMapNet has already been deployed in production at Baidu Maps since June 2023, supporting lane-level map generation tasks for over 360 cities while bringing a 95% reduction in costs. This demonstrates that DuMapNet serves as a practical and cost-effective industrial solution for city-scale lane-level map generation.
Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the process of natural language generation, but their direct application in commentary creation still faces challenges due to unique task requirements. These requirements can be categorized into two levels: 1) fundamental requirements, which include creating well-structured and logically consistent narratives, and 2) advanced requirements, which involve generating quality arguments and providing convincing evidence. In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning (SFT) for each step. To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology. To evaluate the generated commentaries more fairly, corresponding to the two-level requirements, we introduce a comprehensive evaluation metric that considers five distinct perspectives in commentary generation. Our experiments confirm the effectiveness of our proposed system. We also observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes. Importantly, such an increase in efficiency does not compromise the quality of the commentaries.
Real-world last-mile express datasets are crucial for research in logistics, supply chain management, and spatio-temporal data mining. Despite a plethora of algorithms developed to date, no widely accepted, publicly available last-mile express dataset exists to support research in this field. In this paper, we introduce LaDe, the first publicly available last-mile express dataset with millions of packages from the industry. LaDe has three unique characteristics: (1)Large-scale. It involves 10,677k packages of 21k couriers over 6 months of real-world operation. (2)Comprehensive information. It offers original package information, task-event information, as well as couriers' detailed trajecotries and road networks. (3)Diversity. The dataset includes data from various scenarios, including package pick-up and delivery, and from multiple cities, each with its unique spatio-temporal patterns due to their distinct characteristics such as populations. We verify LaDe on three tasks by running several classical baseline models per task. We believe that the large-scale, comprehensive, diverse feature of LaDe can offer unparalleled opportunities to researchers in the supply chain community, data mining community, and beyond. The dataset and code is publicly available at https://huggingface.co/datasets/Cainiao-AI/LaDe.
Accurate vehicle trajectory recovery enables providing indispensable data foundations in intelligent urban transportation. However, existing methods face two challenges: i) the inability to process city-wide vehicle trajectories, and ii) the dependence on a substantial amount of accurate GPS trajectories for model training, leading to poor generalization ability. To address these issues, we propose a novel trajectory recovery system based on vehicle snapshots captured by traffic cameras, named TrajRecovery. TrajRecovery consists of three main components: i) Preprocessor processes traffic cameras and vehicle snapshots to provide necessary data for trajectory recovery; ii) Spatial Transfer Probabilistic Model (STPM) integrates road conditions and driver behavior to compute turning probability at intersections; iii) Trajectory Generator utilizes the output probabilities from STPM to recover a continuous and most likely complete trajectory. We evaluate TrajRecovery on two real datasets from a city in China, demonstrating substantial performance gains compared to state-of-the-art methods. Furthermore, our system is deployed in practical applications at Huawei Company, achieving extraordinary profits in business scenarios.
Nested Fusion: A Method for Learning High Resolution Latent Structure of Multi-Scale Measurement Data on Mars
PDF ↗The Mars Perseverance Rover represents a generational change in the scale of measurements that can be taken on Mars, however this increased resolution introduces new challenges for techniques in exploratory data analysis. The multiple different instruments on the rover each measures specific properties of interest to scientists, so analyzing how underlying phenomena affect multiple different instruments together is important to understand the full picture. However each instrument has a unique resolution, making the mapping between overlapping layers of data non-trivial. In this work, we introduce Nested Fusion, a method to combine arbitrarily layered datasets of different resolutions and produce a latent distribution at the highest possible resolution, encoding complex interrelationships between different measurements and scales. Our method is efficient for large datasets, can perform inference even on unseen data, and outperforms existing methods of dimensionality reduction and latent analysis on real-world Mars rover data. We have deployed our method Nested Fusion within a Mars science team at NASA Jet Propulsion Laboratory (JPL) and through multiple rounds of participatory design enabled greatly enhanced exploratory analysis workflows for real scientists. To ensure the reproducibility of our work we have open sourced our code on GitHub at https://github.com/pixlise/NestedFusion.
Rules are widely used in Fintech institutions to make fraud prevention decisions, since rules are highly interpretable thanks to their intuitive if-then structure. In practice, a two-stage framework of fraud prevention decision rule set mining is usually employed in large Fintech institutions; Stage 1 generates a potentially large pool of rules and Stage 2 aims to produce a refined rule subset according to some criteria (typically based on precision and recall). This paper focuses on improving the flexibility and efficacy of this two-stage framework, and is concerned with finding high-quality rule subsets in a bi-objective space (such as precision and recall). To this end, we first introduce a novel algorithm called SpectralRules that directly generates a compact pool of rules in Stage 1 with high diversity. We empirically find such diversity improves the quality of the final rule subset. In addition, we introduce an intermediate stage between Stage 1 and 2 that adopts the concept of Pareto optimality and aims to find a set of non-dominated rule subsets, which constitutes a Pareto front. This intermediate stage greatly simplifies the selection criteria and increases the flexibility of Stage 2. For this intermediate stage, we propose a heuristic-based framework called PORS and we identify that the core of PORS is the problem of solution selection on the front (SSF). We provide a systematic categorization of the SSF problem and a thorough empirical evaluation of various SSF methods on both public and proprietary datasets. On two real application scenarios within Alipay, we demonstrate the advantages of our proposed methodology over existing work.
Enhancing Pre-Ranking Performance: Tackling Intermediary Challenges in Multi-Stage Cascading Recommendation Systems
PDF ↗Large-scale search engines and recommendation systems utilize a three-stage cascading architecture-recall, pre-ranking, and ranking-to deliver relevant results within stringent latency limits. The pre-ranking stage is crucial for filtering a large number of recalled items into a manageable set for the ranking stage, greatly affecting the system's performance. Pre-ranking faces two intermediary challenges: Sample Selection Bias (SSB) arises when training is based on ranking stage feedback but the evaluation is on a broader recall dataset. Also, compared to the ranking stage, simpler pre-rank models may perform worse and less consistently. Traditional methods to tackle SSB issues include using all recall results and treating unexposed portions as negatives for training, which can be costly and noisy. To boost performance and consistency, some pre-ranking feature interaction enhancers don't fully fix consistency issues, while methods like knowledge distillation in ranking models ignore exposure bias. Our proposed framework targets these issues with three integral modules: Sample Selection, Domain Adaptation, and Unbiased Distillation. Sample Selection filters recall results to mitigate SSB and compute costs. Domain Adaptation enhances model robustness by assigning pseudo-labels to unexposed samples. Unbiased Distillation uses exposure-independent scores from Domain Adaptation to implement unbiased distillation for the pre-ranking model. The framework focuses on optimizing pre-ranking while maintaining training efficiency. We introduce new metrics for pre-ranking evaluation, while experiments confirm the effectiveness of our framework. Our framework is also deployed in real industrial systems.
Computational marketing has become increasingly important in today's digital world, facing challenges such as massive heterogeneous data, multi-channel customer journeys, and limited marketing budgets. In this paper, we propose a general framework for marketing AI systems, the Neural Optimization with Adaptive Heuristics (NOAH) framework. NOAH is the first general framework for marketing optimization that considers both to-business (2B) and to-consumer (2C) products, as well as both owned and paid channels. We describe key modules of the NOAH framework, including prediction, optimization, and adaptive heuristics, providing examples for bidding and content optimization. We then detail the successful application of NOAH to LinkedIn's email marketing system, showcasing significant wins over the legacy ranking system. Additionally, we share details and insights that are broadly useful, particularly on: (i) addressing delayed feedback with lifetime value, (ii) performing large-scale linear programming with randomization, (iii) improving retrieval with audience expansion, (iv) reducing signal dilution in targeting tests, and (v) handling zero-inflated heavy-tail metrics in statistical testing.
Real-time Bidding (RTB) advertisers wish to know in advance the expected cost and yield of ad campaigns to avoid trial-and-error expenses. However, Campaign Performance Forecasting (CPF), a sequence modeling task involving tens of thousands of ad auctions, poses challenges of evolving user interest, auction representation, and long context, making coarse-grained and static-modeling methods sub-optimal. We propose AdVance, a time-aware framework that integrates local auction-level and global campaign-level modeling. User preference and fatigue are disentangled using a time-positioned sequence of clicked items and a concise vector of all displayed items. Cross-attention, conditioned on the fatigue vector, captures the dynamics of user interest toward each candidate ad. Bidders compete with each other, presenting a complete graph similar to the self-attention mechanism. Hence, we employ a Transformer Encoder to compress each auction into embedding by solving auxiliary tasks. These sequential embeddings are then summarized by a conditional state space model (SSM) to comprehend long-range dependencies while maintaining global linear complexity. Considering the irregular time intervals between auctions, we make SSM's parameters dependent on the current auction embedding and the time interval. We further condition SSM's global predictions on the accumulation of local results. Extensive evaluations and ablation studies demonstrate its superiority over state-of-the-art methods. AdVance has been deployed on the Tencent Advertising platform, and A/B tests show a remarkable 4.5% uplift in Average Revenue per User (ARPU).
Efficient and accurate product relevance assessment is critical for user experiences and business success. Training a proficient relevance assessment model requires high-quality query-product pairs, often obtained through negative sampling strategies. Unfortunately, current methods introduce pooling bias by mistakenly sampling false negatives, diminishing performance and business impact. To address this, we present Bias-mitigating Hard Negative Sampling (BHNS), a novel negative sampling strategy tailored to identify and adjust for false negatives, building upon our original False Negative Estimation algorithm. Our experiments in the Instacart search setting confirm BHNS as effective for practical e-commerce use. Furthermore, comparative analyses on public dataset showcase its domain-agnostic potential for diverse applications.
In recommender systems, reinforcement learning solutions have shown promising results in optimizing the interaction sequence between users and the system over the long-term performance. For practical reasons, the policy's actions are typically designed as recommending a list of items to handle users' frequent and continuous browsing requests more efficiently. In this list-wise recommendation scenario, the user state is updated upon every request in the corresponding MDP formulation. However, this request-level formulation is essentially inconsistent with the user's item-level behavior. In this study, we demonstrate that an item-level optimization approach can better utilize item characteristics and optimize the policy's performance even under the request-level MDP. We support this claim by comparing the performance of standard request-level methods with the proposed item-level actor-critic framework in both simulation and online experiments. Furthermore, we show that a reward-based future decomposition strategy can better express the item-wise future impact and improve the recommendation accuracy in the long term. To achieve a more thorough understanding of the decomposition strategy, we propose a model-based re-weighting framework with adversarial learning that further boost the performance and investigate its correlation with the reward-based strategy.
As the non-fungible token (NFT) market flourishes, price prediction emerges as a pivotal direction for investors gaining valuable insight to maximize returns. However, existing works suffer from a lack of practical definitions and standardized evaluations, limiting their practical application. Moreover, the influence of users' multi-behaviour transactions that are publicly accessible on NFT price is still not explored and exhibits challenges. In this paper, we address these gaps by presenting a practical and hierarchical problem definition. This approach unifies both collection-level and token-level task and evaluation methods, which cater to varied practical requirements of investors. To further understand the impact of user behaviours on the variation of NFT price, we propose a general wallet profiling framework and develop a COmmunity enhanced Multi-bEhavior Transaction graph model, named COMET. COMET profiles wallets with a comprehensive view and considers the impact of diverse relations and interactions within the NFT ecosystem on NFT price variations, thereby improving prediction performance. Extensive experiments conducted in our deployed system demonstrate the superiority of COMET, underscoring its potential in the insight toolkit for NFT investors.
In the realm of recommender systems, the ubiquitous adoption of deep neural networks has emerged as a dominant paradigm for modeling diverse business objectives. As user bases continue to expand, the necessity of personalization and frequent model updates have assumed paramount significance to ensure the delivery of relevant and refreshed experiences to a diverse array of members. In this work, we introduce an innovative meta-learning solution tailored to the personalization of models for individual members and other entities, coupled with the frequent updates based on the latest user interaction signals. Specifically, we leverage the Model-Agnostic Meta Learning (MAML) algorithm to adapt per-task sub-networks using recent user interaction data. Given the near infeasibility of productionizing original MAML-based models in online recommendation systems, we propose an efficient strategy to operationalize meta-learned sub-networks in production, which involves transforming them into fixed-sized vectors, termed meta embeddings, thereby enabling the seamless deployment of models with hundreds of billions of parameters for online serving. Through extensive experimentation on production data drawn from various applications at LinkedIn, we demonstrate that the proposed solution consistently outperforms the best performing baseline models of those applications, including strong baselines such as using wide-and-deep ID based personalization approach. Our approach has enabled the deployment of a range of highly personalized AI models across diverse LinkedIn applications, leading to substantial improvements in business metrics as well as refreshed experience for our members.