arXiv subjects

Chen Zhu

Publications and source records attributed to Chen Zhu.

At least 73 records · Page 4Linked to original sources

arXiv2024

DISCO: A Hierarchical Disentangled Cognitive Diagnosis Framework for Interpretable Job Recommendation

The rapid development of online recruitment platforms has created unprecedented opportunities for job seekers while concurrently posing the significant challenge of quickly and accurately pinpointing positions that align with their skills and preferences. Job recommendation systems have significantly alleviated the extensive search burden for job seekers by optimizing user engagement metrics, such as clicks and applications, thus achieving notable success. In recent years, a substantial amount of research has been devoted to developing effective job recommendation models, primarily focusing on text-matching based and behavior modeling based methods. While these approaches have realized impressive outcomes, it is imperative to note that research on the explainability of recruitment recommendations remains profoundly unexplored. To this end, in this paper, we propose DISCO, a hierarchical Disentanglement based Cognitive diagnosis framework, aimed at flexibly accommodating the underlying representation learning model for effective and interpretable job recommendations. Specifically, we first design a hierarchical representation disentangling module to explicitly mine the hierarchical skill-related factors implied in hidden representations of job seekers and jobs. Subsequently, we propose level-aware association modeling to enhance information communication and robust representation learning both inter- and intra-level, which consists of the interlevel knowledge influence module and the level-wise contrastive learning. Finally, we devise an interaction diagnosis module incorporating a neural diagnosis function for effectively modeling the multi-level recruitment interaction process between job seekers and jobs, which introduces the cognitive measurement theory.

cs.IR↗

arXiv2024

Smart Navigation System for Parking Assignment at Large Events: Incorporating Heterogeneous Driver Characteristics

Parking challenges escalate significantly during large events such as concerts and sports games, yet few studies address dynamic parking lot assignments in these occasions. This paper introduces a smart navigation system designed to optimize parking assignments efficiently during major events, employing a mixed search algorithm that considers diverse drivers characteristics. We validated our system through simulations conducted in Berkeley, CA during the "Big Game" showcasing the advantages of our novel parking assignment approach.

cs.HC↗

arXiv2024

Airport Delay Prediction with Temporal Fusion Transformers

Since flight delay hurts passengers, airlines, and airports, its prediction becomes crucial for the decision-making of all stakeholders in the aviation industry and thus has been attempted by various previous research. However, previous delay predictions are often categorical and at a highly aggregated level. To improve that, this study proposes to apply the novel Temporal Fusion Transformer model and predict numerical airport arrival delays at quarter hour level for U.S. top 30 airports. Inputs to our model include airport demand and capacity forecasts, historic airport operation efficiency information, airport wind and visibility conditions, as well as enroute weather and traffic conditions. The results show that our model achieves satisfactory performance measured by small prediction errors on the test set. In addition, the interpretability analysis of the model outputs identifies the important input factors for delay prediction.

cs.LG↗

arXiv2024

The Perfect Blend: Redefining RLHF with Mixture of Judges

Reinforcement learning from human feedback (RLHF) has become the leading approach for fine-tuning large language models (LLM). However, RLHF has limitations in multi-task learning (MTL) due to challenges of reward hacking and extreme multi-objective optimization (i.e., trade-off of multiple and/or sometimes conflicting objectives). Applying RLHF for MTL currently requires careful tuning of the weights for reward model and data combinations. This is often done via human intuition and does not generalize. In this work, we introduce a novel post-training paradigm which we called Constrained Generative Policy Optimization (CGPO). The core of CGPO is Mixture of Judges (MoJ) with cost-efficient constrained policy optimization with stratification, which can identify the perfect blend in RLHF in a principled manner. It shows strong empirical results with theoretical guarantees, does not require extensive hyper-parameter tuning, and is plug-and-play in common post-training pipelines. Together, this can detect and mitigate reward hacking behaviors while reaching a pareto-optimal point across an extremely large number of objectives. Our empirical evaluations demonstrate that CGPO significantly outperforms standard RLHF algorithms like PPO and DPO across various tasks including general chat, STEM questions, instruction following, and coding. Specifically, CGPO shows improvements of 7.4% in AlpacaEval-2 (general chat), 12.5% in Arena-Hard (STEM & reasoning), and consistent gains in other domains like math and coding. Notably, PPO, while commonly used, is prone to severe reward hacking in popular coding benchmarks, which CGPO successfully addresses. This breakthrough in RLHF not only tackles reward hacking and extreme multi-objective optimization challenges but also advances the state-of-the-art in aligning general-purpose LLMs for diverse applications.

cs.LG↗

arXiv2024

Deep Reinforcement Learning for Real-Time Ground Delay Program Revision and Corresponding Flight Delay Assignments

This paper explores the optimization of Ground Delay Programs (GDP), a prevalent Traffic Management Initiative used in Air Traffic Management (ATM) to reconcile capacity and demand discrepancies at airports. Employing Reinforcement Learning (RL) to manage the inherent uncertainties in the national airspace system-such as weather variability, fluctuating flight demands, and airport arrival rates-we developed two RL models: Behavioral Cloning (BC) and Conservative Q-Learning (CQL). These models are designed to enhance GDP efficiency by utilizing a sophisticated reward function that integrates ground and airborne delays and terminal area congestion. We constructed a simulated single-airport environment, SAGDP_ENV, which incorporates real operational data along with predicted uncertainties to facilitate realistic decision-making scenarios. Utilizing the whole year 2019 data from Newark Liberty International Airport (EWR), our models aimed to preemptively set airport program rates. Despite thorough modeling and simulation, initial outcomes indicated that the models struggled to learn effectively, attributed potentially to oversimplified environmental assumptions. This paper discusses the challenges encountered, evaluates the models' performance against actual operational data, and outlines future directions to refine RL applications in ATM.

cs.LG↗

arXiv2024

Flight Path Optimization with Optimal Control Method

This paper is based on a crucial issue in the aviation world: how to optimize the trajectory and controls given to the aircraft in order to optimize flight time and fuel consumption. This study aims to provide elements of a response to this problem and to define, under certain simplifying assumptions, an optimal response, using Constrained Finite Time Optimal Control(CFTOC). The first step is to define the dynamic model of the aircraft in accordance with the controllable inputs and wind disturbances. Then we will identify a precise objective in terms of optimization and implement an optimization program to solve it under the circumstances of simulated real flight situation. Finally, the optimization result is validated and discussed by different scenarios.

math.OC↗

arXiv2024

LiRank: Industrial Large Scale Ranking Models at LinkedIn

We present LiRank, a large-scale ranking framework at LinkedIn that brings to production state-of-the-art modeling architectures and optimization methods. We unveil several modeling improvements, including Residual DCN, which adds attention and residual connections to the famous DCNv2 architecture. We share insights into combining and tuning SOTA architectures to create a unified model, including Dense Gating, Transformers and Residual DCN. We also propose novel techniques for calibration and describe how we productionalized deep learning based explore/exploit methods. To enable effective, production-grade serving of large ranking models, we detail how to train and compress models using quantization and vocabulary compression. We provide details about the deployment setup for large-scale use cases of Feed ranking, Jobs Recommendations, and Ads click-through rate (CTR) prediction. We summarize our learnings from various A/B tests by elucidating the most effective technical approaches. These ideas have contributed to relative metrics improvements across the board at LinkedIn: +0.5% member sessions in the Feed, +1.76% qualified job applications for Jobs search and recommendations, and +4.3% for Ads CTR. We hope this work can provide practical insights and solutions for practitioners interested in leveraging large-scale deep ranking systems.

cs.LG↗

arXiv2024

Nemotron-4 340B Technical Report

We release the Nemotron-4 340B model family, including Nemotron-4-340B-Base, Nemotron-4-340B-Instruct, and Nemotron-4-340B-Reward. Our models are open access under the NVIDIA Open Model License Agreement, a permissive model license that allows distribution, modification, and use of the models and its outputs. These models perform competitively to open access models on a wide range of evaluation benchmarks, and were sized to fit on a single DGX H100 with 8 GPUs when deployed in FP8 precision. We believe that the community can benefit from these models in various research studies and commercial applications, especially for generating synthetic data to train smaller language models. Notably, over 98% of data used in our model alignment process is synthetically generated, showcasing the effectiveness of these models in generating synthetic data. To further support open research and facilitate model development, we are also open-sourcing the synthetic data generation pipeline used in our model alignment process.

cs.CL↗

arXiv2024

Generative Organizational Behavior Simulation using Large Language Model based Autonomous Agents: A Holacracy Perspective

In this paper, we present the technical details and periodic findings of our project, CareerAgent, which aims to build a generative simulation framework for a Holacracy organization using Large Language Model-based Autonomous Agents. Specifically, the simulation framework includes three phases: construction, execution, and evaluation, and it incorporates basic characteristics of individuals, organizations, tasks, and meetings. Through our simulation, we obtained several interesting findings. At the organizational level, an increase in the average values of management competence and functional competence can reduce overall members' stress levels, but it negatively impacts deeper organizational performance measures such as average task completion. At the individual level, both competences can improve members' work performance. From the analysis of social networks, we found that highly competent members selectively participate in certain tasks and take on more responsibilities. Over time, small sub-communities form around these highly competent members within the holacracy. These findings contribute theoretically to the study of organizational science and provide practical insights for managers to understand the organization dynamics.

cs.CY↗

arXiv2024

Fair Resource Allocation for Probabilistic Semantic Communication in IIoT

In this paper, the problem of minimum rate maximization for probabilistic semantic communication (PSCom) in industrial Internet of Things (IIoT) is investigated. In the considered model, users employ semantic information extraction techniques to compress the original data before sending it to the base station (BS). During this semantic compression process, knowledge graphs are employed to represent the semantic information, and the probability graph sharing between users and the BS is utilized to further compress the knowledge graph. The semantic compression process can significantly reduce the transmitted data size, but it inevitably introduces additional computation overhead. Considering the limited power budget of the user, we formulate a joint communication and computation optimization problem is formulated aiming to maximize the minimum equivalent rate among all users while meeting total power and semantic compression ratio constraints. To address this problem, two algorithms with different computational complexities are proposed to obtain suboptimal solutions. One algorithm is based on a prorate distribution of transmission power, while the other traverses the combinations of semantic compression ratios among all users. In both algorithms, bisection is employed in order to achieve the greatest minimum equivalent rate. The simulation results validate the effectiveness of the proposed algorithms.

cs.IT↗

arXiv2024

Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning

Job recommender systems are crucial for aligning job opportunities with job-seekers in online job-seeking. However, users tend to adjust their job preferences to secure employment opportunities continually, which limits the performance of job recommendations. The inherent frequency of preference drift poses a challenge to promptly and precisely capture user preferences. To address this issue, we propose a novel session-based framework, BISTRO, to timely model user preference through fusion learning of semantic and behavioral information. Specifically, BISTRO is composed of three stages: 1) coarse-grained semantic clustering, 2) fine-grained job preference extraction, and 3) personalized top-$k$ job recommendation. Initially, BISTRO segments the user interaction sequence into sessions and leverages session-based semantic clustering to achieve broad identification of person-job matching. Subsequently, we design a hypergraph wavelet learning method to capture the nuanced job preference drift. To mitigate the effect of noise in interactions caused by frequent preference drift, we innovatively propose an adaptive wavelet filtering technique to remove noisy interaction. Finally, a recurrent neural network is utilized to analyze session-based interaction for inferring personalized preferences. Extensive experiments on three real-world offline recruitment datasets demonstrate the significant performances of our framework. Significantly, BISTRO also excels in online experiments, affirming its effectiveness in live recruitment settings. This dual success underscores the robustness and adaptability of BISTRO. The source code is available at https://github.com/Applied-Machine-Learning-Lab/BISTRO.

cs.IR↗

arXiv2024

A Survey on Large Language Models for Recommendation

Large Language Models (LLMs) have emerged as powerful tools in the field of Natural Language Processing (NLP) and have recently gained significant attention in the domain of Recommendation Systems (RS). These models, trained on massive amounts of data using self-supervised learning, have demonstrated remarkable success in learning universal representations and have the potential to enhance various aspects of recommendation systems by some effective transfer techniques such as fine-tuning and prompt tuning, and so on. The crucial aspect of harnessing the power of language models in enhancing recommendation quality is the utilization of their high-quality representations of textual features and their extensive coverage of external knowledge to establish correlations between items and users. To provide a comprehensive understanding of the existing LLM-based recommendation systems, this survey presents a taxonomy that categorizes these models into two major paradigms, respectively Discriminative LLM for Recommendation (DLLM4Rec) and Generative LLM for Recommendation (GLLM4Rec), with the latter being systematically sorted out for the first time. Furthermore, we systematically review and analyze existing LLM-based recommendation systems within each paradigm, providing insights into their methodologies, techniques, and performance. Additionally, we identify key challenges and several valuable findings to provide researchers and practitioners with inspiration. We have also created a GitHub repository to index relevant papers on LLMs for recommendation, https://github.com/WLiK/LLM4Rec.

cs.IR↗

arXiv2024

OPTune: Efficient Online Preference Tuning

Reinforcement learning with human feedback~(RLHF) is critical for aligning Large Language Models (LLMs) with human preference. Compared to the widely studied offline version of RLHF, \emph{e.g.} direct preference optimization (DPO), recent works have shown that the online variants achieve even better alignment. However, online alignment requires on-the-fly generation of new training data, which is costly, hard to parallelize, and suffers from varying quality and utility. In this paper, we propose a more efficient data exploration strategy for online preference tuning (OPTune), which does not rely on human-curated or pre-collected teacher responses but dynamically samples informative responses for on-policy preference alignment. During data generation, OPTune only selects prompts whose (re)generated responses can potentially provide more informative and higher-quality training signals than the existing responses. In the training objective, OPTune reweights each generated response (pair) by its utility in improving the alignment so that learning can be focused on the most helpful samples. Throughout our evaluations, OPTune'd LLMs maintain the instruction-following benefits provided by standard preference tuning whilst enjoying 1.27-1.56x faster training speed due to the efficient data exploration strategy.

cs.LG↗

arXiv2024

Smart Navigation System for Parking Assignment at Large Events: Incorporating Heterogeneous Driver Characteristics

Parking challenges escalate significantly during large events such as concerts or sports games, yet few studies address dynamic parking lot assignments for such occasions. This paper introduces a smart navigation system designed to optimize parking assignments swiftly during large events, utilizing a mixed search algorithm that accounts for the heterogeneous characteristics of drivers. We conducted simulations in the Berkeley city area during the "Big Game" to validate our system and demonstrate the benefits of our innovative parking assignment approach.

cs.RO↗

arXiv2024

Linear correlations of Gibbs free energy for rare earth element oxide, hydroxide, chloride, fluoride, carbonate, and ferrite minerals and crystalline solids

Rare Earth Elements (REE) are critical minerals (metals) for the transition from fossil fuels to renewable and clean energy. Accurate thermodynamic properties of REE minerals and other crystalline solids are crucial for geochemical modeling of the solubility, speciation, and transport of REE in ore formation, extraction, chemical processing, and recycling processes. However, the Gibbs free energies of formation (DGof, REEX) for these solids from different sources vary by 10s kJ/mol. We applied the Sverjensky linear free energy relationship (LFER) to evaluate their internal consistency and predict the unavailable DGof of the REE solids. By considering both the effects of ionic radius size and corresponding aqueous ion properties, the Sverjensky LFER allows estimates with much accuracy and precision. Here, rREEZ+ represents the Shannon-Prewitt ionic radii of REEZ+, and DGon, REEZ+ denotes the non-solvation contribution to the DGof of the aqueous REEZ+ ion. X represents the remainder of the compounds. In this study, the parameters aREEX, bREEX, and beta REEX were regressed from DGof compilations in the literature for 13 isostructural families. Based on these linear relationships, we recommend a set of internally consistent DGof, REEX for 119 end-members of REE oxides, hydroxides, chlorides, fluorides, carbonates, hydrous carbonates, and ferrites. These DGof, REEX are combined with experimental or predicted values of So, Vo, and Cpo from the literature and incorporated into a new SUPCRT database, which allows the calculations of thermodynamic properties to high P-T conditions (e.g., up to 1000 oC and 5 kb).

physics.geo-ph↗

arXiv2024

Towards Efficient Resume Understanding: A Multi-Granularity Multi-Modal Pre-Training Approach

In the contemporary era of widespread online recruitment, resume understanding has been widely acknowledged as a fundamental and crucial task, which aims to extract structured information from resume documents automatically. Compared to the traditional rule-based approaches, the utilization of recently proposed pre-trained document understanding models can greatly enhance the effectiveness of resume understanding. The present approaches have, however, disregarded the hierarchical relations within the structured information presented in resumes, and have difficulty parsing resumes in an efficient manner. To this end, in this paper, we propose a novel model, namely ERU, to achieve efficient resume understanding. Specifically, we first introduce a layout-aware multi-modal fusion transformer for encoding the segments in the resume with integrated textual, visual, and layout information. Then, we design three self-supervised tasks to pre-train this module via a large number of unlabeled resumes. Next, we fine-tune the model with a multi-granularity sequence labeling task to extract structured information from resumes. Finally, extensive experiments on a real-world dataset clearly demonstrate the effectiveness of ERU.

cs.CL↗

arXiv2024

Hashing Beam Training for Near-Field Communications

In this paper, we investigate the millimeter-wave (mmWave) near-field beam training problem to find the correct beam direction. In order to address the high complexity and low identification accuracy of existing beam training techniques, we propose an efficient hashing multi-arm beam (HMB) training scheme for the near-field scenario. Specifically, we first design a set of sparse bases based on the polar domain sparsity of the near-field channel. Then, the random hash functions are chosen to construct the near-field multi-arm beam training codebook. Each multi-arm beam codeword is scanned in a time slot until all the predefined codewords are traversed. Finally, the soft decision and voting methods are applied to distinguish the signal from different base stations and obtain correctly aligned beams. Simulation results show that our proposed near-field HMB training method can reduce the beam training overhead to the logarithmic level, and achieve 96.4% identification accuracy of exhaustive beam training. Moreover, we also verify applicability under the far-field scenario.

cs.IT↗

arXiv2024

The Solution for the ICCV 2023 1st Scientific Figure Captioning Challenge

In this paper, we propose a solution for improving the quality of captions generated for figures in papers. We adopt the approach of summarizing the textual content in the paper to generate image captions. Throughout our study, we encounter discrepancies in the OCR information provided in the official dataset. To rectify this, we employ the PaddleOCR toolkit to extract OCR information from all images. Moreover, we observe that certain textual content in the official paper pertains to images that are not relevant for captioning, thereby introducing noise during caption generation. To mitigate this issue, we leverage LLaMA to extract image-specific information by querying the textual content based on image mentions, effectively filtering out extraneous information. Additionally, we recognize a discrepancy between the primary use of maximum likelihood estimation during text generation and the evaluation metrics such as ROUGE employed to assess the quality of generated captions. To bridge this gap, we integrate the BRIO model framework, enabling a more coherent alignment between the generation and evaluation processes. Our approach ranked first in the final test with a score of 4.49.

cs.CV↗