Haoyuan Hu

Lixia Wu, Haomin Wen, Haoyuan Hu et al.

Real-world last-mile delivery 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 delivery dataset exists to support research in this field. In this paper, we introduce \texttt{LaDe}, the first publicly available last-mile delivery 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, such as its location and time requirements, as well as task-event information, which records when and where the courier is while events such as task-accept and task-finish events happen. (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 homepage is publicly available at https://huggingface.co/datasets/Cainiao-AI/LaDe.

Lixia Wu, Jianlin Liu, Junhong Lou et al.

Text-based delivery addresses, as the data foundation for logistics systems, contain abundant and crucial location information. How to effectively encode the delivery address is a core task to boost the performance of downstream tasks in the logistics system. Pre-trained Models (PTMs) designed for Natural Language Process (NLP) have emerged as the dominant tools for encoding semantic information in text. Though promising, those NLP-based PTMs fall short of encoding geographic knowledge in the delivery address, which considerably trims down the performance of delivery-related tasks in logistic systems such as Cainiao. To tackle the above problem, we propose a domain-specific pre-trained model, named G2PTL, a Geography-Graph Pre-trained model for delivery address in Logistics field. G2PTL combines the semantic learning capabilities of text pre-training with the geographical-relationship encoding abilities of graph modeling. Specifically, we first utilize real-world logistics delivery data to construct a large-scale heterogeneous graph of delivery addresses, which contains abundant geographic knowledge and delivery information. Then, G2PTL is pre-trained with subgraphs sampled from the heterogeneous graph. Comprehensive experiments are conducted to demonstrate the effectiveness of G2PTL through four downstream tasks in logistics systems on real-world datasets. G2PTL has been deployed in production in Cainiao's logistics system, which significantly improves the performance of delivery-related tasks. The code of G2PTL is available at https://huggingface.co/Cainiao-AI/G2PTL.

Xiaowei Mao, Haomin Wen, Hengrui Zhang et al.

Pick-up and Delivery Route Prediction (PDRP), which aims to estimate the future service route of a worker given his current task pool, has received rising attention in recent years. Deep neural networks based on supervised learning have emerged as the dominant model for the task because of their powerful ability to capture workers' behavior patterns from massive historical data. Though promising, they fail to introduce the non-differentiable test criteria into the training process, leading to a mismatch in training and test criteria. Which considerably trims down their performance when applied in practical systems. To tackle the above issue, we present the first attempt to generalize Reinforcement Learning (RL) to the route prediction task, leading to a novel RL-based framework called DRL4Route. It combines the behavior-learning abilities of previous deep learning models with the non-differentiable objective optimization ability of reinforcement learning. DRL4Route can serve as a plug-and-play component to boost the existing deep learning models. Based on the framework, we further implement a model named DRL4Route-GAE for PDRP in logistic service. It follows the actor-critic architecture which is equipped with a Generalized Advantage Estimator that can balance the bias and variance of the policy gradient estimates, thus achieving a more optimal policy. Extensive offline experiments and the online deployment show that DRL4Route-GAE improves Location Square Deviation (LSD) by 0.9%-2.7%, and Accuracy@3 (ACC@3) by 2.4%-3.2% over existing methods on the real-world dataset.

Jinyun Li, Huiwen Zheng, Yuanlin Liu et al.

Large-scale commercial platforms usually involve numerous business domains for diverse business strategies and expect their recommendation systems to provide click-through rate (CTR) predictions for multiple domains simultaneously. Existing promising and widely-used multi-domain models discover domain relationships by explicitly constructing domain-specific networks, but the computation and memory boost significantly with the increase of domains. To reduce computational complexity, manually grouping domains with particular business strategies is common in industrial applications. However, this pre-defined data partitioning way heavily relies on prior knowledge, and it may neglect the underlying data distribution of each domain, hence limiting the model's representation capability. Regarding the above issues, we propose an elegant and flexible multi-distribution modeling paradigm, named Adaptive Distribution Hierarchical Model (AdaptDHM), which is an end-to-end optimization hierarchical structure consisting of a clustering process and classification process. Specifically, we design a distribution adaptation module with a customized dynamic routing mechanism. Instead of introducing prior knowledge for pre-defined data allocation, this routing algorithm adaptively provides a distribution coefficient for each sample to determine which cluster it belongs to. Each cluster corresponds to a particular distribution so that the model can sufficiently capture the commonalities and distinctions between these distinct clusters. Extensive experiments on both public and large-scale Alibaba industrial datasets verify the effectiveness and efficiency of AdaptDHM: Our model achieves impressive prediction accuracy and its time cost during the training stage is more than 50% less than that of other models.

Qixin Zhang, Zengde Deng, Zaiyi Chen et al.

In this paper, we revisit the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, which finds wide real-world applications in the domain of machine learning, economics, and operations research. At first, we present the Meta-MFW algorithm achieving a $1/e$-regret of $O(\sqrt{T})$ at the cost of $T^{3/2}$ stochastic gradient evaluations per round. As far as we know, Meta-MFW is the first algorithm to obtain $1/e$-regret of $O(\sqrt{T})$ for the online non-monotone continuous DR-submodular maximization problem over a down-closed convex set. Furthermore, in sharp contrast with ODC algorithm \citep{thang2021online}, Meta-MFW relies on the simple online linear oracle without discretization, lifting, or rounding operations. Considering the practical restrictions, we then propose the Mono-MFW algorithm, which reduces the per-function stochastic gradient evaluations from $T^{3/2}$ to 1 and achieves a $1/e$-regret bound of $O(T^{4/5})$. Next, we extend Mono-MFW to the bandit setting and propose the Bandit-MFW algorithm which attains a $1/e$-regret bound of $O(T^{8/9})$. To the best of our knowledge, Mono-MFW and Bandit-MFW are the first sublinear-regret algorithms to explore the one-shot and bandit setting for online non-monotone continuous DR-submodular maximization problem over a down-closed convex set, respectively. Finally, we conduct numerical experiments on both synthetic and real-world datasets to verify the effectiveness of our methods.

Qixin Zhang, Zengde Deng, Xiangru Jian et al.

Maximizing a monotone submodular function is a fundamental task in machine learning, economics, and statistics. In this paper, we present two communication-efficient decentralized online algorithms for the monotone continuous DR-submodular maximization problem, both of which reduce the number of per-function gradient evaluations and per-round communication complexity from $T^{3/2}$ to $1$. The first one, One-shot Decentralized Meta-Frank-Wolfe (Mono-DMFW), achieves a $(1-1/e)$-regret bound of $O(T^{4/5})$. As far as we know, this is the first one-shot and projection-free decentralized online algorithm for monotone continuous DR-submodular maximization. Next, inspired by the non-oblivious boosting function \citep{zhang2022boosting}, we propose the Decentralized Online Boosting Gradient Ascent (DOBGA) algorithm, which attains a $(1-1/e)$-regret of $O(\sqrt{T})$. To the best of our knowledge, this is the first result to obtain the optimal $O(\sqrt{T})$ against a $(1-1/e)$-approximation with only one gradient inquiry for each local objective function per step. Finally, various experimental results confirm the effectiveness of the proposed methods.

Yuwei Chen, Zengde Deng, Yinzhi Zhou et al.

This paper studies the online stochastic resource allocation problem (RAP) with chance constraints. The online RAP is a 0-1 integer linear programming problem where the resource consumption coefficients are revealed column by column along with the corresponding revenue coefficients. When a column is revealed, the corresponding decision variables are determined instantaneously without future information. Moreover, in online applications, the resource consumption coefficients are often obtained by prediction. To model their uncertainties, we take the chance constraints into the consideration. To the best of our knowledge, this is the first time chance constraints are introduced in the online RAP problem. Assuming that the uncertain variables have known Gaussian distributions, the stochastic RAP can be transformed into a deterministic but nonlinear problem with integer second-order cone constraints. Next, we linearize this nonlinear problem and analyze the performance of vanilla online primal-dual algorithm for solving the linearized stochastic RAP. Under mild technical assumptions, the optimality gap and constraint violation are both on the order of $\sqrt{n}$. Then, to further improve the performance of the algorithm, several modified online primal-dual algorithms with heuristic corrections are proposed. Finally, extensive numerical experiments on both synthetic and real data demonstrate the applicability and effectiveness of our methods.

Minfang Lu, Yuchen Jiang, Huihui Dong et al.

In large-scale industrial e-commerce, the efficiency of an online recommendation system is crucial in delivering highly relevant item/content advertising that caters to diverse business scenarios. However, most existing studies focus solely on item advertising, neglecting the significance of content advertising. This oversight results in inconsistencies within the multi-entity structure and unfair retrieval. Furthermore, the challenge of retrieving top-k advertisements from multi-entity advertisements across different domains adds to the complexity. Recent research proves that user-entity behaviors within different domains exhibit characteristics of differentiation and homogeneity. Therefore, the multi-domain matching models typically rely on the hybrid-experts framework with domain-invariant and domain-specific representations. Unfortunately, most approaches primarily focus on optimizing the combination mode of different experts, failing to address the inherent difficulty in optimizing the expert modules themselves. The existence of redundant information across different domains introduces interference and competition among experts, while the distinct learning objectives of each domain lead to varying optimization challenges among experts. To tackle these issues, we propose robust representation learning for the unified online top-k recommendation. Our approach constructs unified modeling in entity space to ensure data fairness. The robust representation learning employs domain adversarial learning and multi-view wasserstein distribution learning to learn robust representations. Moreover, the proposed method balances conflicting objectives through the homoscedastic uncertainty weights and orthogonality constraints. Various experiments validate the effectiveness and rationality of our proposed method, which has been successfully deployed online to serve real business scenarios.

HaoYuan Hu, Mingcong Lu, Di Luo et al.

Multi-turn dialogues and context-intensive tasks challenge Large Language Models (LLMs) to integrate long histories without sacrificing generation quality. Although prefix LLMs can better exploit historical context via bidirectional attention on prefix tokens, they are rarely used in practice because multi-turn training requires many duplicated triplets, and its bidirectional prefix prevents KV-cache reuse at inference time, driving up high cost and latency. To retain the contextual understanding of prefix mask while preserving the inference-time efficiency of causal mask, we introduce Intermittent Semi-working Mask (ISM), a masking scheme that injects sparse bidirectional attention into the causal backbone. ISM alternates bidirectional attention over query segments with unidirectional attention over answer segments, enabling the synthesis of in-context while preserving global causality. This design eliminates triplet expansion during training and maintains KV-cache reuse during inference, yielding latency comparable to standard causal LLMs. ISM is architecture-agnostic and parameter-free, adding only minimal latency. Across extensive evaluations, ISM outperforms causal baselines not only on multi-turn dialogue, but also on context-intensive tasks like mathematical reasoning.

Youfang Lin, Jinji Fu, Haomin Wen et al.

In Location-Based Services (LBS), such as food delivery, a fundamental task is segmenting Areas of Interest (AOIs), aiming at partitioning the urban geographical spaces into non-overlapping regions. Traditional AOI segmentation algorithms primarily rely on road networks to partition urban areas. While promising in modeling the geo-semantics, road network-based models overlooked the service-semantic goals (e.g., workload equality) in LBS service. In this paper, we point out that the AOI segmentation problem can be naturally formulated as a Markov Decision Process (MDP), which gradually chooses a nearby AOI for each grid in the current AOI's border. Based on the MDP, we present the first attempt to generalize Deep Reinforcement Learning (DRL) for AOI segmentation, leading to a novel DRL-based framework called DRL4AOI. The DRL4AOI framework introduces different service-semantic goals in a flexible way by treating them as rewards that guide the AOI generation. To evaluate the effectiveness of DRL4AOI, we develop and release an AOI segmentation system. We also present a representative implementation of DRL4AOI - TrajRL4AOI - for AOI segmentation in the logistics service. It introduces a Double Deep Q-learning Network (DDQN) to gradually optimize the AOI generation for two specific semantic goals: i) trajectory modularity, i.e., maximize tightness of the trajectory connections within an AOI and the sparsity of connections between AOIs, ii) matchness with the road network, i.e., maximizing the matchness between AOIs and the road network. Quantitative and qualitative experiments conducted on synthetic and real-world data demonstrate the effectiveness and superiority of our method. The code and system is publicly available at https://github.com/Kogler7/AoiOpt.

Kaiyi Zhang, Ang Lv, Jinpeng Li et al.

Reinforcement learning with verifiable rewards (RLVR) is a promising approach for improving the complex reasoning abilities of large language models (LLMs). However, current RLVR methods face two significant challenges: the near-miss reward problem, where a small mistake can invalidate an otherwise correct reasoning process, greatly hindering training efficiency; and exploration stagnation, where models tend to focus on solutions within their ``comfort zone,'' lacking the motivation to explore potentially more effective alternatives. To address these challenges, we propose StepHint, a novel RLVR algorithm that utilizes multi-level stepwise hints to help models explore the solution space more effectively. StepHint generates valid reasoning chains from stronger models and partitions these chains into reasoning steps using our proposed adaptive partitioning method. The initial few steps are used as hints, and simultaneously, multiple-level hints (each comprising a different number of steps) are provided to the model. This approach directs the model's exploration toward a promising solution subspace while preserving its flexibility for independent exploration. By providing hints, StepHint mitigates the near-miss reward problem, thereby improving training efficiency. Additionally, the external reasoning pathways help the model develop better reasoning abilities, enabling it to move beyond its ``comfort zone'' and mitigate exploration stagnation. StepHint outperforms competitive RLVR enhancement methods across six mathematical benchmarks, while also demonstrating superior generalization and excelling over baselines on out-of-domain benchmarks.

Taoye Yin, Haoyuan Hu, Yaxin Fan et al.

In financial Retrieval-Augmented Generation (RAG) systems, models frequently rely on retrieved documents to generate accurate responses due to the time-sensitive nature of the financial domain. While retrieved documents help address knowledge gaps, model-generated responses still suffer from hallucinations that contradict the retrieved information. To mitigate this inconsistency, we propose a Reinforcement Learning framework enhanced with Fine-grained Knowledge Verification (RLFKV). Our method decomposes financial responses into atomic knowledge units and assesses the correctness of each unit to compute the fine-grained faithful reward. This reward offers more precise optimization signals, thereby improving alignment with the retrieved documents. Additionally, to prevent reward hacking (e.g., overly concise replies), we incorporate an informativeness reward that encourages the policy model to retain at least as many knowledge units as the base model. Experiments conducted on the public Financial Data Description (FDD) task and our newly proposed FDD-ANT dataset demonstrate consistent improvements, confirming the effectiveness of our approach.

Lipeng Xie, Sen Huang, Zhuo Zhang et al.

Reward models are essential for aligning Large Language Models (LLMs) with human values, yet their development is hampered by costly preference datasets and poor interpretability. While recent rubric-based approaches offer transparency, they often lack systematic quality control and optimization, creating a trade-off between scalability and reliability. We address these limitations with a novel, training-free framework built on a key assumption: \textit{evaluation rubrics underlying human preferences exhibit significant generalization ability across diverse queries}, a property that enables remarkable data efficiency. Our two-stage approach first infers high-quality, query-specific rubrics using a validation-guided \textbf{Propose-Evaluate-Revise} pipeline. Second, it generalizes these granular rubrics into a compact, non-redundant core set by maximizing an \textbf{information-theoretic coding rate}. The final output is an interpretable, hierarchical "Theme-Tips" rubric set. Extensive experiments demonstrate the framework's exceptional data efficiency and performance. Critically, using just 70 preference pairs (1.5\% of the source data), our method also empowers smaller models like Qwen3-8B to outperform specialized, fully-trained counterparts. This work pioneers a scalable, interpretable, and data-efficient path for reward modeling.

Fanwei Zhu, Jinke Yu, Zulong Chen et al.

Automated resume information extraction is critical for scaling talent acquisition, yet its real-world deployment faces three major challenges: the extreme heterogeneity of resume layouts and content, the high cost and latency of large language models (LLMs), and the lack of standardized datasets and evaluation tools. In this work, we present a layout-aware and efficiency-optimized framework for automated extraction and evaluation that addresses all three challenges. Our system combines a fine-tuned layout parser to normalize diverse document formats, an inference-efficient LLM extractor based on parallel prompting and instruction tuning, and a robust two-stage automated evaluation framework supported by new benchmark datasets. Extensive experiments show that our framework significantly outperforms strong baselines in both accuracy and efficiency. In particular, we demonstrate that a fine-tuned compact 0.6B LLM achieves top-tier accuracy while significantly reducing inference latency and computational cost. The system is fully deployed in Alibaba's intelligent HR platform, supporting real-time applications across its business units.

Hexian Ni, Tao Lu, Haoyuan Hu et al.

Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human preferences. However, poor feedback- and sample- efficiency still remain the problems that hinder the application of PbRL. In this paper, we present a novel efficient query selection and preference-guided exploration method, called SENIOR, which could select the meaningful and easy-to-comparison behavior segment pairs to improve human feedback-efficiency and accelerate policy learning with the designed preference-guided intrinsic rewards. Our key idea is twofold: (1) We designed a Motion-Distinction-based Selection scheme (MDS). It selects segment pairs with apparent motion and different directions through kernel density estimation of states, which is more task-related and easy for human preference labeling; (2) We proposed a novel preference-guided exploration method (PGE). It encourages the exploration towards the states with high preference and low visits and continuously guides the agent achieving the valuable samples. The synergy between the two mechanisms could significantly accelerate the progress of reward and policy learning. Our experiments show that SENIOR outperforms other five existing methods in both human feedback-efficiency and policy convergence speed on six complex robot manipulation tasks from simulation and four real-worlds.

Hao Zeng, Jiaqi Wang, Avirup Das et al.

Feasible solutions are crucial for Integer Programming (IP) since they can substantially speed up the solving process. In many applications, similar IP instances often exhibit similar structures and shared solution distributions, which can be potentially modeled by deep learning methods. Unfortunately, existing deep-learning-based algorithms, such as Neural Diving and Predict-and-search framework, are limited to generating only partial feasible solutions, and they must rely on solvers like SCIP and Gurobi to complete the solutions for a given IP problem. In this paper, we propose a novel framework that generates complete feasible solutions end-to-end. Our framework leverages contrastive learning to characterize the relationship between IP instances and solutions, and learns latent embeddings for both IP instances and their solutions. Further, the framework employs diffusion models to learn the distribution of solution embeddings conditioned on IP representations, with a dedicated guided sampling strategy that accounts for both constraints and objectives. We empirically evaluate our framework on four typical datasets of IP problems, and show that it effectively generates complete feasible solutions with a high probability (> 89.7 \%) without the reliance of Solvers and the quality of solutions is comparable to the best heuristic solutions from Gurobi. Furthermore, by integrating our method's sampled partial solutions with the CompleteSol heuristic from SCIP, the resulting feasible solutions outperform those from state-of-the-art methods across all datasets, exhibiting a 3.7 to 33.7\% improvement in the gap to optimal values, and maintaining a feasible ratio of over 99.7\% for all datasets.

Peng Li, Lixia Wu, Chaoqun Feng et al.

Real-world scenarios frequently involve multi-objective data-driven optimization problems, characterized by unknown problem coefficients and multiple conflicting objectives. Traditional two-stage methods independently apply a machine learning model to estimate problem coefficients, followed by invoking a solver to tackle the predicted optimization problem. The independent use of optimization solvers and prediction models may lead to suboptimal performance due to mismatches between their objectives. Recent efforts have focused on end-to-end training of predictive models that use decision loss derived from the downstream optimization problem. However, these methods have primarily focused on single-objective optimization problems, thus limiting their applicability. We aim to propose a multi-objective decision-focused approach to address this gap. In order to better align with the inherent properties of multi-objective optimization problems, we propose a set of novel loss functions. These loss functions are designed to capture the discrepancies between predicted and true decision problems, considering solution space, objective space, and decision quality, named landscape loss, Pareto set loss, and decision loss, respectively. Our experimental results demonstrate that our proposed method significantly outperforms traditional two-stage methods and most current decision-focused methods.

Yuan Gao, Yiheng Zhu, Yuanbin Cao et al.

Open Domain Multi-Hop Question Answering (ODMHQA) plays a crucial role in Natural Language Processing (NLP) by aiming to answer complex questions through multi-step reasoning over retrieved information from external knowledge sources. Recently, Large Language Models (LLMs) have demonstrated remarkable performance in solving ODMHQA owing to their capabilities including planning, reasoning, and utilizing tools. However, LLMs may generate off-topic answers when attempting to solve ODMHQA, namely the generated answers are irrelevant to the original questions. This issue of off-topic answers accounts for approximately one-third of incorrect answers, yet remains underexplored despite its significance. To alleviate this issue, we propose the Discriminate->Re-Compose->Re- Solve->Re-Decompose (Dr3) mechanism. Specifically, the Discriminator leverages the intrinsic capabilities of LLMs to judge whether the generated answers are off-topic. In cases where an off-topic answer is detected, the Corrector performs step-wise revisions along the reversed reasoning chain (Re-Compose->Re-Solve->Re-Decompose) until the final answer becomes on-topic. Experimental results on the HotpotQA and 2WikiMultiHopQA datasets demonstrate that our Dr3 mechanism considerably reduces the occurrence of off-topic answers in ODMHQA by nearly 13%, improving the performance in Exact Match (EM) by nearly 3% compared to the baseline method without the Dr3 mechanism.

Jinlei Zhang, Ergang Shan, Lixia Wu et al.

Express systems play important roles in modern major cities. Couriers serving for the express system pick up packages in certain areas of interest (AOI) during a specific time. However, future pick-up requests vary significantly with time. While the assignment results are generally static without changing with time. Using the historical pick-up request number to conduct AOI assignment (or pick-up request assignment) for couriers is thus unreasonable. Moreover, even we can first predict future pick-up requests and then use the prediction results to conduct the assignments, this kind of two-stage method is also impractical and trivial, and exists some drawbacks, such as the best prediction results might not ensure the best clustering results. To solve these problems, we put forward an intelligent end-to-end predict-then-optimize clustering method to simultaneously predict the future pick-up requests of AOIs and assign AOIs to couriers by clustering. At first, we propose a deep learning-based prediction model to predict order numbers on AOIs. Then a differential constrained K-means clustering method is introduced to cluster AOIs based on the prediction results. We finally propose a one-stage end-to-end predict-then-optimize clustering method to assign AOIs to couriers reasonably, dynamically, and intelligently. Results show that this kind of one-stage predict-then-optimize method is beneficial to improve the performance of optimization results, namely the clustering results. This study can provide critical experiences for predict-and-optimize related tasks and intelligent assignment problems in express systems.

Qixin Zhang, Zengde Deng, Zaiyi Chen et al.

In this paper, we revisit Stochastic Continuous Submodular Maximization in both offline and online settings, which can benefit wide applications in machine learning and operations research areas. We present a boosting framework covering gradient ascent and online gradient ascent. The fundamental ingredient of our methods is a novel non-oblivious function $F$ derived from a factor-revealing optimization problem, whose any stationary point provides a $(1-e^{-γ})$-approximation to the global maximum of the $γ$-weakly DR-submodular objective function $f\in C^{1,1}_L(\mathcal{X})$. Under the offline scenario, we propose a boosting gradient ascent method achieving $(1-e^{-γ}-ε^{2})$-approximation after $O(1/ε^2)$ iterations, which improves the $(\frac{γ^2}{1+γ^2})$ approximation ratio of the classical gradient ascent algorithm. In the online setting, for the first time we consider the adversarial delays for stochastic gradient feedback, under which we propose a boosting online gradient algorithm with the same non-oblivious function $F$. Meanwhile, we verify that this boosting online algorithm achieves a regret of $O(\sqrt{D})$ against a $(1-e^{-γ})$-approximation to the best feasible solution in hindsight, where $D$ is the sum of delays of gradient feedback. To the best of our knowledge, this is the first result to obtain $O(\sqrt{T})$ regret against a $(1-e^{-γ})$-approximation with $O(1)$ gradient inquiry at each time step, when no delay exists, i.e., $D=T$. Finally, numerical experiments demonstrate the effectiveness of our boosting methods.

Qixin Zhang, Wenbing Ye, Zaiyi Chen et al.

In this paper, we investigate the online allocation problem of maximizing the overall revenue subject to both lower and upper bound constraints. Compared to the extensively studied online problems with only resource upper bounds, the two-sided constraints affect the prospects of resource consumption more severely. As a result, only limited violations of constraints or pessimistic competitive bounds could be guaranteed. To tackle the challenge, we define a measure of feasibility $ξ^*$ to evaluate the hardness of this problem, and estimate this measurement by an optimization routine with theoretical guarantees. We propose an online algorithm adopting a constructive framework, where we initialize a threshold price vector using the estimation, then dynamically update the price vector and use it for decision-making at each step. It can be shown that the proposed algorithm is $\big(1-O(\frac{\varepsilon}{ξ^*-\varepsilon})\big)$ or $\big(1-O(\frac{\varepsilon}{ξ^*-\sqrt{\varepsilon}})\big)$ competitive with high probability for $ξ^*$ known or unknown respectively. To the best of our knowledge, this is the first result establishing a nearly optimal competitive algorithm for solving two-sided constrained online allocation problems with a high probability of feasibility.

Hao Zeng, Qiong Wu, Kunpeng Han et al.

In this paper, we investigate the online parcel assignment (OPA) problem, in which each stochastically generated parcel needs to be assigned to a candidate route for delivery to minimize the total cost subject to certain business constraints. The OPA problem is challenging due to its stochastic nature: each parcel's candidate routes, which depends on the parcel's origin, destination, weight, etc., are unknown until its order is placed, and the total parcel volume is uncertain in advance. To tackle this challenge, we propose the PPO-OPA algorithm based on deep reinforcement learning that shows competitive performance. More specifically, we introduce a novel Markov Decision Process (MDP) framework to model the OPA problem, and develop a policy gradient algorithm that adopts attention networks for policy evaluation. By designing a dedicated reward function, our proposed algorithm can achieve a lower total cost with smaller violation of constraints, comparing to the traditional method which assigns parcels to candidate routes proportionally. In addition, the performances of our proposed algorithm and the Primal-Dual algorithm are comparable, while the later assumes a known total parcel volume in advance, which is unrealistic in practice.

Lu Duan, Haoyuan Hu, Zili Wu et al.

Balanced order batching problem (BOBP) arises from the process of warehouse picking in Cainiao, the largest logistics platform in China. Batching orders together in the picking process to form a single picking route, reduces travel distance. The reason for its importance is that order picking is a labor intensive process and, by using good batching methods, substantial savings can be obtained. The BOBP is a NP-hard combinational optimization problem and designing a good problem-specific heuristic under the quasi-real-time system response requirement is non-trivial. In this paper, rather than designing heuristics, we propose an end-to-end learning and optimization framework named Balanced Task-orientated Graph Clustering Network (BTOGCN) to solve the BOBP by reducing it to balanced graph clustering optimization problem. In BTOGCN, a task-oriented estimator network is introduced to guide the type-aware heterogeneous graph clustering networks to find a better clustering result related to the BOBP objective. Through comprehensive experiments on single-graph and multi-graphs, we show: 1) our balanced task-oriented graph clustering network can directly utilize the guidance of target signal and outperforms the two-stage deep embedding and deep clustering method; 2) our method obtains an average 4.57m and 0.13m picking distance ("m" is the abbreviation of the meter (the SI base unit of length)) reduction than the expert-designed algorithm on single and multi-graph set and has a good generalization ability to apply in practical scenario.

Yujie Chen, Yu Qian, Yichen Yao et al.

In this paper, we study a courier dispatching problem (CDP) raised from an online pickup-service platform of Alibaba. The CDP aims to assign a set of couriers to serve pickup requests with stochastic spatial and temporal arrival rate among urban regions. The objective is to maximize the revenue of served requests given a limited number of couriers over a period of time. Many online algorithms such as dynamic matching and vehicle routing strategy from existing literature could be applied to tackle this problem. However, these methods rely on appropriately predefined optimization objectives at each decision point, which is hard in dynamic situations. This paper formulates the CDP as a Markov decision process (MDP) and proposes a data-driven approach to derive the optimal dispatching rule-set under different scenarios. Our method stacks multi-layer images of the spatial-and-temporal map and apply multi-agent reinforcement learning (MARL) techniques to evolve dispatching models. This method solves the learning inefficiency caused by traditional centralized MDP modeling. Through comprehensive experiments on both artificial dataset and real-world dataset, we show: 1) By utilizing historical data and considering long-term revenue gains, MARL achieves better performance than myopic online algorithms; 2) MARL is able to construct the mapping between complex scenarios to sophisticated decisions such as the dispatching rule. 3) MARL has the scalability to adopt in large-scale real-world scenarios.

Yiheng Zhu, Yichen Yao, Zili Wu et al.

Convolutional neural networks (CNNs) are effective at solving difficult problems like visual recognition, speech recognition and natural language processing. However, performance gain comes at the cost of laborious trial-and-error in designing deeper CNN architectures. In this paper, a genetic programming (GP) framework for convolutional neural network architecture search, abbreviated as GP-CNAS, is proposed to automatically search for optimal CNN architectures. GP-CNAS encodes CNNs as trees where leaf nodes (GP terminals) are selected residual blocks and non-leaf nodes (GP functions) specify the block assembling procedure. Our tree-based representation enables easy design and flexible implementation of genetic operators. Specifically, we design a dynamic crossover operator that strikes a balance between exploration and exploitation, which emphasizes CNN complexity at early stage and CNN diversity at later stage. Therefore, the desired CNN architecture with balanced depth and width can be found within limited trials. Moreover, our GP-CNAS framework is highly compatible with other manually-designed and NAS-generated block types as well. Experimental results on the CIFAR-10 dataset show that GP-CNAS is competitive among the state-of-the-art automatic and semi-automatic NAS algorithms.

Lu Duan, Haoyuan Hu, Yu Qian et al.

A 3D flexible bin packing problem (3D-FBPP) arises from the process of warehouse packing in e-commerce. An online customer's order usually contains several items and needs to be packed as a whole before shipping. In particular, 5% of tens of millions of packages are using plastic wrapping as outer packaging every day, which brings pressure on the plastic surface minimization to save traditional logistics costs. Because of the huge practical significance, we focus on the issue of packing cuboid-shaped items orthogonally into a least-surface-area bin. The existing heuristic methods for classic 3D bin packing don't work well for this particular NP-hard problem and designing a good problem-specific heuristic is non-trivial. In this paper, rather than designing heuristics, we propose a novel multi-task framework based on Selected Learning to learn a heuristic-like policy that generates the sequence and orientations of items to be packed simultaneously. Through comprehensive experiments on a large scale real-world transaction order dataset and online AB tests, we show: 1) our selected learning method trades off the imbalance and correlation among the tasks and significantly outperforms the single task Pointer Network and the multi-task network without selected learning; 2) our method obtains an average 5.47% cost reduction than the well-designed greedy algorithm which is previously used in our online production system.

Haoyuan Hu, Xiaodong Zhang, Xiaowei Yan et al.

In this paper, a new type of 3D bin packing problem (BPP) is proposed, in which a number of cuboid-shaped items must be put into a bin one by one orthogonally. The objective is to find a way to place these items that can minimize the surface area of the bin. This problem is based on the fact that there is no fixed-sized bin in many real business scenarios and the cost of a bin is proportional to its surface area. Our research shows that this problem is NP-hard. Based on previous research on 3D BPP, the surface area is determined by the sequence, spatial locations and orientations of items. Among these factors, the sequence of items plays a key role in minimizing the surface area. Inspired by recent achievements of deep reinforcement learning (DRL) techniques, especially Pointer Network, on combinatorial optimization problems such as TSP, a DRL-based method is applied to optimize the sequence of items to be packed into the bin. Numerical results show that the method proposed in this paper achieve about 5% improvement than heuristic method.