Due to the complexity of data collection in the real world, Multi-view Representation Learning (MvRL) always encounters the incomplete information challenge, typically manifested as the Sample-missing Problem (SP) and the View-unaligned Problem (VP). Although several methods have been proposed, they fail to find a good trade-off among sample restoration, view alignment, and data diversity preservation. To address this issue, we take and mathematically formulate two sociological concepts for MvRL, i.e., community commonality and community versatility, where the former refers to the identical custom shared within the same community, and the latter refers to the similar but non-identical custom within communities of the same minority. One could find that the community commonality can enhance the compactness of view-specific clusters, and the community versatility can preserve the view diversity. Moreover, combining both of them could facilitate achieving robust MvRL with incomplete information. With the formulations, we propose a novel method dubbed Community-Aware Multi-viEw RepresentAtion learning with incomplete information (CAMERA). In brief, CAMERA employs a novel dual-stream network and an elaborate objective function that theoretically and empirically embraces community commonality and versatility. Extensive experimental results on seven datasets demonstrate that CAMERA remarkably outperforms 24 competitive multi-view learning methods on clustering, classification, and human action recognition tasks.

Automated Guided Vehicle (AGV) positioning and scheduling critically impact automated container terminal efficiency, yet operational uncertainties significantly challenge effective decision-making. This study addresses the integrated AGV positioning and scheduling problem (AGV-PSP) under uncertainty through a novel framework integrating reinforcement learning (RL), combinatorial optimization, and high-fidelity simulation. We formulate the AGV-PSP as a Markov Decision Process where RL learns the state value function, estimating the long-term operational value of terminal locations. Based on the value function, our positioning policy strategically locates AGVs in high-value areas, while our scheduling policy balances immediate and long-term rewards using integer linear programming solved by an improved Hungarian algorithm. Experiments demonstrate 35.6% higher rewards and 36.6% lower costs compared to benchmarks on average. Sensitivity analyses validate the framework’s robustness across varying uncertainty.

The success of most existing cross-modal retrieval methods heavily relies on the assumption that the given queries follow the same distribution of the source domain. However, such an assumption is easily violated in real-world scenarios due to the complexity and diversity of queries, thus leading to the query shift problem. Specifically, query shift refers to the online query stream originating from the domain that follows a different distribution with the source one. In this paper, we observe that query shift would not only diminish the uniformity (namely, within-modality scatter) of the query modality but also amplify the gap between query and gallery modalities. Based on the observations, we propose a novel method dubbed Test-time adaptation for Cross-modal Retrieval (TCR). In brief, TCR employs a novel module to refine the query predictions (namely, retrieval results of the query) and a joint objective to prevent query shift from disturbing the common space, thus achieving online adaptation for the cross-modal retrieval models with query shift. Expensive experiments demonstrate the effectiveness of the proposed TCR against query shift. Code is available at https://github.com/XLearning-SCU/2025-ICLR-TCR.

With the development of intelligent logistics technology, some companies began to use robots instead of humans to load cargo. This paper studies a novel container loading problem based on robotic loader system (CLP-RLS). Different from the existing robot-packable pattern in the literature, the robotic loader system in this paper consists of a depalletizing robot, an automatic telescopic roller line and a loading robot, in which the loading robot will enter the carriage along with the automatic telescopic roller line. In CLP-RLS, it is necessary to consider not only many practical constraints already in the literature, including load balancing, orientation, stability, and multi-drop but also two new constraints related to robotic loader system: pallet continuity constraint (the loading sequence of cargo on the same pallet is continuous) and robot position constraint (the robot can only load cargo incrementally from the front to the back of the truck). Due to the difficulty in modeling CLP-RLS and the large scale of the real-case instances, we present a tree search approach based on wall-building to solve CLP-RLS, intending to find a feasible loading scheme for the RLS to minimize the length required to load all cargo. The effectiveness of the proposed approach is verified through both real-case instances and numerical instances.

In this paper, we study how to achieve two characteristics highly-expected by incomplete multi-view clustering (IMvC). Namely, i) instance commonality refers to that within-cluster instances should share a common pattern, and ii) view versatility refers to that cross-view samples should own view-specific patterns. To this end, we design a novel dual-stream model which employs a dual attention layer and a dual contrastive learning loss to learn view-specific prototypes and model the sample-prototype relationship. When the view is missed, our model performs data recovery using the prototypes in the missing view and the sample-prototype relationship inherited from the observed view. Thanks to our dual-stream model, both cluster- and view-specific information could be captured, and thus the instance commonality and view versatility could be preserved to facilitate IMvC. Extensive experiments demonstrate the superiority of our method on five challenging benchmarks compared with 11 approaches. The code could be accessed from https://pengxi.me.

There has been a growing interest in developing conversational recommendation system (CRS), which provides valuable recommendations to users through conversations. Compared to the traditional recommendation, it advocates wealthier interactions and provides possibilities to obtain users’ exact preferences explicitly. Nevertheless, the corresponding research on this topic is limited due to the lack of broad-coverage dialogue corpus, especially real-world dialogue corpus. To handle this issue and facilitate our exploration, we construct E-ConvRec, an authentic Chinese dialogue dataset consisting of over 25k dialogues and 770k utterances, which contains user profile, product knowledge base (KB), and multiple sequential real conversations between users and recommenders. Next, we explore conversational recommendation in a real scene from multiple facets based on the dataset. Therefore, we particularly design three tasks: user preference recognition, dialogue management, and personalized recommendation. In the light of the three tasks, we establish baseline results on E-ConvRec to facilitate future studies.

The N-k problem is very well known in the power industry and it tries to answer the question whether there exists a set of k lines in a power network with N elements whose removal would cause the failure of the system. In practice, it is common to evaluate a system according to an N-1 criterion, i.e., k = 1. While this problem has traditionally been considered in a deterministic setting, stochastic behavior within the system is important especially in the context of extreme events. A number of stochastic Monte Carlo models have been proposed to estimate the probability of cascading failures. In this paper, we deal with simulation budget allocation of the stochastic N-1 problem. More specifically, we assume that a simulation model is able to provide us an estimate of the system failure rate when any line is tripped. It is not difficult to see how simulation of all configurations to some certain accuracy can become computationally expensive with the growth of N. Under such a setting, we transform the N-1 problem into a stochastic selection process with optimal computing budget allocation (OCBA): given N configurations, we would like to sequentially allocate a certain number of simulation replications in order to answer the question whether the system is reliable or not. We show through theoretical analysis and numerical experiments that the probability of correctly identifying the system reliability state can be increased by applying OCBA allocation rules in the simulation budget allocation process.

This paper presents an overview of our work for searching and retrieving facts and relationships within natural language text sources. In this work, an extraction task over a text collection is expressed as a query that combines text fragments with wild cards, and the query result is a set of facts in the form of unary, binary and general n-ary tuples. Despite being both simple and declarative, the framework can be applied to a wide range of extraction tasks. This paper presents an overview of the work and its various components. We also report some of our experiments and an evaluation of the proposed querying framework in extracting relevant information to a task.

No abstract available.