IJCAI 2024 Papers

The development of the smart manufacturing trend includes the integration of Artificial Intelligence technologies into industrial processes. One example of such implementation is deep learning models that diagnose the current state of a technological process. Recent studies have demonstrated that small data perturbations, named adversarial attacks, can significantly affect the correct predictions of such models. This fact is critical in industrial systems, where AI-based decisions can be made to manage physical equipment. In this work, we present a system which can help to evaluate the robustness of technological process diagnosis models to adversarial attacks, as well as consider protection options. We briefly review the system's modules and also consider some useful applications. Our demo video is available at: http://tinyurl.com/3by9zcj5

Learning first-order logic programs from relational facts yields intuitive insights into the data. Inductive logic programming (ILP) models are effective in learning first-order logic programs from observed relational data. Symbolic ILP models support rule learning in a data-ecient manner. However, symbolic ILP models are not robust to learn from noisy data. Neuro-symbolic ILP models utilize neural networks to learn logic programs in a differentiable manner which improves the robustness of ILP models. However, most neuro-symbolic methods need a strong language bias to learn logic programs, which reduces the usability and flexibility of ILP models and limits the logic program formats. In addition, most neuro-symbolic ILP methods cannot learn logic programs effectively from both small-size datasets and large-size datasets such as knowledge graphs. In the paper, we introduce a novel differentiable ILP model called differentiable first-order rule learner (DFORL), which is scalable to learn rules from both smaller and larger datasets. Besides, DFORL only needs the number of variables in the learned logic programs as input. Hence, DFORL is easy to use and does not need a strong language bias. We demonstrate that DFORL can perform well on several standard ILP datasets, knowledge graphs, and probabilistic relation facts and outperform several well-known differentiable ILP models. Experimental results indicate that DFORL is a precise, robust, scalable, and computationally cheap differentiable ILP model.

Few-shot semantic segmentation (FSS) aims to generate a model for segmenting novel classes using a limited number of annotated samples. Previous FSS methods have shown sensitivity to background noise due to inherent bias, attention bias, and spatial-aware bias. In this study, we propose a Transformer-Based Adaptive Prototype Matching Network to establish robust matching relationships by improving the semantic and spatial perception of query features. The model includes three modules: target enhancement module (TEM), dual constraint aggregation module (DCAM), and dual classification module (DCM). In particular, TEM mitigates inherent bias by exploring the relevance of multi-scale local context to enhance foreground features. Then, DCAM addresses attention bias through the dual semantic-aware attention mechanism to strengthen constraints. Finally, the DCM module decouples the segmentation task into semantic alignment and spatial alignment to alleviate spatial-aware bias. Extensive experiments on PASCAL-5i and COCO-20i confirm the effectiveness of our approach.

This paper addresses the challenge of solution counting for Quantified Boolean Formulas (QBFs), a task distinct from the well-established model counting problem for SAT (\#SAT). Unlike SAT, where models are straightforward assignments to Boolean variables, QBF solution counting involves tree models that capture dependencies among variables within different quantifier blocks. We present a comprehensive top-down tree model counter capable of handling diverse satisfiable QBF formulas. Emphasizing the critical role of the branching heuristic, which must consider variables in the correct order according to quantification blocks, we further demonstrate the importance of addressing connected components, free variables, and caching. Experimental results indicate that our proposed approach for counting tree models of QBF formulas is highly efficient in practice, surpassing existing state-of-the-art methods designed for this specific purpose.

We present a formalization of the Event Calculus (EC) in tensor spaces. The motivation for a tensor-based predicate calculus comes from the area of composite event recognition (CER). As a CER engine, we adopt a logic programming implementation of EC with optimizations for continuous narrative assimilation on data streams. We show how to evaluate EC rules algebraically and solve a linear equation to compute the corresponding models. We demonstrate the scalability of our approach with the use of large datasets from a real-world application domain, and show it outperforms significantly symbolic EC, in terms of processing time.

Proper attire is a professional requirement for teachers and teachers' dress influence students' perceptions of teacher quality. Therefore, evaluating teacher attire can better regulate and improve the teacher’s dress. However, the lack of a dataset on teacher attire hinders the development of this field. For this purpose, this paper constructs a Teachers' Classroom Dress Assessment (TCDA) dataset. To our knowledge, it is the first dataset focused on teacher attire. This dataset is entirely from the classroom environment, covering 25 teacher attributes, with a total of 11879 teacher dress samples and sufficient positive and negative examples. Therefore, the TCDA dataset is a challenging evaluation dataset with characteristics such as data diversity. In order to verify the effectiveness of the dataset, this paper systematically explores a new perspective on human attribute information and proposes for the first time a Teachers' Dress Assessment Method (TDAM), aiming to use predicted teacher attributes to scoring the overall attire of each teacher, thereby promoting the development of the teacher's classroom teaching field. The experimental results demonstrate the rationality of the TCDA dataset and the effectiveness of the TDAM method. The dataset and code can be openly obtained at https://github.com/MingZier/TCDA-dataset.

Federated learning (FL) revolutionizes distributed machine learning by enabling devices to collaboratively learn a model while maintaining data privacy. However, FL usually faces a critical challenge with limited labeled data, making semi-supervised learning (SSL) crucial for utilizing abundant unlabeled data. The integration of SSL within the federated framework gives rise to federated semi-supervised learning (FSSL), a novel approach that exploits unlabeled data across devices without compromising privacy. This paper systematically explores FSSL, shedding light on its four basic problem settings that commonly appear in real-world scenarios. By examining the unique challenges, generic solutions, and representative methods tailored for each setting of FSSL, we aim to provide a cohesive overview of the current state of the art and pave the way for future research directions in this promising field.

The Latin square completion (LSC) problem aims to assign n symbols to the empty cells of a partially filled Latin square such that in each row and each column, each symbol appears exactly once. In this paper, we propose a swap relaxation-based fast local search algorithm called SRLS for solving the LSC problem. First, it introduces a novel search space definition, which forbids row conflicts based on which a swap-based neighborhood is defined. Second, a color domain relaxation technique is employed in the swap-based neighborhood by temporarily accepting the violation of some constraints to connect high-quality solutions. Third, two effective scoring functions are adopted to select neighborhood moves minimizing the number of conflicting edges as well as the number of color domain violations. Finally, SRLS employs an adaptive restart mechanism to balance the exploitation and exploration of the search. Extensive experiments on 1819 public benchmark instances demonstrate that SRLS outperforms the state-of-the-art algorithms in the literature in terms of both success rate and computational efficiency.

Intimate Partner Violence (IPV) is a global problem affecting more than 2 billion women worldwide. Our paper makes two key contributions. First, via a substantial corpus of 53,220 comments to 1,563 Intimate Partner Physical Violence (IPPV) posts gleaned from more than 10 million comments posted on 523,232 posts on a popular parental health website in Iran, we present the first-ever computational analysis of user comments on accounts of IPPV in Iran. We harness large language models and participatory AI and tackle extreme class imbalance and other linguistic challenges that arise from tackling low-resource languages to shed light on the gender struggles of a country with documented stark gender inequality. With active input from a woman with a history of advocacy for social rights and grounded in Iranian culture, we characterize comments on IPPV into three broad categories: empathy, confront, and conform, and analyze their distribution. Second, we release an important dataset of 3,400 comments on IPPV posts.

Rank aggregation (RA), the technique of combining multiple basic rankings into a consensus one, plays an important role in social choices, bioinformatics, information retrieval, metasearch, and recommendation systems. Although recent years have witnessed remarkable progress in RA, the absence of a systematic overview motivates us to conduct a comprehensive survey including both classic algorithms and the latest advances in RA study. Specifically, we first discuss the challenges of RA research, then present a systematic review with a fine-grained taxonomy to introduce representative algorithms in unsupervised RA, supervised RA, as well as the previously overlooked semi-supervised RA. Within each category, we not only summarize the common ideas of similar methods, but also discuss their strengths and weaknesses. Particularly, to investigate the performance difference of different types of RA methods, we conduct the largest scale of comparative evaluation to date of 27 RA methods on 7 public datasets from person re-identification, recommendation systems, bioinformatics and social choices. Finally, we raise two open questions in the current RA research and make our comments about future trends in the context of the latest research progress.

Automated Planning deals with finding a sequence of actions that solves a given (planning) problem. The cost of the solution is a direct consequence of these actions, for example its number or their accumulated costs. Thus, in most applications, cheaper plans are preferred. Yet, finding an optimal solution is more challenging than finding some solution. So, many planning algorithms find some solution and then post-process, i.e., optimize it -- a technique called plan optimization. Over the years many different approaches were developed, not all for the same kind of plans, and not all optimize the same metric. In this comprehensive survey, we give an overview of the existing plan optimization goals, their computational complexity (if known), and existing techniques for such optimizations.

In this survey, we present a detailed examination of the advancements in Neural Question Generation (NQG), a field leveraging neural network techniques to generate relevant questions from diverse inputs like knowledge bases, texts, and images. The survey begins with an overview of NQG's background, encompassing the task's problem formulation, prevalent benchmark datasets, established evaluation metrics, and notable applications. It then methodically classifies NQG approaches into three predominant categories: structured NQG, which utilizes organized data sources, unstructured NQG, focusing on more loosely structured inputs like texts or visual content, and hybrid NQG, drawing on diverse input modalities. This classification is followed by an in-depth analysis of the distinct neural network models tailored for each category, discussing their inherent strengths and potential limitations. The survey culminates with a forward-looking perspective on the trajectory of NQG, identifying emergent research trends and prospective developmental paths. Accompanying this survey is a curated collection of related research papers, datasets, and codes, all of which are available on GitHub. This provides an extensive reference for those delving into NQG.

Network alignment, the task of mapping corresponding nodes across networks, is attracting more attention for cross-network analysis in diverse domains, including social, biological, and co-authorship networks. Although a variety of methods have been proposed, we lack a holistic understanding of the approaches and applications. Our survey aims to bridge this gap by first proposing a taxonomy of network alignment, characterizing existing approaches, and then systematically summarizing and reviewing their performance and highlighting their scopes for future development. Finally, we discuss some important applications and give directions for future research within this domain.

Goal Recognition is the task of inferring an agent's intentions from a set of observations. Existing recognition approaches have made considerable advances in domains such as human-robot interaction, intelligent tutoring systems, and surveillance. However, most approaches rely on explicit domain knowledge, often defined by a domain expert. Much recent research focus on mitigating the need for a domain expert while maintaining the ability to perform quality recognition, leading researchers to explore Model-Free Goal Recognition approaches. We comprehensively survey Model-Free Goal Recognition, and provide a perspective on the state-of-the-art approaches and their applications, showing recent advances. We categorize different approaches, introducing a taxonomy with a focus on their characteristics, strengths, weaknesses, and suitability for different scenarios. We compare the advances each approach made to the state-of-the-art and provide a direction for future research in Model-Free Goal Recognition.

With the continuous growth of large Knowledge Graphs (KGs), extractive KG summarization becomes a trending task. Aiming at distilling a compact subgraph with condensed information, it facilitates various downstream KG-based tasks. In this survey paper, we are among the first to provide a systematic overview of its applications and define a taxonomy for existing methods from its interdisciplinary studies. Future directions are also laid out based on our extensive and comparative review.

Federated Learning (FL) has become an established technique to facilitate privacy-preserving collaborative training across a multitude of clients. However, new approaches to FL often discuss their contributions involving small deep-learning models only and focus on training full models on clients. In the wake of Foundation Models (FM), the reality is different for many deep learning applications. Typically, FMs have already been pre-trained across a wide variety of tasks and can be fine-tuned to specific downstream tasks over significantly smaller datasets than required for full model training. However, access to such datasets is often challenging. By its design, FL can help to open data silos. With this survey, we introduce a novel taxonomy focused on computational and communication efficiency, the vital elements to make use of FMs in FL systems. We discuss the benefits and drawbacks of parameter-efficient fine-tuning (PEFT) for FL applications, elaborate on the readiness of FL frameworks to work with FMs and provide future research opportunities on how to evaluate generative models in FL as well as the interplay of privacy and PEFT.

Cross-domain sequential recommendation (CDSR) shifts the modeling of user preferences from flat to stereoscopic by integrating and learning interaction information from multiple domains at different granularities (ranging from inter-sequence to intra-sequence and from single-domain to cross-domain). In this survey, we initially define the CDSR problem using a four-dimensional tensor and then analyze its multi-type input representations under multidirectional dimensionality reductions. Following that, we provide a systematic overview from both macro and micro views. From a macro view, we abstract the multi-level fusion structures of various models across domains and discuss their bridges for fusion. From a micro view, focusing on the existing models, we specifically discuss the basic technologies and then explain the auxiliary learning technologies. Finally, we exhibit the available public datasets and the representative experimental results as well as provide some insights into future directions for research in CDSR.

With large language models, robots can understand language more flexibly and more capable than ever before. This survey reviews and situates recent literature into a spectrum with two poles: 1) mapping between language and some manually defined formal representation of meaning, and 2) mapping between language and high-dimensional vector spaces that translate directly to low-level robot policy. Using a formal representation allows the meaning of the language to be precisely represented, limits the size of the learning problem, and leads to a framework for interpretability and formal safety guarantees. Methods that embed language and perceptual data into high-dimensional spaces avoid this manually specified symbolic structure and thus have the potential to be more general when fed enough data but require more data and computing to train. We discuss the benefits and tradeoffs of each approach and finish by providing directions for future work that achieves the best of both worlds.

Sarcasm is a rhetorical device that is used to convey the opposite of the literal meaning of an utterance. Sarcasm is widely used on social media and other forms of computer-mediated communication motivating the use of computational models to identify it automatically. While the clear majority of approaches to sarcasm detection have been carried out on text only, sarcasm detection often requires additional information present in tonality, facial expression, and contextual images. This has led to the introduction of multimodal models, opening the possibility to detect sarcasm in multiple modalities such as audio, images, text, and video. In this paper, we present the first comprehensive survey on multimodal sarcasm detection - henceforth MSD - to date. We survey papers published between 2018 and 2023 on the topic, and discuss the models and datasets used for this task. We also present future research directions in MSD.