IJCAI 2024 Papers

End-to-end spoken language understanding (SLU) aims to directly capture the comprehensive semantics from the given spoken utterance without generating any transcript. Since the transcripts might not always be available, Textless SLU is attracting increasing attention, which could eliminate the need for transcripts but often does not perform as well as SLU models trained with transcripts. In this paper, we focus on the scenarios where the transcripts are not available and propose a framework GMA-SLU to generate more audios according to the labels. In order to alleviate the modality gap between text and audio, two language models are developed and discrete tokens are utilized as a bridge, where the first language model utilizes labels to generate semantic tokens and the second language model adopts these obtained semantic tokens and the acoustic tokens of source audios to generate the synthetic audios. All the experiments are conducted on the monolingual SLU dataset SLURP and the multilingual SLU dataset MINDS-14. Experimental results show that our method outperforms the previous best Textless End-to-end SLU models and can obtain the comparable performance with the models trained with the assistance of the corresponding transcripts.

Due to the potential leakage of sensitive information in text, there is a societal call for feeding privacy-preserving text to model training. Recently, a lot of work showed that using synthetic text with differential privacy, rather than private text, can provide a strong privacy protection. However, achieving higher semantic similarity between synthetic and private text has not been thoroughly investigated. In this paper, we propose an approach that combines the iteratively optimized mindset from genetic algorithms to align the distribution of synthetic text with that of private text. Furthermore, not only does the final synthetic text meet the requirements of privacy protection, but also has a high level of quality. Through comparisons with various baselines on different datasets, we demonstrate that our synthetic text can closely match the utility of private text, while providing privacy protection standards robust enough to resist membership inference attacks from malicious users.

Graph neural networks have been demonstrated to be effective analytic apparatus for mining network data. Most real-world networks are inherently hierarchical, offering unique opportunities to acquire latent, intrinsic network organizational properties by utilizing network taxonomies. The existing approaches for learning implicit hierarchical network structures focus on introducing taxonomy to graph neural networks but often run short of exploiting the rich network semantics and structural properties in the taxonomy, resulting in poor generalizability and reusability. To address these issues, we propose generalized Taxonomy-Guided Graph Neural Networks (TG-GNN) to integrate taxonomy into network representation learning. We first construct a taxonomy representation learning module that introduces the concept of ego network to propagate and aggregate rich semantic and structural information in the taxonomy. We then design a taxonomy-guided Markov mechanism, which encapsulates taxonomy knowledge in pairwise potential functions, to refine network embeddings. Extensive experiments on various real-world networks illustrate the effectiveness of TG-GNN over the state-of-the-art methods on scenarios involving incomplete taxonomies and inductive settings.

Epistemic Abstract Argumentation Framework (EAAF) extends Dung's framework (AAF)---a central formalism in AI for modeling disputes among agents---by allowing the representation of epistemic knowledge. In particular, EAAF augments AAF with weak and strong epistemic attacks whose intuitive meaning is that an argument a defeats an argument b by means of a weak (resp. strong) epistemic attack if a is true in every (resp. at least one) extension. So far, the semantics of EAAF has been defined only for a restricted class of frameworks, namely acyclic EAAF, where epistemic attacks do not occur in any cycle. In this paper, we provide an intuitive semantics for (general) EAAF that naturally extends that for AAF as well as that for acyclic EAAF. After providing some fundamental properties and giving an algorithm that enables the computation of EAAF semantics, by relying on state-of-the-art AAF-solvers, we investigate the complexity of canonical argumentation problems.

Great advancements in semantic, instance, and panoptic segmentation have been made in recent years, yet the top-performing models remain vulnerable to imperceptible adversarial perturbation. Current attacks on segmentation primarily focus on a single task, and these methods typically rely on iterative instance-specific strategies, resulting in limited attack transferability and low efficiency. In this paper, we propose GenSeg, a Generative paradigm that creates unified adversaries for Segmentation tasks. In particular, we propose an intermediate-level objective to enhance attack transferability, including a mutual agreement loss for feature deviation, and a prototype obfuscating loss to disrupt intra-class and inter-class relationships. Moreover, GenSeg crafts an adversary in a single forward pass, significantly boosting the attack efficiency. Besides, we unify multiple segmentation tasks to GenSeg in a novel category-and-mask view, which makes it possible to attack these segmentation tasks within this unified framework, and conduct cross-domain and cross-task attacks as well. Extensive experiments demonstrate the superiority of GenSeg in black-box attacks compared with state-of-the-art attacks. To our best knowledge, GenSeg is the first approach capable of conducting cross-domain and cross-task attacks on segmentation tasks, which are closer to real-world scenarios.

In this paper, we investigate under which conditions normal-form games are (guaranteed to be) strategically equivalent. First, we show for N -player games (N >= 3) that (A) it is NP-hard to decide whether a given strategy is a best response to some strategy profile of the opponents, and that (B) it is co-NP-hard to decide whether two games have the same best-response sets. Combining that with known results from the literature, we move our attention to equivalence-preserving game transformations. It is a widely used fact that a positive affine (linear) transformation of the utility payoffs neither changes the best-response sets nor the Nash equilibrium set. We investigate which other game transformations also possess either of the following two properties when being applied to an arbitrary N-player game (N >= 2): (i) The Nash equilibrium set stays the same; (ii) The best-response sets stay the same. For game transformations that operate player-wise and strategy-wise, we prove that (i) implies (ii) and that transformations with property (ii) must be positive affine. The resulting equivalence chain highlights the special status of positive affine transformations among all the transformation procedures that preserve key game-theoretic characteristics.

There are substantial instructional videos on the Internet, which provide us tutorials for completing various tasks. Existing instructional video datasets only focus on specific steps at the video level, lacking experiential guidelines at the task level, which can lead to beginners struggling to learn new tasks due to the lack of relevant experience. Moreover, the specific steps without guidelines are trivial and unsystematic, making it difficult to provide a clear tutorial. To address these problems, we present the Guide (Guideline-Guided) dataset, which contains 3.5K videos of 560 instructional tasks in 8 domains related to our daily life. Specifically, we annotate each instructional task with a guideline, representing a common pattern shared by all task-related videos. On this basis, we annotate systematic specific steps, including their associated guideline steps, specific step descriptions and timestamps. Our proposed benchmark consists of three sub-tasks to evaluate comprehension ability of models: (1) Step Captioning: models have to generate captions for specific steps from videos. (2) Guideline Summarization: models have to mine the common pattern in task-related videos and summarize a guideline from them. (3) Guideline-Guided Captioning: models have to generate captions for specific steps under the guide of guideline. We evaluate plenty of foundation models with Guide and perform in-depth analysis. Given the diversity and practicality of Guide, we believe that it can be used as a better benchmark for instructional video comprehension.

While Learning to Rank (LTR) is widely employed in web searches to prioritize pertinent webpages from the retrieved contents based on input queries, traditional LTR models stumble over two principal stumbling blocks leading to subpar performance: 1) the lack of well-annotated query-webpage pairs with ranking scores to cover search queries of various popularity, debilitating their coverage of search queries across the popularity spectrum, and 2) ill-trained models that are incapable of inducing generalized representations for LTR, culminating in overfitting. To tackle above challenges, we proposed a Generative Semi-supervised Pre-trained (GS2P) LTR model. Specifically, GS2P first generates pseudo-labels for the unlabeled samples using tree-based LTR models after a series of co-training procedures, then learns the representations of query-webpage pairs with self-attentive transformers via both discriminative and generative losses. Finally, GS2P boosts the performance of LTR through incorporating Random Fourier Features to over-parameterize the models into "interpolating regime", so as to enjoy the further descent of generalization errors with learned representations. We conduct extensive offline experiments on a publicly available dataset and a real-world dataset collected from a large-scale search engine. The results show that GS2P can achieve the best performance on both datasets, compared to baselines. We also deploy GS2P at a large-scale web search engine with realistic traffic, where we can still observe significant improvement in real-world applications.

This paper presents GRASP, a novel benchmark to evaluate the language grounding and physical understanding capabilities of video-based multimodal large language models (LLMs). This evaluation is accomplished via a two-tier approach leveraging Unity simulations. The first level tests for language grounding by assessing a model's ability to relate simple textual descriptions with visual information. The second level evaluates the model's understanding of "Intuitive Physics" principles, such as object permanence and continuity. In addition to releasing the benchmark, we use it to evaluate several state-of-the-art multimodal LLMs. Our evaluation reveals significant shortcomings in the language grounding and intuitive physics capabilities of these models. Although they exhibit at least some grounding capabilities, particularly for colors and shapes, these capabilities depend heavily on the prompting strategy. At the same time, all models perform below or at the chance level of 50% in the Intuitive Physics tests, while human subjects are on average 80% correct. These identified limitations underline the importance of using benchmarks like GRASP to monitor the progress of future models in developing these competencies.

Generating engaging multimodal content is a key objective in numerous applications, such as the creation of online advertisements that captivate user attention through a synergy of images and text. In this paper, we introduce GEM, a novel framework engineered for the generation of engaging multimodal image-text posts. The GEM framework operates in two primary phases. Initially, GEM integrates a pre-trained engagement discriminator with a technique for deriving an effective continuous prompt tailored for the stable diffusion model. Subsequently, GEM unveils an iterative algorithm dedicated to producing coherent and compelling image-sentence pairs centered around a specified topic of interest. Through a combination of experimental analysis and human evaluations, we establish that the image-sentence pairs generated by GEM not only surpass several established baselines in terms of engagement but also in achieving superior alignment.

Predicting future trajectories of traffic agents accurately holds substantial importance in various applications such as autonomous driving. Previous methods commonly infer all future steps of an agent either recursively or simultaneously. However, the recursive strategy suffers from the accumulated error, while the simultaneous strategy overlooks the constraints among future steps, resulting in kinematically infeasible predictions. To address these issues, in this paper, we propose G2LTraj, a plug-and-play global-to-local generation approach for trajectory prediction. Specifically, we generate a series of global key steps that uniformly cover the entire future time range. Subsequently, the local intermediate steps between the adjacent key steps are recursively filled in. In this way, we prevent the accumulated error from propagating beyond the adjacent key steps. Moreover, to boost the kinematical feasibility, we not only introduce the spatial constraints among key steps but also strengthen the temporal constraints among the intermediate steps. Finally, to ensure the optimal granularity of key steps, we design a selectable granularity strategy that caters to each predicted trajectory. Our G2LTraj significantly improves the performance of seven existing trajectory predictors across the ETH, UCY and nuScenes datasets. Experimental results demonstrate its effectiveness. Code will be available at https://github.com/Zhanwei-Z/G2LTraj.

The joint classification of multisource remote sensing data is a prominent research field. However, most of the existing works are tailored for two specific data sources, which fail to effectively address the diverse combinations of data sources in practical applications. The importance of designing a unified network with applicability has been disregarded. In this paper, we propose a unified and self-supervised Symbiotic Diffusion framework (named SymDiffuser), which achieves the joint classification of any pair of different remote sensing data sources in a single model. The SymDiffuser captures the inter-modal relationship through establishing reciprocal conditional distributions across diverse sources step by step. The fusion process of multisource data is consistently represented within the framework from a data distribution perspective. Subsequently, features under the current conditional distribution at each time step is integrated during the downstream phase to accomplish the classification task. Such joint classification methodology transcends source-specific considerations, rendering it applicable to remote sensing data from any diverse sources. The experimental results showcase the framework's potential in achieving state-of-the-art performance in multimodal fusion classification task.

This paper introduces a novel Functional Graph Convolutional Network (funGCN) framework that combines Functional Data Analysis and Graph Convolutional Networks to address the complexities of multi-task and multi-modal learning in digital health and longitudinal studies. With the growing importance of health solutions to improve health care and social support, ensure healthy lives, and promote well-being at all ages, funGCN offers a unified approach to handle multivariate longitudinal data for multiple entities and ensures interpretability even with small sample sizes. Key innovations include task-specific embedding components that manage different data types, the ability to perform classification, regression, and forecasting, and the creation of a knowledge graph for insightful data interpretation. The efficacy of funGCN is validated through simulation experiments and a real-data application. funGCN source code is publicly available at https://github.com/IBM/funGCN.

Due to the complex and dynamic traffic contexts, the interpretability and uncertainty of traffic forecasting have gained increasing attention. Significance testing is a powerful tool in statistics used to determine whether a hypothesis is valid, facilitating the identification of pivotal features that predominantly contribute to the true relationship. However, existing works mainly regard traffic forecasting as a deterministic problem, making it challenging to perform effective significance testing. To fill this gap, we propose to conduct Full Bayesian Significance Testing for Neural Networks in Traffic Forecasting, namely ST-nFBST. A Bayesian neural network is utilized to capture the complicated traffic relationships through an optimization function resolved in the context of aleatoric uncertainty and epistemic uncertainty. Thereupon, ST-nFBST can achieve the significance testing by means of a delicate grad-based evidence value, further capturing the inherent traffic schema for better spatiotemporal modeling. Extensive experiments are conducted on METR-LA and PEMS-BAY to verify the advantages of our method in terms of uncertainty analysis and significance testing, helping the interpretability and promotion of traffic forecasting.

In recent years, there are trends toward cleaner port environments through enforcement by imposed legislation. Transit optimisation of fuel-based port service boats like harbour tugs has emerged as a critical task to reduce fuel consumption and carbon emission. In this paper, an innovative learning-based method, comprising a Reinforcement Learning (RL) model together with a fuel consumption prediction model, was proposed to formulate fuel-saving transit routes. Firstly, an ensemble model is established by combining a Long Short-Term Memory (LSTM) model with a Multilayer Perceptron (MLP) model, predicting fuel use based on tugboat movement and environment factors. Subsequently, an innovative RL based on Deep Deterministic Policy Gradient (DDPG) framework is developed considering the characteristics and obstructions of waterway in Singapore as well as the environmental factors to learn the optimal transit strategy that minimizes fuel consumption. We also demonstrate the efficacy of the solution to generate routes from origin to destination terminals, exhibiting significantly reduced fuel consumption in comparison to real-world transit scenarios.

In the digital era, the rapid propagation of fake news and rumors via social networks brings notable societal challenges and impacts public opinion regulation. Traditional fake news modeling typically forecasts the general popularity trends of different groups or numerically represents opinions shift. However, these methods often oversimplify real-world complexities and overlook the rich semantic information of news text. The advent of large language models (LLMs) provides the possibility of modeling subtle dynamics of opinion. Consequently, in this work, we introduce a Fake news Propagation Simulation framework (FPS) based on LLM, which studies the trends and control of fake news propagation in detail. Specifically, each agent in the simulation represents an individual with a distinct personality. They are equipped with both short-term and long-term memory, as well as a reflective mechanism to mimic human-like thinking. Every day, they engage in random opinion exchanges, reflect on their thinking, and update their opinions. Our simulation results uncover patterns in fake news propagation related to topic relevance, and individual traits, aligning with real-world observations. Additionally, we evaluate various intervention strategies and demonstrate that early and appropriately frequent interventions strike a balance between governance cost and effectiveness, offering valuable insights for practical applications. Our study underscores the significant utility and potential of LLMs in combating fake news.

The Sustainable Development Goals (SDGs) aim to resolve societal challenges, such as eradicating poverty and improving the lives of vulnerable populations in impoverished areas. Those areas rely on road infrastructure construction to promote accessibility and economic development. Although publicly available data like OpenStreetMap is available to monitor road status, data completeness in impoverished areas is limited. Meanwhile, the development of deep learning techniques and satellite imagery shows excellent potential for earth monitoring. To tackle the challenge of road network assessment in impoverished areas, we develop a systematic road extraction framework combining an encoder-decoder architecture and morphological operations on satellite imagery, offering an integrated workflow for interdisciplinary researchers. Extensive experiments of road network extraction on real-world data in impoverished regions achieve a 42.7% enhancement in the F1-score over the baseline methods and reconstruct about 80% of the actual roads. We also propose a comprehensive road network dataset covering approximately 794,178 km2 area and 17.048 million people in 382 impoverished counties in China. The generated dataset is further utilized to conduct socioeconomic analysis in impoverished counties, showing that road network construction positively impacts regional economic development. The technical appendix, code, and generated dataset can be found at https://github.com/tsinghua-fib-lab/Road_network_extraction_impoverished_counties.

This paper describes our response to a unique challenge presented by the Portuguese National Press-Mint: to use Artificial Intelligence to design a commemorative coin that celebrates the "digital world". We explain the process of this coin's co-creation, from conceptualisation to production, highlighting the design process, the underlying rationale, key obstacles encountered, and the technical innovations and developments made to meet the challenge. These include the development of an evolutionary art system guided by Contrastive Language–Image Pre-training (CLIP) and Machine Learning-based aesthetic models, a system for prompt evolution, and a representation for encoding genotypes in mintable format. This collaboration produced a limited edition 10 euro silver proof coin, with a total of 4000 units minted by the National Press-Mint. The coin was met with enthusiasm, selling out within two months. This work contributes to Computational Creativity, particularly co-creativity, co-design, and digital art, and represents a significant step in using Artificial Intelligence for Numismatics.

In an era where language biases contribute to societal inequalities, this research focuses on gender bias in textual data, with profound implications for promoting inclusivity and equity, aligning with United Nations Sustainable Development Goals (SDGs) and upholding the principle of Leave No One Behind (LNOB). Leveraging advances in artificial intelligence, the study introduces the GEnder-NEutralizing Text Transformation (GENETT) framework, addressing gender bias in text through auto-encoders, vector quantization, and Neutrality-Infused Stylization. Furthermore, we present the first-of-its-kind corpus of GEnder Neutralized REvisions (GENRE) crafted from gender-stereotyped versions. This corpus serves a multifaceted utility, offering a resource for diverse downstream tasks in gender-bias analysis. Extensive experimentation on GENRE highlights the superiority of the proposed model over established baselines and state-of-the-art methods. Access the code and dataset at 1. https://www.iitp.ac.in/~ai-nlp-ml/resources.html#GNR, 2. https://github.com/Soumitra816/GNR. Note: Our research focuses on understanding cyber harassment conversations, especially in under-researched areas, with the exclusion of non-binary cases due to existing dataset limitations, not lack of sensitivity. We strive for inclusivity and plan to address this in future research with suitable datasets.