IJCAI 2024 Papers

We introduce an open-source platform for annotating body-worn video (BWV) footage aimed at enhancing transparency and accountability in policing. Despite the widespread adoption of BWVs in police departments, analyzing the vast amount of footage generated has presented significant challenges. This is primarily due to resource constraints, the sensitive nature of the data, which limits widespread access, and consequently, lack of annotations for training machine learning models. Our platform, called CVAT-BWV, offers a secure, locally hosted annotation environment that integrates several AI tools to assist in annotating multimodal data. With features such as automatic speech recognition, speaker diarization, object detection, and face recognition, CVAT-BWV aims to reduce the manual annotation workload, improve annotation quality, and allow for capturing perspectives from a diverse population of annotators. This tool aims to streamline the collection of annotations and the building of models, enhancing the use of BWV data for oversight and learning purposes to uncover insights into police-civilian interactions.

Scalability and training time are crucial for any graph neural network model processing a knowledge graph (KG). While partitioning knowledge graphs helps reduce the training time, the prediction accuracy reduces significantly compared to training the model on the whole graph. In this paper, we propose CPa-WAC: a lightweight architecture that incorporates graph convolutional networks and modularity maximization-based constellation partitioning to harness the power of local graph topology. The proposed CPa-WAC method reduces the training time and memory cost of knowledge graph embedding, making the learning model scalable. The results from our experiments on standard databases, such as Wordnet and Freebase, show that by achieving meaningful partitioning, any knowledge graph can be broken down into subgraphs and processed separately to learn embeddings. Furthermore, these learned embeddings can be used for knowledge graph completion, retaining similar performance compared to training a GCN on the whole KG, while speeding up the training process by upto five times. Additionally, the proposed CPa-WAC method outperforms several other state-of-the-art KG in terms of prediction accuracy.

As a popular task in graph learning, node classification seeks to assign labels to nodes, taking into account both their features and connections. However, an important challenge for its application in real-world scenarios is the presence of newly-emerged out-of-distribution samples and noisy samples, which affect the quality and robustness of learned classifiers. Out-of-distribution (OOD) samples are often found in both the training and testing phases. Such samples don’t belong to any known categories. These OOD samples are considered as outliers (OOD noise) when they appear during training, and are recognized as open-set samples during the testing. Meanwhile, in-distribution (IND) noisy data, i.e., known class samples with wrong labels, are also prevalent and inevitably degrade a model’s performance. The challenge of open-set learning with complex IND and OOD noise remains largely unexplored, particularly when dealing with non-IID graph data. To address these challenges, this paper introduces a novel complex-noise-resistant open-set node classification approach, designed for open-set graph data containing both IND and OOD noisy nodes. Specifically, a trustworthiness learner is adopted to learn the trustworthiness rates of the feature and label for each node while a decoder and an open-set classifier are trained to reconstruct the structure of a node and to predict its category simultaneously with the guidance of node trustworthiness. The experimental results demonstrate the superiority of our method.

Multi-modal large language models(MLLMs) have achieved remarkable progress and demonstrated powerful knowledge comprehension and reasoning abilities. However, the mastery of domain-specific knowledge, which is essential for evaluating the intelligence of MLLMs, continues to be a challenge. Current multi-modal benchmarks for domain-specific knowledge concentrate on multiple-choice questions and are predominantly available in English, which imposes limitations on the comprehensiveness of the evaluation. To this end, we introduce CMMU, a novel benchmark for multi-modal and multi-type question understanding and reasoning in Chinese. CMMU consists of 3,603 questions in 7 subjects, covering knowledge from primary to high school. The questions can be categorized into 3 types: multiple-choice, multiple-response, and fill-in-the-blank, bringing greater challenges to MLLMs. In addition, we propose an evaluation strategy called Positional Error Variance for assessing multiple-choice questions. The strategy aims to perform a quantitative analysis of position bias. We evaluate seven open-source MLLMs along with GPT4-V, Gemini-Pro, and Qwen-VL-Plus. The results demonstrate that CMMU poses a significant challenge to the recent MLLMs. The data and code are available at https://github.com/FlagOpen/CMMU.

Explanatory Artificial Intelligence plays a vital role in machine learning, due to its widespread application in decision-making scenarios, e.g., credit lending. Counterfactual Explanation (CFE) is a new kind of explanatory method that involves asking “what if ”, i.e. what would have happened if model inputs slightly change. To answer the question, Counterfactual Explanation aims at finding a minimum perturbation in model inputs leading to a different model decision. Compared with model-agnostic approaches, model-specific CFE approaches designed only for specific type of models usually have better performance in finding optimal counterfactual perturbations, owing to access to the inner workings of models. To deal with this dilemma, this work first proposes CMAES-based Counterfactual Explanations (CMACE): an effective model-agnostic counterfactual generating approach based on Covariance Matrix Adaptation Evolution Strategy (CMA-ES) and a warm starting scheme that provides good initialization of the counterfactual's mean and covariance parameters for CMA-ES taking advantage of prior information of training samples. CMACE significantly outperforms another state-of-art (SOTA) model-agnostic approach (Bayesian Counterfactual Generator, BayCon) with various experimental settings. Extensive experiments also demonstrate that CMACE is superior to a SOTA model-specific approach (Flexible Optimizable Counterfactual Explanations for Tree Ensembles, FOCUS) that is designed for tree-based models using gradient-based optimization.

Recent generative methods have shown promising blind face restoration performance. They usually project the degraded images to the latent space and then decode high-quality faces either by single-stage latent optimization or directly from the encoding. Generating fine-grained facial details faithful to inputs remains challenging. Most existing methods produce either overly smooth outputs or alter the identity. This could be attributed to the typical trade-off between quality and resolution in the latent space. If the latent is highly compressed, the decoded output is more robust to degradations but shows worse fidelity. On the other hand, a more flexible latent space can capture intricate details better, but is extremely difficult to optimize for highly degraded faces. We introduce a diffusion-based-prior inside a VQGAN architecture that focuses on learning the distribution over uncorrupted latent embeddings. We iteratively recover the clean embedding conditioning on the degraded counterpart. Furthermore, to ensure the reverse diffusion trajectory does not deviate from the underlying identity, we train a separate Identity Recovery Network and use its output to constrain the reverse diffusion. Specifically, using a learnable latent mask, we add gradients from a face-recognition network to a subset of latent features that correlates with the finer identity-related details in the pixel space, leaving the other features untouched. Disentanglement between perception and fidelity in the latent space allows us to achieve the best of both worlds. We perform extensive evaluations on multiple real and synthetic datasets to validate our approach.

Few-shot anomaly classification (FSAC) is a vital task in manufacturing industry. Recent methods focus on utilizing CLIP in zero/few normal shot anomaly detection instead of custom models. However, there is a lack of specific text prompts in anomaly classification and most of them ignore the modality gap between image and text. Meanwhile, there is distribution discrepancy between the pre-trained and the target data. To provide a remedy, in this paper, we propose a method to boost CLIP for few-normal-shot anomaly classification, dubbed CLIP-FSAC, which contains two-stage of training and alternating fine-tuning with two modality-specific adapters. Specifically, in the first stage, we train image adapter with text representation output from text encoder and introduce an image-to-text tuning to enhance multi-modal interaction and facilitate a better language-compatible visual representation. In the second stage, we freeze the image adapter to train the text adapter. Both of them are constrained by fusion-text contrastive loss. Comprehensive experiment results are provided for evaluating our method in few-normal-shot anomaly classification, which outperforms the state-of-the-art method by 12.2%, 10.9%, 10.4% AUROC on VisA for 1, 2, and 4-shot settings.

Image Captioning generates descriptive sentences from images using Vision-Language Pre-trained models (VLPs) such as BLIP, which has improved greatly. However, current methods lack the generation of detailed descriptive captions for the cultural elements depicted in the images, such as the traditional clothing worn by people from Asian cultural groups. In this paper, we propose a new framework, Culturally-aware Image Captioning (CIC), that generates captions and describes cultural elements extracted from cultural visual elements in images representing cultures. Inspired by methods combining visual modality and Large Language Models (LLMs) through appropriate prompts, our framework (1) generates questions based on cultural categories from images, (2) extracts cultural visual elements from Visual Question Answering (VQA) using generated questions, and (3) generates culturally-aware captions using LLMs with the prompts. Our human evaluation conducted on 45 participants from 4 different cultural groups with a high understanding of the corresponding culture shows that our proposed framework generates more culturally descriptive captions when compared to the image captioning baseline based on VLPs. Resources can be found at https://shane3606.github.io/cic.

The explosion of massive urban data recently has provided us with a valuable opportunity to gain deeper insights into urban regions and the daily lives of residents. Urban region representation learning emerges as a crucial realm for fulfilling this task. Among deep learning approaches, graph neural networks (GNNs) have shown promise, given that city elements can be naturally represented as nodes with various connections between them as edges. However, many existing GNN approaches encounter challenges such as over-smoothing and limitations in capturing information from nodes in other regions, resulting in the loss of crucial urban information and a decline in region representation performance. To address these challenges, we leverage urban graph structure information and introduce a hierarchical graph pooling process called Coarsened Graph Attention Pooling (CGAP). CGAP features local attention units to create coarsened intermediate graphs and global features. Additionally, by incorporating urban region graphs and global features into a global attention layer, we harness relational information to enhance representation effectiveness. Furthermore, CGAP integrates region attributes such as Points of Interest (POIs) and inter-regional contexts like human mobility, enabling the exploitation of multi-modal urban data for more comprehensive representation learning. Experiments on three downstream tasks related to the UN Sustainable Development Goals validate the effectiveness of region representations learned by our approach. Experimental results and analyses demonstrate that CGAP excels in various socioeconomic prediction tasks compared to competitive baselines.

Weakly aligned visible-infrared object detection poses significant challenges due to the imprecise alignment between visible and infrared images. Most existing methods explore the alignment strategies between visible and infrared images, yielding unbearable computation costs. This paper first proposes an end-to-end alignment-free architecture Cross-modal Fusion Deformable DEtection TRansformer (``CF-Deformable DETR'') for weakly aligned visible-infrared object detection. Abandoning the traditional image alignment, CF-Deformable DETR introduces a simple yet effective cross-modal deformable attention mechanism to directly implement automatic cross-modal point mapping, generating well-aligned bimodal features with high efficiency. Moreover, we design a Point-level Feature Consistency Loss to guide the cross-modal point mapping, ensuring the consistency of paired features to support the following fusion. Extensive experiments are conducted on three benchmark datasets. The experimental results demonstrate that CF-Deformable DETR achieves close accuracy on weakly aligned and strictly aligned data as well as maintains stable performance to a certain extent against various offset degrees of weakly aligned data. Code is available at https://github.com/116508/CF-Deformable-DETR.

Trajectory prediction is a cornerstone in autonomous driving (AD), playing a critical role in enabling vehicles to navigate safely and efficiently in dynamic environments. To address this task, this paper presents a novel trajectory prediction model tailored for accuracy in the face of heterogeneous and uncertain traffic scenarios. At the heart of this model lies the Characterized Diffusion Module, an innovative module designed to simulate traffic scenarios with inherent uncertainty. This module enriches the predictive process by infusing it with detailed semantic information, thereby enhancing trajectory prediction accuracy. Complementing this, our Spatio-Temporal (ST) Interaction Module captures the nuanced effects of traffic scenarios on vehicle dynamics across both spatial and temporal dimensions with remarkable effectiveness. Demonstrated through exhaustive evaluations, our model sets a new standard in trajectory prediction, achieving state-of-the-art (SOTA) results on the Next Generation Simulation (NGSIM), Highway Drone (HighD), and Macao Connected Autonomous Driving (MoCAD) datasets across both short and extended temporal spans. This performance underscores the model's unparalleled adaptability and efficacy in navigating complex traffic scenarios, including highways, urban streets, and intersections.

Neural predictors are effective in boosting the time-consuming performance evaluation stage in neural architecture search (NAS), owing to their direct estimation of unseen architectures. Despite the effectiveness, training a powerful neural predictor with fewer annotated architectures remains a huge challenge. In this paper, we propose a context-aware neural predictor (CAP) which only needs a few annotated architectures for training based on the contextual information from the architectures. Specifically, the input architectures are encoded into graphs and the predictor infers the contextual structure around the nodes inside each graph. Then, enhanced by the proposed context-aware self-supervised task, the pre-trained predictor can obtain expressive and generalizable representations of architectures. Therefore, only a few annotated architectures are sufficient for training. Experimental results in different search spaces demonstrate the superior performance of CAP compared with state-of-the-art neural predictors. In particular, CAP can rank architectures precisely at the budget of only 172 annotated architectures in NAS-Bench-101. Moreover, CAP can help find promising architectures in both NAS-Bench-101 and DARTS search spaces on the CIFAR-10 dataset, serving as a useful navigator for NAS to explore the search space efficiently.

Vision-Language Instruction Tuning (VLIT) is a critical training phase for Large Vision-Language Models (LVLMs). With the improving capabilities of open-source LVLMs, researchers have increasingly turned to generate VLIT data by using open-source LVLMs and achieved significant progress. However, such data generation approaches are bottlenecked by the following challenges: 1) Since multi-modal models tend to be influenced by prior language knowledge, directly using LVLMs to generate VLIT data would inevitably lead to low content relevance between generated data and images. 2) To improve the ability of the models to generate VLIT data, previous methods have incorporated an additional training phase to boost the generative capacity. This process hurts the generalization of the models to unseen inputs (i.e., “exposure bias” problem). In this paper, we propose a new Content Correlated VLIT data generation via Contrastive Learning (C3L). Specifically, we design a new content relevance module which enhances the content relevance between VLIT data and images by computing Image Instruction Correspondence Scores S(I2C). Moreover, a contrastive learning module is introduced to further boost the VLIT data generation capability of the LVLMs. A large number of automatic measures on four benchmarks show the effectiveness of our method.

Answer Set Programming (ASP) is a key paradigm for problems in artificial intelligence and industrial contexts. In ASP, problems are modeled via a set of rules. Over the time this paradigm grew into a rich language, enabling complex rule types like aggregate expressions. Most practical ASP systems follow a ground-and-solve pattern, where rule schemes are grounded and resulting rules are solved. There, the so-called grounding bottleneck may prevent from solving, due to sheer grounding sizes. Recently body-decoupled grounding (BDG) demonstrated how to reduce grounding sizes by delegating effort to solving. However, BDG provides limited interoperability with traditional grounders and only covers simple rule types. In this work, we establish hybrid grounding — based on a novel splitting theorem that allows us to freely combine BDG with traditional grounders. To mitigate huge groundings in practice, we define rewriting procedures for efficiently deferring grounding effort of aggregates to solving. Our experimental results indicate that this approach is competitive, especially for instances, where traditional grounding fails.

In the rapidly evolving landscape of eCommerce, Artificial Intelligence (AI) based pricing algorithms, particularly those utilizing Reinforcement Learning (RL), are becoming increasingly prevalent. This rise has led to an inextricable pricing situation with the potential for market collusion. Our research employs an experimental oligopoly model of repeated price competition, systematically varying the environment to cover scenarios from basic economic theory to subjective consumer demand preferences. We also introduce a novel demand framework that enables the implementation of various demand models, allowing for a weighted blending of different models. In contrast to existing research in this domain, we aim to investigate the strategies and emerging pricing patterns developed by the agents, which may lead to a collusive outcome. Furthermore, we investigate a scenario where agents cannot observe their competitors’ prices. Finally, we provide a comprehensive legal analysis across all scenarios. Our findings indicate that RL-based AI agents converge to a collusive state characterized by the charging of supracompetitive prices, without necessarily requiring inter-agent communication. Implementing alternative RL algorithms, altering the number of agents or simulation settings, and restricting the scope of the agents’ observation space does not significantly impact the collusive market outcome behavior.

We present a comprehensive survey of the advancements and techniques in the field of tractable probabilistic generative modeling, primarily focusing on Probabilistic Circuits (PCs). We provide a unified perspective on the inherent trade-offs between expressivity and tractability, highlighting the design principles and algorithmic extensions that have enabled building expressive and efficient PCs, and provide a taxonomy of the field. We also discuss recent efforts to build deep and hybrid PCs by fusing notions from deep neural models, and outline the challenges and open questions that can guide future research in this evolving field.

In recent decades, the design of budget feasible mechanisms for a wide range of procurement auction settings has received significant attention in the Artificial Intelligence (AI) community. These procurement auction settings have practical applications in various domains such as federated learning, crowdsensing, edge computing, and resource allocation. In a basic procurement auction setting of these domains, a buyer with a limited budget is tasked with procuring items (\eg, goods or services) from strategic sellers, who have private information on the true costs of their items and incentives to misrepresent their items' true costs. The primary goal of budget feasible mechanisms is to elicit the true costs from sellers and determine items to procure from sellers to maximize the buyer valuation function for the items and ensure that the total payment to the sellers is no more than the budget. In this survey, we provide a comprehensive overview of key procurement auction settings and results of budget feasible mechanisms. We provide several promising future research directions.

We introduce a Cascaded Diffusion Model (Cas-DM) that improves a Denoising Diffusion Probabilistic Model (DDPM) by effectively incorporating additional metric functions in training. Metric functions such as the LPIPS loss have been proven highly effective in consistency models derived from the score matching. However, for the diffusion counterparts, the methodology and efficacy of adding extra metric functions remain unclear. One major challenge is the mismatch between the noise predicted by a DDPM at each step and the desired clean image that the metric function works well on. To address this problem, we propose Cas-DM, a network architecture that cascades two network modules to effectively apply metric functions to the diffusion model training. The first module, similar to a standard DDPM, learns to predict the added noise and is unaffected by the metric function. The second cascaded module learns to predict the clean image, thereby facilitating the metric function computation. Experiment results show that the proposed diffusion model backbone enables the effective use of the LPIPS loss, improving the image quality (FID, sFID) of diffusion models on various established benchmarks.

In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data. The central challenge is the substantial learning gap between seen and novel categories, as the model learns the former faster due to accurate supervisory information. Moreover, capturing the semantics of unlabeled novel category samples is also challenging due to the missing label information. To address the above issues, we introduce 1) the adaptive synchronizing marginal loss which imposes class-specific negative margins to alleviate the model bias towards seen classes, and 2) the pseudo-label contrastive clustering which exploits pseudo-labels predicted by the model to group unlabeled data from the same category together in the output space. Extensive experiments on benchmark datasets demonstrate that previous approaches may significantly hinder novel class learning, whereas our method strikingly balances the learning pace between seen and novel classes, achieving a remarkable 3% average accuracy increase on the ImageNet dataset. Importantly, we find that fine-tuning the self-supervised pre-trained model significantly boosts the performance, which is overlooked in prior literature. Our code is available at https://github.com/yebo0216best/LPS-main.