AAAI 2023 Papers

Social networks have enabled user-specific advertisements and recommendations on their platforms, which puts a significant focus on Influence Maximisation (IM) for target advertising and related tasks. The aim is to identify nodes in the network which can maximize the spread of information through a diffusion cascade. We propose a community structures-based approach that employs K-Shell algorithm with community structures to generate a score for the connections between seed nodes and communities. Further, our approach employs entropy within communities to ensure the proper spread of information within the communities. We validate our approach on four publicly available networks and show its superiority to four state-of-the-art approaches while still being relatively efficient.

Exemplar-based image translation refers to the task of generating images with the desired style, while conditioning on certain input image. Most of the current methods learn the correspondence between two input domains and lack the mining of information within the domain. In this paper, we propose a more general learning approach by considering two domain features as a whole and learning both inter-domain correspondence and intra-domain potential information interactions. Specifically, we propose a Cross-domain Feature Fusion Transformer (CFFT) to learn inter- and intra-domain feature fusion. Based on CFFT, the proposed CFFT-GAN works well on exemplar-based image translation. Moreover, CFFT-GAN is able to decouple and fuse features from multiple domains by cascading CFFT modules. We conduct rich quantitative and qualitative experiments on several image translation tasks, and the results demonstrate the superiority of our approach compared to state-of-the-art methods. Ablation studies show the importance of our proposed CFFT. Application experimental results reflect the potential of our method.

Vision Transformers (ViT) have made many breakthroughs in computer vision tasks. However, considerable redundancy arises in the spatial dimension of an input image, leading to massive computational costs. Therefore, We propose a coarse-to-fine vision transformer (CF-ViT) to relieve computational burden while retaining performance in this paper. Our proposed CF-ViT is motivated by two important observations in modern ViT models: (1) The coarse-grained patch splitting can locate informative regions of an input image. (2) Most images can be well recognized by a ViT model in a small-length token sequence. Therefore, our CF-ViT implements network inference in a two-stage manner. At coarse inference stage, an input image is split into a small-length patch sequence for a computationally economical classification. If not well recognized, the informative patches are identified and further re-split in a fine-grained granularity. Extensive experiments demonstrate the efficacy of our CF-ViT. For example, without any compromise on performance, CF-ViT reduces 53% FLOPs of LV-ViT, and also achieves 2.01x throughput. Code of this project is at https://github.com/ChenMnZ/CF-V

We study the problem of semantically annotating textual documents that are complex in the sense that the documents are long, feature rich, and domain specific. Due to their complexity, such annotation tasks require trained human workers, which are very expensive in both time and money. We propose CEMA, a method for deploying machine learning to assist humans in complex document annotation. CEMA estimates the human cost of annotating each document and selects the set of documents to be annotated that strike the best balance between model accuracy and human cost. We conduct experiments on complex annotation tasks in which we compare CEMA against other document selection and annotation strategies. Our results show that CEMA is the most cost-efficient solution for those tasks.

In the absence of assigned tasks, a learning agent typically seeks to explore its environment efficiently. However, the pursuit of exploration will bring more safety risks. An under-explored aspect of reinforcement learning is how to achieve safe efficient exploration when the task is unknown. In this paper, we propose a practical Constrained Entropy Maximization (CEM) algorithm to solve task-agnostic safe exploration problems, which naturally require a finite horizon and undiscounted constraints on safety costs. The CEM algorithm aims to learn a policy that maximizes state entropy under the premise of safety. To avoid approximating the state density in complex domains, CEM leverages a k-nearest neighbor entropy estimator to evaluate the efficiency of exploration. In terms of safety, CEM minimizes the safety costs, and adaptively trades off safety and exploration based on the current constraint satisfaction. The empirical analysis shows that CEM enables the acquisition of a safe exploration policy in complex environments, resulting in improved performance in both safety and sample efficiency for target tasks.

The limited number of actors and actions in existing datasets make 3D pose estimators tend to overfit, which can be seen from the performance degradation of the algorithm on cross-datasets, especially for rare and complex poses. Although previous data augmentation works have increased the diversity of the training set, the changes in camera viewpoint and position play a dominant role in improving the accuracy of the estimator, while the generated 3D poses are limited and still heavily rely on the source dataset. In addition, these works do not consider the adaptability of the pose estimator to generated data, and complex poses will cause training collapse. In this paper, we propose the CEE-Net, a Complementary End-to-End Network for 3D human pose generation and estimation. The generator extremely expands the distribution of each joint-angle in the existing dataset and limits them to a reasonable range. By learning the correlations within and between the torso and limbs, the estimator can combine different body-parts more effectively and weaken the influence of specific joint-angle changes on the global pose, improving the generalization ability. Extensive ablation studies show that our pose generator greatly strengthens the joint-angle distribution, and our pose estimator can utilize these poses positively. Compared with the state-of-the-art methods, our method can achieve much better performance on various cross-datasets, rare and complex poses.

Despite the excellent performance, deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples. Besides, these examples are often transferable among different models. In other words, the same adversarial example can fool multiple models with different architectures at the same time. Based on this property, many black-box transfer-based attack techniques have been developed. However, current transfer-based attacks generally focus on the cross-architecture setting, where the attacker has access to the training data of the target model, which is not guaranteed in realistic situations. In this paper, we design a Cross-Domain Transfer-Based Attack (CDTA), which works in the cross-domain scenario. In this setting, attackers have no information about the target model, such as its architecture and training data. Specifically, we propose a contrastive spectral training method to train a feature extractor on a source domain (e.g., ImageNet) and use it to craft adversarial examples on target domains (e.g., Oxford 102 Flower). Our method corrupts the semantic information of the benign image by scrambling the outputs of both the intermediate feature layers and the final layer of the feature extractor. We evaluate CDTA with 16 target deep models on four datasets with widely varying styles. The results confirm that, in terms of the attack success rate, our approach can consistently outperform the state-of-the-art baselines by an average of 11.45% across all target models. Our code is available at https://github.com/LiulietLee/CDTA.

Minimax problems arise in a wide range of important applications including robust adversarial learning and Generative Adversarial Network (GAN) training. Recently, algorithms for minimax problems in the Federated Learning (FL) paradigm have received considerable interest. Existing federated algorithms for general minimax problems require the full aggregation (i.e., aggregation of local model information from all clients) in each training round. Thus, they are inapplicable to an important setting of FL known as the cross-device setting, which involves numerous unreliable mobile/IoT devices. In this paper, we develop the first practical algorithm named CDMA for general minimax problems in the cross-device FL setting. CDMA is based on a Start-Immediately-With-Enough-Responses mechanism, in which the server first signals a subset of clients to perform local computation and then starts to aggregate the local results reported by clients once it receives responses from enough clients in each round. With this mechanism, CDMA is resilient to the low client availability. In addition, CDMA is incorporated with a lightweight global correction in the local update steps of clients, which mitigates the impact of slow network connections. We establish theoretical guarantees of CDMA under different choices of hyperparameters and conduct experiments on AUC maximization, robust adversarial network training, and GAN training tasks. Theoretical and experimental results demonstrate the efficiency of CDMA.

Learning multi-organ segmentation from multiple partially-labeled datasets attracts increasing attention. It can be a promising solution for the scarcity of large-scale, fully labeled 3D medical image segmentation datasets. However, existing algorithms of multi-organ segmentation on partially-labeled datasets neglect the semantic relations and anatomical priors between different categories of organs, which is crucial for partially-labeled multi-organ segmentation. In this paper, we tackle the limitations above by proposing the Cross-Class Query Network (CCQ). CCQ consists of an image encoder, a cross-class query learning module, and an attentive refinement segmentation module. More specifically, the image encoder captures the long-range dependency of a single image via the transformer encoder. Cross-class query learning module first generates query vectors that represent semantic concepts of different categories and then utilizes these query vectors to find the class-relevant features of image representation for segmentation. The attentive refinement segmentation module with an attentive skip connection incorporates the high-resolution image details and eliminates the class-irrelevant noise. Extensive experiment results demonstrate that CCQ outperforms all the state-of-the-art models on the MOTS dataset, which consists of seven organ and tumor segmentation tasks. Code is available at https://github.com/Yang-007/CCQ.git.

Contrastive Language-Image Pre-training (CLIP) has been shown to learn visual representations with promising zero-shot performance. To further improve its downstream accuracy, existing works propose additional learnable modules upon CLIP and fine-tune them by few-shot training sets. However, the resulting extra training cost and data requirement severely hinder the efficiency for model deployment and knowledge transfer. In this paper, we introduce a free-lunch enhancement method, CALIP, to boost CLIP's zero-shot performance via a parameter-free attention module. Specifically, we guide visual and textual representations to interact with each other and explore cross-modal informative features via attention. As the pre-training has largely reduced the embedding distances between two modalities, we discard all learnable parameters in the attention and bidirectionally update the multi-modal features, enabling the whole process to be parameter-free and training-free. In this way, the images are blended with textual-aware signals and the text representations become visual-guided for better adaptive zero-shot alignment. We evaluate CALIP on various benchmarks of 14 datasets for both 2D image and 3D point cloud few-shot classification, showing consistent zero-shot performance improvement over CLIP. Based on that, we further insert a small number of linear layers in CALIP's attention module and verify our robustness under the few-shot settings, which also achieves leading performance compared to existing methods. Those extensive experiments demonstrate the superiority of our approach for efficient enhancement of CLIP. Code is available at https://github.com/ZiyuGuo99/CALIP.

Event sequences in continuous time space are ubiquitous across applications and have been intensively studied with both classic temporal point process (TPP) and its recent deep network variants. This work is motivated by an observation that many of event data exhibit inherent clustering patterns in terms of the sparse correlation among events, while such characteristics are seldom explicitly considered in existing neural TPP models whereby the history encoders are often embodied by RNNs or Transformers. In this work, we propose a c-NTPP (Cluster-Aware Neural Temporal Point Process) model, which leverages a sequential variational autoencoder framework to infer the latent cluster each event belongs to in the sequence. Specially, a novel event-clustered attention mechanism is devised to learn each cluster and then aggregate them together to obtain the final representation for each event. Extensive experiments show that c-NTPP achieves superior performance on both real-world and synthetic datasets, and it can also uncover the underlying clustering correlations.

This paper summarizes my research roadmap for building compositional robot autonomy with the principles of modularity and abstraction.

As artificial intelligence (AI) becomes a prominent part of modern life, AI literacy is becoming important for all citizens, not just those in technology careers. Previous research in AI education materials has largely focused on the introduction of terminology as well as AI use cases and ethics, but few allow students to learn by creating their own machine learning models. Therefore, there is a need for enriching AI educational tools with more adaptable and flexible platforms for interested educators with any level of technical experience to utilize within their teaching material. As such, we propose the development of an open-source tool (Build-A-Bot) for students and teachers to not only create their own transformer-based chatbots based on their own course material but also learn the fundamentals of AI through the model creation process. The primary concern of this paper is the creation of an interface for students to learn the principles of artificial intelligence by using a natural language pipeline to train a customized model to answer questions based on their own school curriculums. The model uses contexts given by their instructor, such as chapters of a textbook, to answer questions and is deployed on an interactive chatbot/voice agent. The pipeline teaches students data collection, data augmentation, intent recognition, and question answering by having them work through each of these processes while creating their AI agent, diverging from previous chatbot work where students and teachers use the bots as black-boxes with no abilities for customization or the bots lack AI capabilities, with the majority of dialogue scripts being rule-based. In addition, our tool is designed to make each step of this pipeline intuitive for students at a middle-school level. Further work primarily lies in providing our tool to schools and seeking student and teacher evaluations.

ImageNet-1k is a dataset often used for benchmarking machine learning (ML) models and evaluating tasks such as image recognition and object detection. Wild animals make up 27% of ImageNet-1k but, unlike classes representing people and objects, these data have not been closely scrutinized. In the current paper, we analyze the 13,450 images from 269 classes that represent wild animals in the ImageNet-1k validation set, with the participation of expert ecologists. We find that many of the classes are ill-defined or overlapping, and that 12% of the images are incorrectly labeled, with some classes having >90% of images incorrect. We also find that both the wildlife-related labels and images included in ImageNet-1k present significant geographical and cultural biases, as well as ambiguities such as artificial animals, multiple species in the same image, or the presence of humans. Our findings highlight serious issues with the extensive use of this dataset for evaluating ML systems, the use of such algorithms in wildlife-related tasks, and more broadly the ways in which ML datasets are commonly created and curated.

Vision-Language (VL) models with the Two-Tower architecture have dominated visual-language representation learning in recent years. Current VL models either use lightweight uni-modal encoders and learn to extract, align and fuse both modalities simultaneously in a deep cross-modal encoder, or feed the last-layer uni-modal representations from the deep pre-trained uni-modal encoders into the top cross-modal encoder. Both approaches potentially restrict vision-language representation learning and limit model performance. In this paper, we propose BridgeTower, which introduces multiple bridge layers that build a connection between the top layers of uni-modal encoders and each layer of the cross-modal encoder. This enables effective bottom-up cross-modal alignment and fusion between visual and textual representations of different semantic levels of pre-trained uni-modal encoders in the cross-modal encoder. Pre-trained with only 4M images, BridgeTower achieves state-of-the-art performance on various downstream vision-language tasks. In particular, on the VQAv2 test-std set, BridgeTower achieves an accuracy of 78.73%, outperforming the previous state-of-the-art model METER by 1.09% with the same pre-training data and almost negligible additional parameters and computational costs. Notably, when further scaling the model, BridgeTower achieves an accuracy of 81.15%, surpassing models that are pre-trained on orders-of-magnitude larger datasets. Code and checkpoints are available at https://github.com/microsoft/BridgeTower.

Few-shot object detection, expecting detectors to detect novel classes with a few instances, has made conspicuous progress. However, the prototypes extracted by existing meta-learning based methods still suffer from insufficient representative information and lack awareness of query images, which cannot be adaptively tailored to different query images. Firstly, only the support images are involved for extracting prototypes, resulting in scarce perceptual information of query images. Secondly, all pixels of all support images are treated equally when aggregating features into prototype vectors, thus the salient objects are overwhelmed by the cluttered background. In this paper, we propose an Information-Coupled Prototype Elaboration (ICPE) method to generate specific and representative prototypes for each query image. Concretely, a conditional information coupling module is introduced to couple information from the query branch to the support branch, strengthening the query-perceptual information in support features. Besides, we design a prototype dynamic aggregation module that dynamically adjusts intra-image and inter-image aggregation weights to highlight the salient information useful for detecting query images. Experimental results on both Pascal VOC and MS COCO demonstrate that our method achieves state-of-the-art performance in almost all settings. Code will be available at: https://github.com/lxn96/ICPE.

The abundance of data has given machine learning considerable momentum in natural sciences and engineering, though modeling of physical processes is often difficult. A particularly tough problem is the efficient representation of geometric boundaries. Triangularized geometric boundaries are well understood and ubiquitous in engineering applications. However, it is notoriously difficult to integrate them into machine learning approaches due to their heterogeneity with respect to size and orientation. In this work, we introduce an effective theory to model particle-boundary interactions, which leads to our new Boundary Graph Neural Networks (BGNNs) that dynamically modify graph structures to obey boundary conditions. The new BGNNs are tested on complex 3D granular flow processes of hoppers, rotating drums and mixers, which are all standard components of modern industrial machinery but still have complicated geometry. BGNNs are evaluated in terms of computational efficiency as well as prediction accuracy of particle flows and mixing entropies. BGNNs are able to accurately reproduce 3D granular flows within simulation uncertainties over hundreds of thousands of simulation timesteps. Most notably, in our experiments, particles stay within the geometric objects without using handcrafted conditions or restrictions.

Previous researches on multimedia fake news detection include a series of complex feature extraction and fusion networks to gather useful information from the news. However, how cross-modal consistency relates to the fidelity of news and how features from different modalities affect the decision-making are still open questions. This paper presents a novel scheme of Bootstrapping Multi-view Representations (BMR) for fake news detection. Given a multi-modal news, we extract representations respectively from the views of the text, the image pattern and the image semantics. Improved Multi-gate Mixture-of-Expert networks (iMMoE) are proposed for feature refinement and fusion. Representations from each view are separately used to coarsely predict the fidelity of the whole news, and the multimodal representations are able to predict the cross-modal consistency. With the prediction scores, we reweigh each view of the representations and bootstrap them for fake news detection. Extensive experiments conducted on typical fake news detection datasets prove that BMR outperforms state-of-the-art schemes.

Recent breakthroughs in semi-supervised semantic segmentation have been developed through contrastive learning. In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the latent space. However, there exist inaccurate pseudo-labels which map the ambiguous representations of pixels to the wrong classes due to the limited cognitive ability of the model. In this paper, we define pixel-wise representations from a new perspective of probability theory and propose a Probabilistic Representation Contrastive Learning (PRCL) framework that improves representation quality by taking its probability into consideration. Through modelling the mapping from pixels to representations as the probability via multivariate Gaussian distributions, we can tune the contribution of the ambiguous representations to tolerate the risk of inaccurate pseudo-labels. Furthermore, we define prototypes in the form of distributions, which indicates the confidence of a class, while the point prototype cannot. More- over, we propose to regularize the distribution variance to enhance the reliability of representations. Taking advantage of these benefits, high-quality feature representations can be derived in the latent space, thereby the performance of se- mantic segmentation can be further improved. We conduct sufficient experiment to evaluate PRCL on Pascal VOC and CityScapes to demonstrate its superiority. The code is available at https://github.com/Haoyu-Xie/PRCL.