United States

Multimodal hate detection, which aims to identify the harmful content online such as memes, is crucial for building a wholesome internet environment. Previous work has made enlightening exploration in detecting explicit hate remarks. However, most of their approaches neglect the analysis of implicit harm, which is particularly challenging as explicit text markers and demographic visual cues are often twisted or missing. The leveraged cross-modal attention mechanisms also suffer from the distributional modality gap and lack logical interpretability. To address these 
semantic gap issues, we propose TOT: a topology-aware optimal transport framework to decipher the implicit harm in memes scenario, which formulates the cross-modal aligning problem as solutions for optimal transportation plans. Specifically, we leverage an optimal transport kernel method to capture complementary information from multiple modalities. The kernel embedding provides a non-linear transformation ability to reproduce a kernel Hilbert space (RKHS), which reflects significance for eliminating the distributional modality gap. Moreover, we perceive the topology information based on aligned representations to conduct bipartite graph path reasoning. The newly achieved state-of-the-art performance on two publicly available benchmark datasets, together with  further visual analysis, demonstrate the superiority of TOT in capturing implicit cross-modal alignment.

AAAI 2023

TOTÔºöTopology-Aware Optimal Transport For Multimodal Hate Detection

multimodal hate detection

cross-modal alignment

optimal transport

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-23 is the Thirty-Seventh AAAI Conference on Artificial Intelligence. The theme of this conference is to create collaborative bridges within and beyond AI. Like previous AAAI conferences, AAAI-23 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and two new activities: a Bridge Program and a Lab Program. Many of these activities are tailored to the theme of bridges and all are selected according to the highest standards, with additional programs for students and young researchers. 
AAAI is providing you with a conference planner, which you can use to help organize your itinerary of activities. This includes talks to attend in person, talks to attend remotely, breaks with colleagues and your site seeing activities. To access this conference planner, please go to [https://aaai-2023.takemobi.io](https://aaai-2023.takemobi.io).

In order to access this site, you need to register. If you haven't already, please register [here](https://aaai.org/Conferences/AAAI-23/registration/).


The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines.

poster

Many fundamental low-rank optimization problems, such as matrix completion, phase retrieval, and robust PCA, can be formulated as the matrix sensing problem. Two main approaches for solving matrix sensing are based on semidefinite programming (SDP) and Burer-Monteiro (B-M) factorization. The former suffers from high computational and space complexities, whereas the latter may return a spurious solution due to the non-convexity of the problem. The existing theoretical guarantees for the success of these methods have led to similar conservative conditions, which may wrongly imply that these methods have comparable performances. In this paper, we shed light on some major differences between these two methods. First, we present a class of structured matrix completion problems for which the B-M methods fail with an overwhelming probability, while the SDP method works correctly. Second, we identify a class of highly sparse matrix completion problems for which the B-M method works and the SDP method fails. Third, we prove that although the B-M method exhibits the same performance independent of the rank of the unknown solution, the success of the SDP method is correlated to the rank of the solution and improves as the rank increases. Unlike the existing literature that has mainly focused on those instances of matrix sensing for which both SDP and B-M work, this paper offers the first result on the unique merit of each method over the alternative approach. 


Semidefinite Programming Versus Burer-Monteiro Factorization for Matrix Sensing

Predicting the trajectories of pedestrians in crowded conditions is an important task for applications like autonomous navigation systems. Previous studies have tackled this problem using two strategies. They (1) infer all future steps recursively, or (2) predict the potential destinations of pedestrians at once and interpolate the intermediate steps to arrive there. However, these strategies often suffer from the accumulated errors of the recursive inference, or restrictive assumptions about social relations in the intermediate path. In this paper, we present a graph convolutional network-based trajectory prediction. Firstly, we propose a control point prediction that divides the future path into three sections and infers the intermediate destinations of pedestrians to reduce the accumulated error. To do this, we construct multi-relational weighted graphs to account for their physical and complex social relations. We then introduce a trajectory refinement step based on a spatio-temporal and multi-relational graph. By considering the social interactions between neighbors, better prediction results are achievable. In experiments, the proposed network achieves state-of-the-art performance on various real-world trajectory prediction benchmarks.

A Set of Control Points Conditioned Pedestrian Trajectory Prediction

High-resolution (HR) images are usually downscaled to lowresolution (LR) ones for better display and afterward upscaled back to the original size to recover details. Recent work in image rescaling formulates downscaling and upscaling as a unified task and learns a bijective mapping between HR and LR via invertible networks. However, in real-world applications (e.g., social media), most images are compressed for transmission. Lossy compression will lead to irreversible information loss on LR images, hence damaging the inverse upscaling procedure and degrading the reconstruction accuracy. In this paper, we propose the Self-Asymmetric Invertible Network (SAIN) for compression-aware image rescaling. To tackle the distribution shift, we first develop an end-toend asymmetric framework with two separate bijective mappings for high-quality and compressed LR images, respectively. Then, based on empirical analysis of this framework, we model the distribution of the lost information (including downscaling and compression) using isotropic Gaussian mixtures and propose the Enhanced Invertible Block to derive high-quality/compressed LR images in one forward pass. Besides, we design a set of losses to regularize the learned LR images and enhance the invertibility. Extensive experiments demonstrate the consistent improvements of SAIN across various image rescaling datasets in terms of both quantitative and qualitative evaluation under standard image compression formats (i.e., JPEG and WebP).

Self-Asymmetric Invertible Network for Compression-Aware Image Rescaling

The ability to combine learned knowledge and skills to solve novel tasks is a key aspect of generalization in humans that allows us to understand and perform tasks described by novel language utterances. While progress has been made in supervised learning settings, no work has yet studied compositional generalization of a reinforcement learning agent following natural language instructions in an embodied environment. We develop a set of tasks in a photo-realistic simulated kitchen environment that allow us to study the degree to which a behavioral policy captures the systematicity in language by studying its zero-shot generalization performance on held out natural language instructions. We show that our agent which leverages a novel additive action-value decomposition in tandem with attention based subgoal prediction is able to exploit composition in text instructions to generalize to unseen tasks.

Learning Compositional Tasks from Language Instructions

This paper presents SVAM (Sequential Variance-Altered MLE), a unified framework for learning generalized linear models under adversarial label corruption in training data. SVAM extends to tasks such as least squares regression, logistic regression, and gamma regression, whereas many existing works on learning with label corruptions focus only on least squares regression. SVAM is based on a novel variance reduction technique that may be of independent interest and works by iteratively solving weighted MLEs over variance-altered versions of the GLM objective. SVAM offers provable model recovery guarantees superior to the state-of-the-art for robust regression even when a constant fraction of training labels are adversarially corrupted. SVAM also empirically outperforms several existing problem-specific techniques for robust regression and classification. Code for SVAM is available at https://github.com/purushottamkar/svam/

Corruption-tolerant Algorithms for Generalized Linear Models

With the increase of multi-view graph data, multi-view graph clustering (MVGC) that can discover the hidden clusters without label supervision has attracted growing attention from researchers. Existing MVGC methods are often sensitive to the given graphs, especially influenced by the low quality graphs, i.e., they tend to be limited by the homophily assumption. However, the widespread real-world data hardly satisfy the homophily assumption. This gap limits the performance of existing MVGC methods on low homogeneous graphs. To mitigate this limitation, our motivation is to extract high-level view-common information which is used to refine each view's graph, and reduce the influence of non-homogeneous edges. To this end, we propose dual label-guided graph refinement for multi-view graph clustering (DuaLGR), to alleviate the vulnerability in facing low homogeneous graphs. Specifically, DuaLGR consists of two modules named dual label-guided graph refinement module and graph encoder module. The first module is designed to extract the soft label from node features and graphs, and then learn a refinement matrix. In cooperation with the pseudo label from the second module, these graphs are refined and aggregated adaptively with different orders. Subsequently, a consensus graph can be generated in the guidance of the pseudo label. Finally, the graph encoder module encodes the consensus graph along with node features to produce the high-level pseudo label for iteratively clustering. The experimental results show the superior performance on coping with low homogeneous graph data.

Dual Label-Guided Graph Refinement for Multi-View Graph Clustering

Forecasting time series with extreme events has been a challenging and prevalent research topic, especially when the time series data are affected by complicated uncertain factors, such as is the case in hydrologic prediction. Diverse traditional and deep learning models have been applied to discover the nonlinear relationships and recognize the complex patterns in these types of data. However, existing methods usually ignore the negative influence of imbalanced data, or severe events, on model training. Moreover, methods are usually evaluated on a small number of generally well-behaved time series, which does not show their ability to generalize. To tackle these issues, we propose a novel probability-enhanced neural network model, called NEC+, which concurrently learns extreme and normal prediction functions and a way to choose among them via selective back propagation. We evaluate the proposed model on the difficult 3-day ahead hourly water level prediction task applied to 9 reservoirs in California. Experimental results demonstrate that the proposed model significantly outperforms state-of-the-art baselines and exhibits superior generalization ability on data with diverse distributions.

An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks

Automatic medical report generation is an essential task in applying artificial intelligence to the medical domain, which can lighten the workloads of doctors and promote clinical automation. The state-of-the-art approaches employ Transformer-based encoder-decoder architectures to align images and reports. However, they do not fully explore the relationships between multi-modal medical data, and generate inaccurate and incoherent reports. To address these issues, this paper proposes a Multi-modal Memory Transformer Network (MMTN) to cope with multi-modal medical data (i.e., medical image, medical terminology knowledge, and medical report text) for generating coherent medical reports. On the one hand, MMTN reduces the occurrence of image-report inconsistencies by designing a unique encoder to associate and memorize the relationship between medical images and terminologies. On the other hand, MMTN learns the contributions of multi-modal features before word prediction, and further enhances the accuracy and consistency of generating medical reports by exploiting the cross-modal complementarity of multi-modal medical data. Extensive experiments on three real datasets show that MMTN achieves significant effectiveness over state-of-the-art approaches on both automatic metrics and human evaluation.

MMTN: Multi-modal Memory Transformer Network for Image-Report Consistent Medical Report Generation

It is imperative to accelerate the training of neural network force field such as Deep Potential, which usually requires thousands of images based on first-principles calculation and a couple of days to generate an accurate potential energy surface. To this end, we propose a novel optimizer named reorganized layer extended Kalman filtering (RLEKF), an optimized version of global extended Kalman filtering (GEKF) with a strategy of splitting big and gathering small layers to overcome the $O(N^2)$ computational cost of GEKF. This strategy provides an approximation of the dense weights error covariance matrix with a sparse diagonal block matrix for GEKF. We implement both RLEKF and the baseline Adam in our $\alpha$Dynamics package and numerical experiments are performed on 13 unbiased datasets. Overall, RLEKF converges faster with slightly better accuracy. For example, a test on a typical system, bulk copper, shows that RLEKF converges faster by both the number of training epochs ($\times$11.67) and wall-clock time ($\times$1.19). Besides, we theoretically prove that the updates of weights converge and thus are against the gradient exploding problem. Experimental results verify that RLEKF is not sensitive to the initialization of weights. The RLEKF sheds light on other AI-for-science applications where training a large neural network (with tons of thousands parameters) is a bottleneck.

RLEKF: An Optimizer for Deep Potential with Ab Initio Accuracy

Air pollution is a crucial issue affecting human health and livelihoods, as well as one of the barriers to economic and social growth. Forecasting air quality has become an increasingly important endeavor with significant social impacts, especially in emerging countries like China. In this paper, we present a novel Transformer architecture termed AirFormer to collectively predict nationwide air quality in China, with an unprecedented fine spatial granularity covering thousands of locations. AirFormer decouples the learning process into two stages -- 1) a bottom-up deterministic stage that contains two new types of self-attention mechanisms to efficiently learn spatio-temporal representations; 2) a top-down stochastic stage with latent variables to capture the intrinsic uncertainty of air quality data. We evaluate AirFormer with 4-year data from 1,085 stations in the Chinese Mainland. Compared to the state-of-the-art model, AirFormer reduces prediction errors by 5%~8% on 72-hour future predictions. Our source code is available at https://github.com/yoshall/airformer.

Premium content

TOTÔºöTopology-Aware Optimal Transport For Multimodal Hate Detection

Downloads

Next from AAAI 2023

Semidefinite Programming Versus Burer-Monteiro Factorization for Matrix Sensing

Similar lecture

Unbalanced CO-Optimal Transport

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES