United States

With the rise of AI used for critical decision-making, many important
predictions are made by complex and opaque AI algorithms. The aim of
eXplainable Artificial Intelligence (XAI) is to make these opaque
decision-making algorithms more transparent and trustworthy. This is
often done by constructing an ``explainable model&#39;&#39; for a single modality or subsystem. However, this approach fails for complex systems that are made out of multiple parts. In this paper, I discuss how to explain complex system failures. 
I represent a complex machine as a hierarchical model of introspective sub-systems working together towards a common goal. The subsystems communicate in a common symbolic language. This work creates a set of explanatory accountability layers for
trustworthy AI.

AAAI 2023

Accountability Layers

societal impact of ai

robustness & trustworthiness

explainable ml

safety

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.

With the rise of AI used for critical decision-making, many important
predictions are made by complex and opaque AI algorithms. The aim of
eXplainable Artificial Intelligence (XAI) is to make these opaque
decision-making algorithms more transparent and trustworthy. This is
often done by constructing an ``explainable model'' for a single modality or subsystem. However, this approach fails for complex systems that are made out of multiple parts. In this paper, I discuss how to explain complex system failures. 
I represent a complex machine as a hierarchical model of introspective sub-systems working together towards a common goal. The subsystems communicate in a common symbolic language. This work creates a set of explanatory accountability layers for
trustworthy AI.

technical paper

Recently, progress has been made towards improving automatic sarcasm detection in computer science. Among existing models, manually constructing static graphs for texts and then using graph neural networks (GNNs) is one of the most effective approaches for drawing long-range incongruity patterns. However, the manually constructed graph structure might be prone to errors (e.g., noisy or incomplete) and not optimal for the sarcasm detection task. Errors produced during the graph construction step cannot be remedied and may accrue to the following stages, resulting in poor performance. To surmount the above limitations, we explore a novel Iterative Augmenting Affective Graph and Dependency Graph (IAAD) framework to jointly and iteratively learn the incongruity graph structure. IAAD can alternatively update the incongruity graph structure and node representation until the learning graph structure is optimal for the metrics of sarcasm detection. More concretely, we begin with deriving an affective and a dependency graph for each instance, then an iterative incongruity graph learning module is employed to augment affective and dependency graphs for obtaining the optimal inconsistent semantic graph with the goal of optimizing the graph for the sarcasm detection task. Extensive experiments on three datasets demonstrate that the proposed model outperforms state-of-the-art baselines for sarcasm detection with significant margins.

Augmenting Affective Dependency Graph via Iterative Incongruity Graph Learning for Sarcasm Detection

The goal of inductive logic programming (ILP) is to search for a hypothesis that generalises training examples and background knowledge (BK). To improve performance, we introduce an approach that, before searching for a hypothesis, first discovers "where not to search". We use given BK to discover constraints on hypotheses, such as that a number cannot be both even and odd. We use the constraints to bootstrap a constraint-driven ILP system. Our experiments on multiple domains (including program synthesis and inductive general game playing) show that our approach can (i) substantially reduce learning times by up to 97%, and (ii) can scale to domains with millions of facts.

Learning Logic Programs by Discovering Where Not to Search

Recent works on learning-based frameworks for Lagrangian (i.e., particle-based) fluid simulation, though bypassing iterative pressure projection via efficient convolution operators, are still time-consuming due to excessive amount of particles. To address this challenge, we propose a dynamic multi-scale gridding method to reduce the magnitude of elements that have to be processed, by observing repeated particle motion patterns within certain consistent regions. Specifically, we hierarchically generate multi-scale micelles in Euclidean space by grouping particles that share similar motion patterns/characteristics based on super-light motion and scale estimation modules. With little internal motion variation, each micelle is modeled as a single rigid body with convolution only applied to a single representative particle. In addition, a distance-based interpolation is conducted to propagate relative motion message among micelles. With our efficient design, the network produces high visual fidelity fluid simulations with the inference time to be only 4.24 ms/frame (with 6K fluid particles), hence enables real-time human-computer interaction and animation. Experimental results on multiple datasets show that our work achieves great simulation acceleration with negligible prediction error increase.

Fast Fluid Simulation via Dynamic Multi-Scale Gridding

Food recognition has a wide range of applications, such as health-aware recommendation and self-service restaurants. Most previous methods of food recognition firstly locate informative regions in some weakly-supervised manners and then aggregate their features. However, location errors of informative regions limit the effectiveness of these methods to some extent. Instead of locating multiple regions, we propose a Progressive Self-Distillation (PSD) method, which progressively enhances the ability of network to mine more details for food recognition. The training of PSD simultaneously contains multiple self-distillations, in which a teacher network and a student network share the same embedding network. Since the student network receives a modified image from its teacher network by masking some informative regions, the teacher network outputs stronger semantic representations than the student network. Guided by such teacher network with stronger semantics, the student network is encouraged to mine more useful regions from the modified image by enhancing its own ability. The ability of the teacher network is also enhanced with the shared embedding network. By using progressive training, the teacher network incrementally improves its ability to mine more discriminative regions. In inference phase, only the teacher network is used without the help of the student network. Extensive experiments on three datasets demonstrate the effectiveness of our proposed method and state-of-the-art performance.

Learn More for Food Recognition via Progressive Self-Distillation

Crowd-sourcing has attracted much attention due to its growing importance to society, and numerous studies have been conducted on task allocation and wage determination. Recent works have focused on optimizing task allocation and workers' wages, simultaneously. However, existing methods do not provide good solutions for real-world crowd-sourcing platforms due to the low approximation ratio or myopic problem settings. We tackle an optimization problem for wage determination and online task allocation in crowd-sourcing and propose a fast $1-1/\sqrt{k+3}$-approximation algorithm, where $k$ is the minimum of tasks' budgets (numbers of possible assignments). This approximation ratio is greater than or equal to the existing method. The proposed method reduces the tackled problem to a non-convex multi-period continuous optimization problem by approximating the objective function. Then, the method transforms the reduced problem into a minimum convex cost flow problem, which is a well-known combinatorial optimization problem, and solves it by the capacity scaling algorithm. Synthetic experiments and simulation experiments using real crowd-sourcing data show that the proposed method solves the problem faster and outputs higher objective values than existing methods.

An Improved Approximation Algorithm for Wage Determination and Online Task Allocation in Crowd-sourcing

Recent self-supervised video representation learning methods focus on maximizing the similarity between multiple augmented views from the same video and largely rely on the quality of generated views. However, most existing methods lack a mechanism to prevent representation learning from bias towards static information in the video. In this paper, we propose frequency augmentation (FreqAug), a spatio-temporal data augmentation method in the frequency domain
for video representation learning. FreqAug stochastically removes specific frequency components from the video so that learned representation captures essential features more from the remaining information for various downstream tasks. Specifically, FreqAug pushes the model to focus more on dynamic features rather than static features in the video via dropping spatial or temporal low-frequency components. To verify the generality of the proposed method, we experiment with FreqAug on multiple self-supervised learning frameworks along with standard augmentations. Transferring the improved representation to five video action recognition and two temporal action localization downstream tasks shows consistent improvements over baselines.

Frequency Selective Augmentation for Video Representation Learning

Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. 
Following the human perception process, where the scene is effectively understood by decomposing it into visual (e.g. human, animal) and non-visual components (e.g. action, relations) under the mutual influence of vision and language, we first propose a visual-linguistic (VL) feature. In the proposed VL feature, the scene is modeled by three modalities including (i) a global visual environment; (ii) local visual main agents; (iii) linguistic scene elements. We then introduce an autoregressive Transformer-in-Transformer (TinT) to simultaneously capture the semantic coherence of intra- and inter-event contents within a video. Finally, we present a new VL contrastive loss function to guarantee learnt embedding features are matched with the captions semantics. Comprehensive experiments and extensive ablation studies on ActivityNet Captions and YouCookII datasets show that the proposed Visual-Linguistic Transformer-in-Transform (VLTinT) outperforms prior state-of-the-art methods on accuracy and diversity. Source code is made publicly available at: https://github.com/UARK-AICV/VLTinT

VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning

Safe deployment of deep neural networks in high-stake real-world applications require theoretically sound uncertainty quantification. Conformal prediction (CP) is a principled framework for uncertainty quantification of deep models in the form of prediction set for classification tasks with a user-specified  coverage (i.e., true class label is contained with high probability). This paper proposes a novel algorithm referred to as {\em Neighborhood Conformal Prediction (NCP)} to improve the efficiency of uncertainty quantification from CP for deep classifiers (i.e., reduce prediction set size). The key idea behind NCP is to use the learned representation of the neural network to identify $k$ nearest-neighbor calibration examples for a given testing input and assign them importance weights proportional to their distance to create adaptive prediction sets. We theoretically show that if the learned data representation of the neural network satisfies some mild conditions, NCP will produce smaller prediction sets than traditional CP algorithms. Our comprehensive experiments on CIFAR-10, CIFAR-100, and ImageNet datasets using diverse deep neural networks strongly demonstrate that NCP leads to significant reduction in prediction set size over prior CP methods.

Improving Uncertainty Quantification of Deep Classifiers via Neighborhood Conformal Prediction: Novel Algorithm and Theoretical Analysis

The problem of answering complex First-order Logic queries over incomplete knowledge graphs  is receiving growing attention in the literature. A promising recent approach to this problem has been to exploit neural link predictors, which can be
effective in identifying individual missing triples in the incomplete graph, in order to efficiently answer complex queries. A crucial advantage of this approach over
other methods is that it does not require example answers to complex queries for training, as it relies only on the availability of a trained link  predictor for the knowledge graph at hand.  This approach, however, can be computationally expensive during inference,  and cannot deal with queries involving negation. 

In this paper, we propose a novel approach that addresses all of these limitations.
Experiments on established benchmark datasets demonstrate that our approach offers  superior performance while  significantly reducing inference times.

Efficient Embeddings of Logical Variables for Query Answering over Incomplete Knowledge Graphs

Document-level relation extraction (RE) aims to extract relational triples from a document. One of its primary challenges is to predict implicit relations between entities, which are not explicitly expressed in the document but can usually be extracted through relational reasoning. Previous methods mainly implicitly model relational reasoning through the interaction among entities or entity pairs. However, they suffer from two deficiencies: 1) they often consider only one reasoning pattern, of which coverage on relational triples is limited; 2) they do not explicitly model the process of relational reasoning. In this paper, to deal with the first problem, we propose a document-level RE model with a reasoning module that contains a core unit, the reasoning multi-head self-attention unit. This unit is a variant of the conventional multi-head self-attention and utilizes four attention heads to model four common reasoning patterns, respectively, which can cover more relational triples than previous methods. Then, to address the second issue, we propose a self-distillation training framework, which contains two branches sharing parameters. In the first branch, we first randomly mask some entity pair feature vectors in the document, and then train our reasoning module to infer their relations  by exploiting the feature information of other related entity pairs. By doing so, we can explicitly model the process of relational reasoning. However, because the additional masking operation is not used during testing, it causes an input gap between training and testing scenarios, which would hurt the model performance. To reduce this gap, we perform conventional supervised training without masking operation in the second branch and utilize Kullback-Leibler divergence loss to minimize the difference between the predictions of the two branches. Finally, we conduct comprehensive experiments on three benchmark datasets, of which experimental results demonstrate that our model consistently outperforms all competitive baselines. Our source code is available at https://github.com/DeepLearnXMU/DocRE-SD

Premium content

Accountability Layers

Downloads

Next from AAAI 2023

Augmenting Affective Dependency Graph via Iterative Incongruity Graph Learning for Sarcasm Detection

Similar lecture

Safety Aware Neural Pruning for Deep Reinforcement Learning

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES