United States

We study bandits with graph-structured feedback, where a learner repeatedly selects an arm and then observes rewards of the chosen arm as well as its neighbors in the feedback graph. Existing work on graphical bandits assumes either stochastic rewards or adversarial rewards, both of which are extremes and appear rarely in real-world scenarios. In this paper, we study graphical bandits with a reward model that interpolates between the two extremes, where the rewards are overall stochastically generated but a small fraction of them can be adversarially corrupted. For this problem, we propose an online algorithm that can utilize the stochastic pattern and also tolerate the adversarial corruptions. The main idea is to restrict exploration to carefully-designed independent sets of the feedback graph and perform exploitation by adopting a soft version of arm elimination. Theoretical analysis shows that our algorithm attains an $O(\alpha \ln{K} \ln{T} + \alpha C)$ regret, where $\alpha$ is the independence number of the feedback graph, $K$ is the number of arms, $T$ is the time horizon, and $C$ quantifies the total corruptions introduced by the adversary. The effectiveness of our algorithm is demonstrated by numerical experiments.

AAAI 2021

Stochastic Graphical Bandits with Adversarial Corruptions

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

technical paper

Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious for training the action-value and policy functions. To alleviate such problem, this paper proposes to adaptively reweight the imaginary transitions, so as to reduce the negative effects of poorly generated trajectories. More specifically, we evaluate the effect of an imaginary transition by calculating the change of the loss computed on the real samples when we use the transition to train the action-value and policy functions. Based on this evaluation criterion, we construct the idea of reweighting each imaginary transition by a well-designed meta-gradient algorithm. Extensive experimental results demonstrate that our method outperforms state-of-the-art model-based and model-free RL algorithms on multiple tasks. Visualization of our changing weights further validates the necessity of utilizing reweight scheme.

Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning

Abstract argumentation constitutes both a major research strand and a key approach that provides the core reasoning engine for a multitude of formalisms in computational argumentation in AI. Reasoning in abstract argumentation is carried out by viewing arguments and their relationships as abstract entities, with argumentation frameworks (AFs) being the most commonly used abstract formalism. Argumentation semantics then drive the reasoning by specifying formal criteria on which sets of arguments, called extensions, can be deemed as jointly acceptable. Such extensions provide a basic way of explaining argumentative acceptance. Inspired by recent research, we present a more general class of explanations: in this paper we propose and study so-called strong explanations for explaining argumentative acceptance in AFs. A strong explanation is a set of arguments such that a target set of arguments is acceptable in each subframework containing the explaining set. We formally show that strong explanations form a larger class than extensions, in particular giving the possibility of having smaller explanations. Moreover, assuming basic properties, we show that any explanation strategy, broadly construed, is a strong explanation. We show that the increase in variety of strong explanations comes with a computational trade-off: we provide an in-depth analysis of the associated complexity, showing a jump in the polynomial hierarchy compared to extensions.

Strong Explanations in Abstract Argumentation

Human video motion transfer (HVMT) aims to synthesize videos that one person imitates other persons' actions. Although existing GAN-based HVMT methods have achieved great success, they either fail to preserve appearance details due to the loss of spatial consistency between synthesized and exemplary images, or generate incoherent video results due to the lack of temporal consistency among video frames. In this paper, we propose Coarse-to-Fine Flow Warping Network (C2F-FWN) for spatial-temporal consistent HVMT. Particularly, C2F-FWN utilizes coarse-to-fine flow warping and Layout-Constrained Deformable Convolution (LC-DConv) to improve spatial consistency, and employs Flow Temporal Consistency (FTC) Loss to enhance temporal consistency. In addition, provided with multi-source appearance inputs, C2F-FWN can support appearance attribute editing with great flexibility and efficiency. Besides public datasets, we also collected a large-scale HVMT dataset named SoloDance for evaluation. Extensive experiments conducted on our SoloDance dataset and the iPER dataset show that our approach outperforms state-of-art HVMT methods in terms of both spatial and temporal consistency. Source code and the SoloDance dataset are available at https://github.com/wswdx/C2F-FWN.

C2F-FWN: Coarse-to-Fine Flow Warping Network for Spatial-Temporal Consistent Motion Transfer

Word-character lattice models have been proved to be effective for Chinese named entity recognition (NER), in which word boundary information is fused into character sequences for enhancing character representations. However, prior approaches have only used simple methods such as feature concatenation or position encoding to integrate word-character lattice information, but fail to capture fine-grained correlations in word-character spaces. In this paper, we propose DCSAN, a Dynamic Cross- and Self-lattice Attention Network that aims to model dense interactions over word-character lattice structure for Chinese NER. By carefully combining cross-lattice and self-lattice attention modules with gated word-character semantic fusion unit, the network can explicitly capture fine-grained correlations across different spaces (e.g., word-to-character and character-to-character), thus significantly improving model performance. Experiments on four Chinese NER datasets show that DCSAN obtains stateof-the-art results as well as efficiency compared to several competitive approaches.

Dynamic Modeling Cross- and Self-Lattice Attention Network for Chinese NER

In this paper we tackle the problem of pose guided person image generation, which aims to transfer a person image from the source pose to a novel target pose while maintaining the source appearance. Given the inefficiency of standard CNNs in handling large spatial transformation, we propose a structure-aware flow based method for high-quality person image generation. Specifically, instead of learning the complex overall pose changes of human body, we decompose the human body into different semantic parts (e.g., head, torso, and legs) and apply different networks to predict the flow fields for these parts separately. Moreover, we carefully design the network modules to effectively capture the local and global semantic correlations of features within and among the human parts respectively. Extensive experimental results show that our method can generate high-quality results under large pose discrepancy and outperforms state-of-the-art methods in both qualitative and quantitative comparisons.

Structure-Aware Person Image Generation with Pose Decomposition and Semantic Correlation

We propose a  model of winners allocation. In this model, we are given are two elections where the sets of candidates may intersect. The goal is to find two disjoint winning committees from respectively the two elections that are subjected to certain reasonable restrictions. For our model, we first propose several desirable properties. Then, we investigate the implication relationships among these properties. Finally, we study the complexity of computing winners allocations providing these properties. For hardness results, we also study some fixed-parameter algorithms.

A Model of Winners Allocation

We study the problem of inferring causal graphs from observational data. We are particularly interested in discovering graphs where all edges are oriented, as opposed to the partially directed graph that the state of the art discover. To this end, we base our approach on the algorithmic Markov condition. Unlike the statistical Markov condition, it uniquely identifies the true causal network as the one that provides the simplestâ€” as measured in Kolmogorov complexityâ€”factorization of the joint distribution. Although Kolmogorov complexity is not computable, we can approximate it from above via the Minimum Description Length principle, which allows us to define a consistent and computable score based on non-parametric multivariate regression. To efficiently discover causal networks in practice, we introduce the GLOBE algorithm, which greedily adds, removes, and orients edges such that it minimizes the overall cost. Through an extensive set of experiments, we show GLOBE performs very well in practice, beating the state of the art by a margin.

Discovering Fully Oriented Causal Networks

The end-to-end Human Mesh Recovery (HMR) approach has been successfully used for 3D body reconstruction. However, most HMR-based frameworks reconstruct human body by directly learning mesh parameters from images or videos, while lacking explicit guidance of 3D human pose in visual data. As a result, the generated mesh often exhibits incorrect pose for complex activities. To tackle this problem, we propose to exploit 3D pose to calibrate human mesh. Specifically, we develop two novel Pose Calibration frameworks, i.e., Serial PC-HMR and Parallel PC-HMR. By coupling advanced 3D pose estimators and HMR in a serial or parallel manner, these two frameworks can effectively correct human mesh with guidance of a concise pose calibration module. Furthermore, since the calibration module is designed via non-rigid pose transformation, our PC-HMR frameworks can flexibly tackle bone length variations to alleviate misplacement in the calibrated mesh. Finally, our frameworks are based on generic and complementary integration of data-driven learning and geometrical modeling. Via plug-and-play modules, they can be efficiently adapted for both image/video-based human mesh recovery. Additionally, they have no requirement of extra 3D pose annotations in the testing phase, which releases inference difficulties in practice. We perform extensive experiments on the popular benchmarks, i.e., Human3.6M, 3DPW and SURREAL, where our PC-HMR frameworks achieve the SOTA results.

PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos

Lane detection is one of the most important tasks in self-driving. Due to various complex scenarios (e.g., severe occlusion, ambiguous lanes, etc.) and the sparse supervisory signals inherent in lane annotations, lane detection task is still challenging. Thus, it is difficult for the ordinary convolutional neural network (CNN) to train in general scenes to catch subtle lane feature from the raw image. In this paper, we present a novel module named REcurrent Feature-Shift Aggregator (RESA) to enrich lane feature after preliminary feature extraction with an ordinary CNN. RESA takes advantage of strong shape priors of lanes and captures spatial relationships of pixels across rows and columns. It shifts sliced feature map recurrently in vertical and horizontal directions and enables each pixel to gather global information. RESA can conjecture lanes accurately in challenging scenarios with weak appearance clues by aggregating sliced feature map. Moreover, we propose a Bilateral Up-Sampling Decoder that combines coarse-grained and fine-detailed features in the up-sampling stage. It can recover the low-resolution feature map into pixel-wise prediction meticulously. Our method achieves state-of-the-art results on two popular lane detection benchmarks (CULane and Tusimple). Code has been made available at: https://github.com/ZJULearning/resa.

RESA: Recurrent Feature-Shift Aggregator for Lane Detection

Teaching humans is an important topic under the umbrella of machine teaching, and its core problem is to design an algorithm for selecting teaching examples. Existing work typically regards humans as passive learners, where an ordered set of teaching examples are generated and fed to learners sequentially. However, such a mechanism is inconsistent with the behavior of human learners in practice. A real human learner can actively choose whether to review a historical example or to receive a new example depending on the belief of her learning states. In this work, 
 we propose a model of active learners and design an efficient teaching algorithm accordingly. Experimental results with both simulated learners and real crowdsourcing workers demonstrate that our teaching algorithm has better teaching performance compared to existing methods.

Downloads

Next from AAAI 2021

Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning

Similar lecture

Stochastic Bandits with Graph Feedback in Non-Stationary Environments

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learning

Similar lecture

Stochastic Bandits with Graph Feedback in Non-Stationary Environments

Downloads