United States

The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an efficient algorithm to mitigate this bias. However, this comes at the price of an underestimation of action values, in addition to increased memory requirements and a slower convergence.
In this paper, we introduce a new way to address the maximization bias in the form of a &quot;self-correcting algorithm&quot; for approximating the maximum of an expected value. Our method balances the overestimation of the single estimator used in conventional Q-learning and the underestimation of the double estimator used in Double Q-learning. Applying this strategy to Q-learning results in Self-correcting Q-learning. We show theoretically that this new algorithm enjoys the same convergence guarantees as Q-learning while being more accurate. Empirically, it performs better than Double Q-learning in domains with rewards of high variance, and it even attains faster convergence than Q-learning in domains with rewards of zero or low variance. These advantages transfer to a Deep Q Network implementation that we call Self-correcting DQN and which outperforms regular DQN and Double DQN on several tasks in the Atari 2600 domain.

AAAI 2021

Self-Correcting Q-Learning

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. 

The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an efficient algorithm to mitigate this bias. However, this comes at the price of an underestimation of action values, in addition to increased memory requirements and a slower convergence.
In this paper, we introduce a new way to address the maximization bias in the form of a "self-correcting algorithm" for approximating the maximum of an expected value. Our method balances the overestimation of the single estimator used in conventional Q-learning and the underestimation of the double estimator used in Double Q-learning. Applying this strategy to Q-learning results in Self-correcting Q-learning. We show theoretically that this new algorithm enjoys the same convergence guarantees as Q-learning while being more accurate. Empirically, it performs better than Double Q-learning in domains with rewards of high variance, and it even attains faster convergence than Q-learning in domains with rewards of zero or low variance. These advantages transfer to a Deep Q Network implementation that we call Self-correcting DQN and which outperforms regular DQN and Double DQN on several tasks in the Atari 2600 domain.

technical paper

In inference, open-set classification is to either classify a sample into a known class from training or reject it as an unknown class. Existing deep open-set classifiers train explicit closed-set classifiers, in some cases disjointly utilizing reconstruction, which we find dilutes the latent representation's ability to distinguish unknown classes. In contrast, we train our model to cooperatively learn reconstruction and perform class-based clustering in the latent space. With this, our Gaussian mixture variational autoencoder (GMVAE) achieves more accurate and robust open-set classification results, with an average F1 increase of 0.26, through extensive experiments aided by analytical results.

Open-Set Recognition with Gaussian Mixture Variational Autoencoders

Numerous new dialog domains are being created every day while collecting data for these domains is extremely costly since it involves human interactions. Therefore, it is essential to develop algorithms that can adapt to different domains efficiently when building data-driven dialog models. Most recent research on domain adaption focuses on giving the model a better initialization, rather than optimizing the adaptation process. We propose an efficient domain adaptive task-oriented dialog system model, which incorporates a meta-teacher model to emphasize the different impacts between generated tokens with respect to the context. We first train our base dialog model and meta-teacher model adversarially in a meta-learning setting on rich-resource domains. The meta-teacher learns to quantify the importance of tokens under different contexts across different domains. During adaptation, the meta-teacher guides the dialog model to focus on important tokens in order to achieve better adaptation efficiency. We evaluate our model on two multi-domain datasets, MultiWOZ and Google Schema-Guided Dialogue, and achieve state-of-the-art performance.

A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting

It is common practice to constrain the output space of a neural network with the final layer to a problem-specific value range. However, for many tasks it is desired to restrict the output space for each input independently to a different subdomain with a non-trivial geometry, e.g. in safety-critical applications, to exclude hazardous outputs sample-wise. We propose ConstraintNetâ€”a scalable neural network architecture which constrains the output space in each forward pass independently. Contrary to prior approaches, which perform a projection in the final layer, ConstraintNet applies an input-dependent parametrization of the constrained output space. Thereby, the complete interior of the constrained region is covered and computational costs are reduced significantly. For constraints in form of convex polytopes, we leverage the vertex representation to specify the parametrization. The second modification consists of adding an auxiliary input in form of a tensor description of the constraint to enable the handling of multiple constraints for the same sample. Finally, ConstraintNet is end-to-end trainable with almost no overhead in the forward and backward pass. We demonstrate ConstraintNet on two regression tasks: First, we modify a CNN and construct several constraints for facial landmark detection tasks. Second, we demonstrate the application to a follow object controller for vehicles and accomplish safe reinforcement learning in this case. In both experiments, ConstraintNet improves performance and we conclude that our approach is promising for applying neural networks in safety-critical environments.

Sample-Specific Output Constraints for Neural Networks

Many decision making systems require users to indicate their preferences via a ranking. It is common to elicit such rankings through pairwise comparison queries. By using sorting algorithms, this can be achieved by asking at most O(m log m) adaptive comparison queries. However, in many cases we have some advance (probabilistic) information about the user's preferences, for instance if we have a learnt model of the user's preferences or if we expect the user's preferences to be correlated with those of previous users. For these cases, we design elicitation algorithms that ask fewer questions in expectation, by building on results for average-case sorting. If the user's preferences are drawn from a Mallows phi model, O(m) queries are enough; for a mixture of k Mallows models, log k + O(m) queries are enough; for Plackett-Luce models, the answer varies with the alternative weights. Our results match information-theoretic lower bounds. We also provide empirical evidence for the benefits of our approach.

Preference Elicitation as Average-Case Sorting

Machine Learning has seen tremendous growth recently, which has led to a larger adaptation of ML systems for educational assessments, credit risk, healthcare, employment, criminal justice, to name a few. The trustworthiness of ML and NLP systems is a crucial aspect and requires a guarantee that the decisions they make are fair and robust. Aligned with this, we propose a novel framework GYC, to generate a set of exhaustive counterfactual text, which are crucial for testing these ML systems. Our main contributions include a) We introduce GYC, a framework to generate counterfactual samples such that the generation is plausible, diverse, goal-oriented, and effective, b) We generate counterfactual samples, that can direct the generation towards a corresponding \texttt{condition} such as named-entity tag, semantic role label, or sentiment. Our experimental results on various domains show that GYC generates counterfactual text samples exhibiting the above four properties. GYC generates counterfactuals that can act as test cases to evaluate a model and any text debiasing algorithm.

Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Text

Algorithms for exchange of kidneys is one of the key successful applications in market design, artificial intelligence, and operations research. Potent immunosuppressant drugs suppress the body's ability to reject a transplanted organ up to the point that a transplant across blood- or tissue-type incompatibility becomes possible. In contrast to the standard  kidney exchange problem, we consider a setting that also involves the decision about which recipients receive from the limited supply of immunosuppressants that make them compatible with originally incompatible kidneys. We firstly present a general computational framework to model this problem. Our main contribution is a range of efficient algorithms that provide flexibility in terms of meeting meaningful objectives. Motivated by the current reality of kidney exchanges using sophisticated mathematical-programming-based clearing algorithms, we then present a general but scalable approach to optimal clearing with immunosuppression; we validate our approach on realistic data from a large fielded exchange.

Optimal Kidney Exchange with Immunosuppressants

This paper explores a new online learning problem where the input sequence lives in an over-time varying feature space and the ground-truth label of any input point is given only occasionally, making online learners less restrictive and more applicable. The crux in this setting lies in how to exploit the very limited labels to efficiently update the online learners. Plausible ideas such as propagating labels from labeled points to their neighbors through uncovering the point-wise geometric relations face two challenges: (1) distance measurement fails to work as different points may be described by disparate sets of features and (2) storing the geometric shape, which is formed by all arrived points, is unrealistic in an online setting. To address these challenges, we first construct a universal feature space that accumulates all observed features, making distance measurement feasible. Then, we use manifolds to represent the geometric shapes and approximate them in a sparse means, making manifolds computational and memory tractable in online learning. We frame these two building blocks into a regularized risk minimization algorithm. Theoretical analysis and empirical evidence substantiate the viability and effectiveness of our proposal.

Online Learning in Variable Feature Spaces under Incomplete Supervision

Despite the importance and abundance of temporal knowledge graphs, most of the current research has been focused on reasoning on static graphs. In this paper, we study the challenging problem of inference over temporal knowledge graphs. In particular, the task of temporal link prediction. In general, this is a difficult task due to data non-stationarity, data heterogeneity, and its complex temporal dependencies. 
We propose Chronological Rotation embedding (ChronoR), a novel model for learning representations for entities, relations, and time. Learning dense representations is frequently used as an efficient and versatile method to perform reasoning on knowledge graphs. The proposed model learns a k-dimensional rotation transformation parametrized by relation and time, such that after each fact's head entity is transformed using the rotation, it falls near its corresponding tail entity. By using high dimensional rotation as its transformation operator, ChronoR captures rich interaction between the temporal and multi-relational characteristics of a Temporal Knowledge Graph. Experimentally, we show that ChronoR is able to outperform many of the state-of-the-art methods on the benchmark datasets for temporal knowledge graph link prediction.

ChronoR: Rotation Based Temporal Knowledge Graph Embedding

Person search aims to localize and identify a specific person from a gallery of images. Recent methods can be categorized into two groups, i.e., two-step and end-to-end approaches. The former views person search as two independent tasks and achieves dominant results using separately trained person detection and re-identification (Re-ID) models. The latter performs person search in an end-to-end fashion. Although the end-to-end approaches yield higher inference efficiency, they largely lag behind those two-step counterparts in terms of accuracy. In this paper, we argue that the gap between the two kinds of methods is mainly caused by the Re-ID sub-networks of end-to-end methods. To this end, we propose a simple yet strong end-to-end network with diverse knowledge distillation to break the bottleneck. We also design a spatial-invariant augmentation to assist model to be invariant to inaccurate detection results. Experimental results on the CUHK-SYSU and PRW datasets demonstrate the superiority of our method against existing approaches -- it achieves on par accuracy with state-of-the-art two-step methods while maintaining high efficiency due to the single joint model. Code is available at: https://git.io/DKD-PersonSearch.

Diverse Knowledge Distillation for End-to-End Person Search

Existing tensor factorization methods assume that the input tensor follows some specific distribution (i.e. Poisson, Bernoulli, and Gaussian), and solve the factorization by minimizing some empirical loss functions defined based on the corresponding distribution. However, it suffers from several drawbacks: 1) In reality, the underlying distributions are complicated and unknown, making it infeasible to be approximated by a simple distribution. 2) The correlation across dimensions of the input tensor is not well utilized, leading to sub-optimal performance. Although heuristics were proposed to incorporate such correlation as side information under Gaussian distribution, they can not easily be generalized to other distributions. Thus, a more principled way of utilizing the correlation in tensor factorization models is still an open challenge. Without assuming any explicit distribution, we formulate the tensor factorization as an optimal transport problem with Wasserstein distance, which can handle non-negative inputs. 
 
We introduce SWIFT, which minimizes the Wasserstein distance that measures the distance between the input tensor and that of the reconstruction. In particular, we define the N-th order tensor Wasserstein loss for the widely used tensor CP factorization and derive the optimization algorithm that minimizes it. By leveraging sparsity structure and different equivalent formulations for optimizing computational efficiency, SWIFT is as scalable as other well-known CP algorithms. Using the factor matrices as features, SWIFT achieves up to 9.65% and 11.31% relative improvement over baselines for downstream prediction tasks. Under the noisy conditions, SWIFT achieves up to 15% and 17% relative improvements over the best competitors for the prediction tasks.

Downloads

Next from AAAI 2021

Open-Set Recognition with Gaussian Mixture Variational Autoencoders

Similar lecture

Action Candidate Based Clipped Double Q-Learning for Discrete and Continuous Action Tasks

.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

Open-Set Recognition with Gaussian Mixture Variational Autoencoders

Similar lecture

Action Candidate Based Clipped Double Q-Learning for Discrete and Continuous Action Tasks

Downloads