United States

Generalized planning is concerned with the computation of general policies that solve multiple instances of a planning domain all at once. It has been recently shown that these policies can be computed in two steps: first, a suitable abstraction in the form of a qualitative numerical planning problem (QNP) is learned from sample plans, then the general policies are obtained from the learned QNP using a planner. In this work, we introduce an alternative approach for computing more expressive general policies which does not require sample plans or a QNP planner. The new formulation is very simple and can be cast in terms that are more standard in machine learning: a large but finite pool of features is defined from the predicates in the planning examples using a general grammar, and a small subset of features is sought for separating â€œgoodâ€ from â€œbadâ€ state transitions, and goals from non-goals. The problems of finding such a â€œseparating surfaceâ€ while labeling the transitions as â€œgoodâ€ or â€œbadâ€ are jointly addressed as a single combinatorial optimization problem expressed as a Weighted Max-SAT problem. The advantage of looking for the simplest policy in the given feature space that solves the given examples, possibly non-optimally, is that many domains have no general, compact policies that are optimal. The approach yields general policies for a number of benchmark domains.

AAAI 2021

Learning General Planning Policies from Small Examples without Supervision

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

Many practical applications require the solution of numerically challenging linear programs (LPs) and mixed integer programs (MIPs).
Scaling is a widely used preconditioning technique that aims at reducing the error propagation of the involved linear systems,
thereby improving the numerical behavior of the dual simplex algorithm and, consequently, LP-based branch-and-bound.
A reliable scaling method often makes the difference whether these problems can be solved correctly or not.
In this paper, we investigate the use of machine learning to choose at the beginning of the solution process
between two common scaling methods: Standard scaling and Curtis-Reid scaling.
The latter often, but not always, leads to a more robust solution process, but may suffer from longer solution times.

Rather than training for overall solution time, we propose to use the attention level of a MIP solution process as a learning label.
We evaluate the predictive power of a random forest approach and a linear regressor that learns the (square-root of the) difference in attention level.
It turns out that the resulting classification not only reduces various types of numerical errors by large margins, but it also improves the performance of the dual simplex algorithm.

The learned model has been implemented within the FICO Xpress MIP solver and it is used by default since release 8.9, May 2020, to determine the scaling algorithm Xpress applies before solving an LP or a MIP.

Learning to Scale Mixed-Integer Programs

Although static networks have been extensively studied in machine learning, data mining, and AI communities for many decades, the study of dynamic networks has recently taken center stage due to the prominence of social media and its effects on the dynamics of social networks. In this paper, we propose a statistical model for dynamically evolving networks, together with a variational inference approach. Our model, Neural Latent Space Model with Variational Inference, encodes edge dependencies across different time snapshots. It represents nodes via latent vectors and uses interaction matrices to model the presence of edges. These matrices can be used to incorporate multiple relations in heterogeneous networks by having a separate matrix for each of the relations. To capture the temporal dynamics, both node vectors and interaction matrices are allowed to evolve with time. Existing network analysis methods use representation learning techniques for modelling networks. These techniques are different for homogeneous and heterogeneous networks because heterogeneous networks can have multiple types of edges and nodes as opposed to a homogeneous network. Unlike these, we propose a unified model for homogeneous and heterogeneous networks in a variational inference framework. Moreover, the learned node latent vectors and interaction matrices may be interpretable and therefore provide insights on the mechanisms behind network evolution. We experimented with a single step and multi-step link forecasting on real-world networks of homogeneous, bipartite, and heterogeneous nature, and demonstrated that our model significantly outperforms existing models.

Neural Latent Space Model for Dynamic Networks and Temporal Knowledge Graphs

Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works have either required exact gradients or state-action visitation measure based mini-batch stochastic gradients with a diverging batch size, which limit their applicability in practical scenarios. In this paper, we consider classical policy gradient methods that compute an approximate gradient with a single trajectory or a fixed size mini-batch of trajectories under soft-max parametrization and log-barrier regularization, along with the widely-used REINFORCE gradient estimation procedure. By controlling the number of "bad" episodes and resorting to the classical doubling trick, we establish an anytime sub-linear high probability regret bound as well as almost sure global convergence of the average regret with an asymptotically sub-linear rate. These provide the first set of global convergence and sample efficiency results for the well-known REINFORCE algorithm and contribute to a better understanding of its performance in practice.

Sample Efficient Reinforcement Learning with REINFORCE

In machine learning, training data often capture the behaviour of multiple subgroups of some underlying human population.
When the amounts of training data for the subgroups are not controlled carefully, under-representation bias arises.
We introduce two natural notions of subgroup fairness and instantaneous fairness to address such under-representation bias in time-series forecasting problems.
In particular, we consider the subgroup-fair and instant-fair learning of a linear dynamical system (LDS) from multiple trajectories of varying lengths and the associated forecasting problems.
We provide globally convergent methods for the learning problems using hierarchies of convexifications of non-commutative polynomial optimisation problems. 
Our empirical results on a biased data set motivated by insurance applications and the well-known COMPAS data set demonstrate both the beneficial impact of fairness considerations on statistical performance and the encouraging effects of exploiting sparsity on run time.

Fairness in Forecasting and Learning Linear Dynamical Systems

Aspect-based sentiment analysis (ABSA) and Targeted ASBA (TABSA) allow finer-grained inferences about sentiment to be drawn from the same text, depending on context. For example, a given text can have different targets (e.g., neighborhoods) and different aspects (e.g., price or safety), with different sentiment associated with each target-aspect pair. In this paper, we investigate whether adding context to self-attention models improves performance on (T)ABSA. We propose two variants of Context-Guided BERT (CG-BERT) that learn to distribute attention under different contexts. We first adapt a context-aware Transformer to produce a CG-BERT that uses context-guided softmax-attention. Next, we propose an improved Quasi-Attention CG-BERT model that learns a compositional attention that supports subtractive attention. We train both models with pretrained BERT on two (T)ABSA datasets: SentiHood and SemEval-2014 (Task 4). Both models achieve new state-of-the-art results with our QACG-BERT model having the best performance. Furthermore, we provide analyses of the impact of context in the our proposed models. Our work provides more evidence for the utility of adding context-dependencies to pretrained self-attention-based language models for context-based natural language tasks.

Context-Guided BERT for Targeted Aspect-Based Sentiment Analysis

Given an unsatisfiable set of constraints F, a maximal satisfiable subset (MSS) is a maximal subset of constraints C âŠ† F such that C is satisfiable. Over the past two decades, the steady improvement in runtime performance of algorithms for finding MSS has led to an increased adoption of MSS-based techniques in wide variety of domains. Motivated by the progress in finding an MSS, the past decade has witnessed a surge of interest in design of algorithmic techniques to enumerate all the MSSes, which has subsequently led to discovery of new applications utilizing enumeration of MSSes.
The development of techniques for finding and enumeration of MSSes mirrors a similar phenomenon of finding and enumeration of SAT solutions in the early 2000s, which subsequently motivated design of algorithmic techniques for model counting. In a similar spirit, we undertake study to investigate the feasibility of MSS counting techniques. In particular, the focus point of our investigation is to answer whether one can design efficient MSS counting techniques that do not rely on explicit MSS enumeration. The primary contribution of this work is an affirmative answer to the above question. Our tool, CountMSS, uses a novel architecture of a wrapper W and a remainder R such that the desired MSS count can be expressed as |W| âˆ’ |R|. CountMSS relies on the advances in projected model counting to efficiently compute |W| and |R|. Our empirical evaluation demonstrates that CountMSS is able to scale to instances clearly beyond the reach of enumeration-based techniques.

Counting Maximal Satisfiable Subsets

We investigate the problem of bounding causal effects from experimental studies in which treatment assignment is randomized but the subject compliance is imperfect. It is well known that under such conditions, the actual causal effects are not point-identifiable due to uncontrollable unobserved confounding. In their seminal work, Balke and Pearl (1994) derived the tightest bounds over the causal effects in this settings by employing an algebra program to derive analytic expressions. However, Pearl's approach assumes the primary outcome to be discrete and finite. Solving such a program could be intractable when high-dimensional context variables are present. In this paper, we present novel non-parametric methods to bound causal effects on the continuous outcome from studies with imperfect compliance. These bounds could be generalized to settings with a high-dimensional context.

Bounding Causal Effects on Continuous Outcome

Human-robot shared autonomy techniques for vehicle navigation hold promise for reducing a human driverâ€™s workload, ensuring safety, and improving navigation efficiency. However, because typical techniques achieve these improvements by effectively removing human control at critical moments, these approaches often exhibit poor responsiveness to human commandsâ€”especially in cluttered environments. In this paper, we propose a novel goal-blending shared autonomy (GBSA) system, which aims to improve responsiveness in shared autonomy systems by blending human and robot input during the selection of local navigation goals as opposed to low-level motor (servo-level) commands. We validate the proposed approach by performing a human study involving an intelligent wheelchair and compare GBSA to a representative servo-level shared control system that uses a policy-blending approach. The results of both quantitative performance analysis and a subjective survey show that GBSA exhibits significantly better system responsiveness and induces higher user satisfaction than the existing approach.

Goal Blending for Responsive Shared Autonomy in a Navigating Vehicle

Learning invariant representations is a critical first step in a number of machine learning tasks. A common approach is given by the so-called information bottleneck principle in which an application dependent function of mutual information is carefully chosen and optimized. Unfortunately, in practice, these functions are not suitable for optimization purposes since these losses are agnostic of the metric structure of the parameters of the model. In our paper, we introduce a class of losses for learning representations that are invariant to some extraneous variable of interest by inverting the class of contrastive losses, i.e., inverse contrastive loss (ICL). We show that if the extraneous variable is binary, then optimizing ICL is equivalent to optimizing a regularized MMD divergence. More generally, we also show that if we are provided a metric on the sample space, our formulation of ICL can be decomposed into a sum of convex functions of the given distance metric. Our experimental results indicate that models obtained by optimizing ICL achieve significantly better invariance to the extraneous variable for a fixed desired level of accuracy. In a variety of experimental settings, we show applicability of ICL for learning invariant representations for both continuous and discrete protected/extraneous variables. The project page with code is available at https://github.com/adityakumarakash/ICL

Learning Invariant Representations Using Inverse Contrastive Loss

Real-life applications, heavily relying on machine learning, such as dialog systems, demand for out-of-domain detection methods. Intent classification models should be equipped with a mechanism to distinguish seen intents from unseen ones so that the dialog agent is capable of rejecting the latter and avoiding undesired behavior. However, despite increasing attention paid to the task, the best practices for out-of-domain intent detection have not yet been fully established. 

This paper conducts a thorough comparison of out-of-domain intent detection methods. We prioritize the methods, not requiring access to out-of-domain data during training, gathering of which is extremely time- and labor-consuming due to lexical and stylistic variation of user utterances. We evaluate multiple contextual encoders and methods, proven to be efficient, on three common datasets for intent classification, expanded with out-of-domain utterances. Our main findings show that fine-tuning Transformer-based encoders on in-domain data leads to superior results. Mahalanobis distance, together with utterance representations, derived from Transformer-based encoders, outperform other methods by a wide margin(1-5% in
terms of AUROC) and establish new state-of-the-art results for all datasets. 

The broader analysis shows that the reason for success lies in the fact that the fine-tuned Transformer is capable of constructing homogeneous representations of in-domain utterances, revealing geometrical disparity to out of domain utterances. In turn, the Mahalanobis distance captures this disparity easily.

Downloads

Next from AAAI 2021

Learning to Scale Mixed-Integer Programs

Similar lecture

General Policies, Representations, and Planning Width

.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 Scale Mixed-Integer Programs

Similar lecture

General Policies, Representations, and Planning Width

Downloads