United States

Influence diagrams (IDs) are graphical models for representing and reasoning with sequential decision-making problems under uncertainty. Limited memory influence diagrams (LIMIDs) model a decision-maker (DM) who forgets the history in the course of making a sequence of decisions. The standard inference task in IDs and LIMIDs is to compute the maximum expected utility (MEU), which is one of the most challenging tasks in graphical models. We present a model decomposition framework in both IDs and LIMIDs, which we call submodel decomposition that generates a tree of single-stage decision problems through a tree clustering scheme. We also develop a valuation algebra over the submodels that leads to a hierarchical message passing algorithm that propagates conditional expected utility functions over a submodel-tree as external messages. We show that the overall complexity is bounded by the maximum tree-width over the submodels, common in graphical model algorithms. Finally, we present a new method for computing upper bounds over a submodel-tree by first exponentiating the utility functions yielding a standard probabilistic graphical model as an upper bound and then applying standard variational upper bounds for the marginal MAP inference, yielding tighter upper bounds compared with state-of-the-art bounding schemes for the MEU task.

AAAI 2021

Submodel Decomposition Bounds for Influence Diagrams

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

Human understanding of narrative texts requires making commonsense inferences beyond what is stated in the text explicitly. A recent model, COMET, can generate such inferences along several dimensions such as pre- and post-conditions, motivations, and mental states of the participants. However, COMET was trained on short phrases, and is therefore discourse-agnostic. When presented with each sentence of a multi-sentence narrative, it might generate inferences that are inconsistent with the rest of the narrative. 

We present the task of discourse-aware commonsense inference. Given a sentence within a narrative, the goal is to generate commonsense inferences along predefined dimensions, while maintaining coherence with the rest of the narrative. Such large-scale paragraph-level annotation is hard to get and costly, so we use available sentence-level annotations to efficiently and automatically construct a distantly supervised corpus. 

Using this corpus, we train PARA-COMET, a discourse-aware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives. PARA-COMET captures both semantic knowledge pertaining to prior world knowledge, and episodic knowledge involving how current events relate to prior and future events in a narrative. Our results confirm that PARA-COMET outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.

Paragraph-Level Commonsense Transformers with Recurrent Memory

Several behavioral, social, and public health interventions, such as suicide/HIV prevention or community preparedness against natural disasters, leverage social network information to maximize outreach. Algorithmic influence maximization techniques have been proposed to aid with the choice of ``peer leaders'' or ``influencers'' in such interventions. Yet, traditional algorithms for influence maximization have not been designed with these interventions in mind. As a result, they may disproportionately exclude minority communities from the benefits of the intervention. This has motivated research on fair influence maximization. Existing techniques come with two major drawbacks. First, they require committing to a single fairness measure. Second, these measures are typically imposed as strict constraints leading to undesirable properties such as wastage of resources.
To address these shortcomings, we provide a principled characterization of the properties that a fair influence maximization algorithm should satisfy. In particular, we propose a framework based on social welfare theory, wherein the cardinal utilities derived by each community are aggregated using the isoelastic social welfare functions. Under this framework, the trade-off between fairness and efficiency can be controlled by a single inequality aversion design parameter. We then show under what circumstances our proposed principles can be satisfied by a welfare function. The resulting optimization problem is monotone and submodular and can be solved efficiently with optimality guarantees. Our framework encompasses as special cases leximin and proportional fairness. Extensive experiments on synthetic and real world datasets including a case study on landslide risk management demonstrate the efficacy of the proposed framework.

Fair Influence Maximization: a Welfare Optimization Approach

The Uniform Manifold Approximation and Projection (UMAP) algorithm has become widely popular for its ease of use, quality of results, and support for exploratory, unsupervised, supervised, and semi-supervised learning. While many algorithms can be ported to a GPU in a simple and direct fashion, such efforts have resulted in inefficent and inaccurate versions of UMAP. We show a number of techniques that can be used to make a faster and more faithful GPU version of UMAP, and obtain speedups of up to 100x in practice. Many of these design choices/lessons are general purpose and may inform the conversion of other graph and manifold learning algorithms to use GPUs. 
Our implementation has been made publicly available as part of the open source RAPIDS cuML library (https://github.com/rapidsai/cuml).

Bringing UMAP Closer to the Speed of Light with GPU Acceleration

We provide a polynomial-time, scalable algorithm for equilibrium computation in multi-agent influence games on networks, extending work of Bindel, Kleinberg, and Oren (2015) from the single-agent to the multi-agent setting. In games of influence, agents have limited advertising budget to influence the initial predisposition of nodes in some network towards their products, but the eventual decisions of the nodes are determined by the stationary state of DeGroot opinion dynamics on the network, which takes over after the seeding (Ahmadinejad et al. 2014, 2015). In multi-agent systems, how should agents spend their budgets to seed the network to maximize their utility in anticipation of other advertising agents and the network dynamics? We show that Nash equilibria of this game are pure and (under weak assumptions) unique, and can be computed in polynomial time; we test our model by computing equilibria using mirror descent for the two-agent case on random graphs.

Scalable Equilibrium Computation in Multi-Agent Influence Games on Networks

Human judgments of word similarity have been a popular method of evaluating the quality of word embedding. But it fails to measure the geometry properties such as asymmetry. For example, it is more natural to say ``Ellipses are like Circles'' than ``Circles are like Ellipses''. Such asymmetry has been observed from the word evocation experiment, where one word is used to recall another. This association data have been understudied for measuring embedding quality. In this paper, we use three well-known evocation datasets for the purpose and study both static embedding as well as contextual embedding, such as BERT. To fight for the dynamic nature of BERT embedding, we probe BERT's conditional probabilities as a language model, using a large number of Wikipedia contexts to derive a theoretically justifiable Bayesian asymmetry score. The result shows that the asymmetry judgment and similarity judgments disagree, and asymmetry judgment aligns with its strong performance on ``extrinsic evaluations''. This is the first time we can show contextual embeddings's strength on intrinsic evaluation, and the asymmetry judgment provides a new perspective to evaluate contextual embedding and new insights for representation learning.

Circles Are Like Ellipses, or Ellipses Are Like Circles? Measuring the Degree of Asymmetry of Static and Contextual Word Embeddings and the Implications to Representation Learning

Classical game-theoretic approaches for multi-agent systems in both the forward policy design problem and the inverse reward learning problem often make strong rationality assumptions: agents perfectly maximize expected utilities under uncertainties. Such assumptions, however, substantially mismatch with observed human behaviors such as satisficing with sub-optimal, risk-seeking, and loss-aversion decisions. Drawing on iterative reasoning models and cumulative prospect theory, we propose a new game-theoretic framework, bounded risk-sensitive Markov Game (BRSMG), that captures two aspects of realistic human behaviors: bounded intelligence and risk-sensitivity. General solutions to both the forward policy design problem and the inverse reward learning problem are provided with theoretical analysis and simulation verification. We validate the proposed forward policy design algorithm and the inverse reward learning algorithm in a two-player navigation scenario. The results show that agents demonstrate bounded-intelligence, risk-averse and risk-seeking behaviors in our framework. Moreover, in the inverse reward learning task, the proposed bounded risk-sensitive inverse learning algorithm outperforms a baseline risk-neutral inverse learning algorithm by effectively learning not only more accurate reward values but also the intelligence levels and the risk-measure parameters of agents from demonstrations.

Bounded Risk-Sensitive Markov Games: Forward Policy Design and Inverse Reward Learning with Iterative Reasoning and Cumulative Prospect Theory

A fundamental ability of humans is to utilize commonsense knowledge in language understanding and question answering. In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. However, it remains unclear: (1) How far can we get by exploiting external knowledge for CQA? (2) How much potential of knowledge has been exploited in current CQA models? (3) Which are the most promising directions for future CQA? To answer these questions, we benchmark knowledge-enhanced CQA by conducting extensive experiments on multiple standard CQA datasets using a simple and effective knowledge-to-text transformation framework. Experiments show that: (1) Our knowledge-to-text framework is effective and achieves state-of-the-art performance on CommonsenseQA dataset, providing a simple and strong knowledge-enhanced baseline for CQA; (2) The potential of knowledge is still far from being fully exploited in CQA â€” there is a significant performance gap from current models to our models with golden knowledge; and (3) Context-sensitive knowledge selection, heterogeneous knowledge exploitation, and commonsense-rich language models are promising CQA directions.

Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation

We propose a novel task, Multi-Document Driven Dialogue (MD3), in which an agent can guess the target document that the user is interested in by leading a dialogue. To benchmark progress, we introduce a new dataset of GuessMovie, which contains 16,881 documents, each describing a movie, and associated 13,434 dialogues. Further, we propose the MD3 model. Keeping guessing the target document in mind, it converses with the user conditioned on both document engagement and user feedback. In order to incorporate large-scale external documents into the dialogue, it pretrains a document representation which is sensitive to attributes it talks about an object. Then it tracks dialogue state by detecting evolvement of document belief and attribute belief, and finally optimizes dialogue policy in principle of entropy decreasing and reward increasing, which is expected to successfully guess the user's target in a minimum number of turns. Experiments show that our method significantly outperforms several strong baseline methods and is very close to human's performance.

Converse, Focus and Guess - Towards Multi-Document Driven Dialogue

Tree-form sequential decision making (TFSDM) extends classical one-shot decision making by modeling tree-form interactions between an agent and a potentially adversarial environment. It captures the online decision-making problems that each player faces in an extensive-form game, as well as Markov decision processes and partially-observable Markov decision processes where the agent conditions on observed history. Over the past decade, there has been considerable effort into designing online optimization methods for TFSDM. Virtually all of that work has been in the full-feedback setting, where the agent has access to counterfactuals, that is, information on what would have happened had the agent chosen a different action at any decision node. Little is known about the bandit setting, where that assumption is reversed (no counterfactual information is available), despite this latter setting being well understood for almost 20 years in one-shot decision making. In this paper, we give the first algorithm for the bandit linear optimization problem for TFSDM that offers both (i) linear-time iterations (in the size of the decision tree) and (ii) O(sqrt(T)) cumulative regret in expectation compared to any fixed strategy, at all times T. This is made possible by new results that we derive, which may have independent uses as well: 1) geometry of the dilated entropy regularizer, 2) autocorrelation matrix of the natural sampling scheme for sequence-form strategies, 3) construction of an unbiased estimator for linear losses for sequence-form strategies, and 4) a refined regret analysis for mirror descent when using the dilated entropy regularizer.

Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games

Sequence classification is the task of predicting a class label given a sequence of observations.  In many applications such as healthcare monitoring or intrusion detection, early classification is crucial to prompt intervention. In this work, we learn sequence classifiers that favour early classification from an evolving observation trace. While many state-of-the-art sequence classifiers are neural networks, and in particular LSTMs, our classifiers take the form of finite state automata and are learned via discrete optimization. Our automata-based classifiers are interpretable---supporting explanation, counterfactual reasoning, and human-in-the-loop modification---and have strong empirical performance. Experiments over a suite of goal recognition and behaviour classification datasets show our learned automata-based classifiers to have comparable test performance to LSTM-based classifiers, with the added advantage of 
being interpretable.

Downloads

Next from AAAI 2021

Paragraph-Level Commonsense Transformers with Recurrent Memory

Similar lecture

A New Bounding Scheme for Influence Diagrams

.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

Paragraph-Level Commonsense Transformers with Recurrent Memory

Similar lecture

A New Bounding Scheme for Influence Diagrams

Downloads