United States

Policy Optimization (PO) is a widely used approach to address continuous control tasks. In this paper, we introduce the notion of mediator feedback that frames PO as an online learning problem over the policy space. The additional available information, compared to the standard bandit feedback, allows reusing samples generated by one policy to estimate the performance of other policies. Based on this observation, we propose an algorithm, RANDomized-exploration policy Optimization via Multiple Importance Sampling with Truncation (RANDOMIST), for regret minimization in PO, that employs a randomized exploration strategy, differently from the existing optimistic approaches. When the policy space is finite, we show that under certain circumstances, it is possible to achieve constant regret, while always enjoying logarithmic regret. We also derive problem-dependent regret lower bounds. Then, we extend RANDOMIST to compact policy spaces. Finally, we provide numerical simulations on finite and compact policy spaces, in comparison with PO and bandit baselines.

AAAI 2021

Policy Optimization as Online Learning with Mediator Feedback

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. 

AAAI 2022

technical paper

We study the problem of adversarial language games, in which multiple agents with conflicting goals compete with each other via natural language interactions. While adversarial language games are ubiquitous in human activities, little attention has been devoted to this field in natural language processing. In this work, we propose a challenging adversarial language game called Adversarial Taboo as an example, in which an attacker and a defender compete around a target word. The attacker is tasked with inducing the defender to utter the target word invisible to the defender, while the defender is tasked with detecting the target word before being induced by the attacker. In Adversarial Taboo, a successful attacker and defender need to hide or infer the intention, and induce or defend during conversations. This requires several advanced language abilities, such as adversarial pragmatic reasoning and goal-oriented language interactions in open domain, which will facilitate many downstream NLP tasks. To instantiate the game, we create a game environment and a competition platform. Comprehensive experiments on several baseline attack and defense strategies show promising and interesting results, based on which we discuss some directions for future research.

Adversarial Language Games for Advanced Natural Language Intelligence

We consider a natural setting where network parameters are estimated from noisy and incomplete information about the network. More specifically, we investigate how we can efficiently estimate the number of small subgraphs (e.g., edges, triangles, etc.) based on full access to one or two noisy and incomplete samples of a large underlying network and on few queries revealing the neighborhood of carefully selected vertices. After specifying a random generator which removes edges from the underlying graph, we present estimators with strong provable performance guarantees, which exploit information from the noisy network samples and query a constant number of the most important vertices for the estimation. Our experimental evaluation shows that, in practice, a single noisy network sample and a couple of hundreds neighborhood queries suffice for accurately estimating the number of triangles in networks with millions of vertices and edges.

Estimating the Number of Induced Subgraphs from Incomplete Data and Neighborhood Queries

Neural autoregressive sequence models are used to generate sequences in a variety of natural language processing (NLP) tasks, where they are evaluated according to sequence-level task losses. These models are typically trained with maximum likelihood estimation, which ignores the task loss, yet empirically performs well as a surrogate objective. Typical approaches to directly optimizing the task loss such as policy gradient and minimum risk training are based around sampling in the sequence space to obtain candidate update directions that are scored based on the loss of a single sequence. In this paper, we develop an alternative method based on random search in the parameter space that leverages access to the maximum likelihood gradient. We propose maximum likelihood guided parameter search (MGS), which samples from a distribution over update directions that is a mixture of random search around the current parameters and around the maximum likelihood gradient, with each direction weighted by its improvement in the task loss. MGS shifts sampling to the parameter space, and scores candidates using losses that are pooled from multiple sequences. Our experiments show that MGS is capable of optimizing sequence-level losses, with substantial reductions in repetition and non-termination in sequence completion, and similar improvements to those of minimum risk training in machine translation.

MLE-Guided Parameter Search for Task Loss Minimization in Neural Sequence Modeling

The graph Laplacian regularization term is usually used in semi-supervised representation learning to provide graph structure information for a model f(X). However, with the recent popularity of graph neural networks (GNNs), directly encoding graph structure A into a model, i.e., f(A, X), has become the more common approach. While we show that graph Laplacian regularization brings little-to-no benefit to existing GNNs, and propose a simple but non-trivial variant of graph Laplacian regularization, called Propagation-regularization (P-reg), to boost the performance of existing GNN models. We provide formal analyses to show that P-reg not only infuses extra information (that is not captured by the traditional graph Laplacian regularization) into GNNs, but also has the capacity equivalent to an infinite-depth graph convolutional network. We demonstrate that P-reg can effectively boost the performance of existing GNN models on both node-level and graph-level tasks across many different datasets.

Rethinking Graph Regularization for Graph Neural Networks

With the increasing scale of machine learning tasks, it has become essential to reduce the communication between computing nodes. Early work on gradient compression focused on the bottleneck between CPUs and GPUs, but  communication-efficiency is now needed in a variety of  different system architectures, from high-performance clusters to energy-constrained IoT devices. In the current practice, compression levels are typically chosen before training and settings that work well for one task may be vastly suboptimal for another dataset on another architecture. In this paper, we propose a flexible framework which adapts the compression level to the true gradient at each iteration, maximizing the improvement in the objective function that is achieved per communicated bit. Our framework is easy to adapt from one technology to the next by modeling how the communication cost depends on the compression level for the specific technology. Theoretical results and practical experiments indicate that the automatic tuning strategies significantly increase communication efficiency on several state-of-the-art compression schemes.

A Flexible Framework for Communication-Efficient Machine Learning

Knowledge graph (KG for short) alignment aims at building a complete KG by linking the shared entities across complementary KGs. Existing approaches assume that KGs are static, despite the fact that almost every KG evolves over time. In this paper, we introduce the task of dynamic knowledge graph alignment, the main challenge of which is how to efficiently update entity embeddings for the evolving graph topology. Our key insight is to view the parameter matrix of GCN as a feature transformation operator and decouple the transformation process from the aggregation process. Based on that, we first propose a novel base algorithm (DINGAL-B) with topology-invariant mask gate and highway gate, which consistently outperforms 14 existing knowledge graph alignment methods in the static setting. More importantly, it naturally leads to two effective and efficient algorithms to align dynamic knowledge graph, including (1) DINGAL-O which leverages previous parameter matrices to update the embeddings of affected entities; and (2) DINGAL-U which resorts to newly obtained anchor links to fine-tune parameter matrices. Compared with their static counterpart (DINGAL-B), DINGAL-U and DINGAL-O are 10Ã— and 100Ã— faster respectively, with little alignment accuracy loss.

Dynamic Knowledge Graph Alignment

Many applications of machine learning on discrete domains, such as learning preference functions in recommender systems
or auctions, can be reduced to estimating a set function that is sparse in the Fourier domain. In this work, we present a new
family of algorithms for learning Fourier-sparse set functions. They require at most nk âˆ’ k log k + k queries (set function
evaluations), under mild conditions on the Fourier coefficients, where n is the size of the ground set and k the number of
non-zero Fourier coefficients. In contrast to other work that focused on the orthogonal Walsh-Hadamard transform (WHT),
our novel algorithms operate with recently introduced non-orthogonal Fourier transforms that offer different notions of
Fourier-sparsity. These naturally arise when modeling, e.g., sets of items forming substitutes and complements. We 
demonstrate effectiveness on several real-world applications.

Learning Set Functions that are Sparse in Non-Orthogonal Fourier Bases

Multi-task learning has gained popularity due to the advantages it provides with respect to resource usage and performance. Nonetheless, the joint optimization of parameters with respect to multiple tasks remains an active research topic. Sub-partitioning the parameters between different tasks has proven to be an efficient way to relax the optimization constraints over the shared weights, may the partitions be disjoint or overlapping. However, one drawback of this approach is that it can weaken the inductive bias generally set up by the joint task optimization. In this work, we present a novel way to partition the parameter space without weakening the inductive bias. Specifically, we propose Maximum Roaming, a method inspired by dropout that randomly varies the parameter partitioning, while forcing them to visit as many tasks as possible at a regulated frequency, so that the network fully adapts to each update. We study the properties of our method through experiments on a variety of visual multi-task data sets. Experimental results suggest that the regularization brought by roaming has more impact on performance than usual partitioning optimization strategies. The overall method is flexible, easily applicable, provides superior regularization and consistently achieves improved performances compared to recent multi-task learning formulations.

Maximum Roaming Multi-Task Learning

This paper studies the problem of clustering in metric spaces while preserving the privacy of individual data. Specifically, we examine differentially private variants of the k-medians and Euclidean k-means problems. We  present polynomial algorithms with constant multiplicative error and lower additive error than the previous state-of-the-art for each problem. Additionally, our algorithms use a clustering algorithm without differential privacy as a black-box. This allows  practitioners to control the trade-off between runtime and approximation factor by choosing a suitable clustering algorithm to use.

Differentially Private Clustering via Maximum Coverage

This paper focuses on the expected difference in borrower's repayment when there is a change in the lender's credit decisions. Classical estimators overlook the confounding effects and hence the estimation error can be magnificent. As such, we propose another approach to construct the estimators such that the error can be greatly reduced. The proposed estimators are shown to be unbiased, consistent, and robust through a combination of theoretical analysis and numerical testing. Moreover, we compare the power of estimating the causal quantities between the classical estimators and the proposed estimators. The comparison is tested across a wide range of models, including linear regression models, tree-based models, and neural network-based models, under different simulated datasets that exhibit different levels of causality, different degrees of nonlinearity, and different distributional properties. Most importantly, we apply our approaches to a large observational dataset provided by a global technology firm that operates in both the e-commerce and the lending business. We find that the relative reduction of estimation error is strikingly substantial if the causal effects are accounted for correctly.

Downloads

Next from AAAI 2021

Adversarial Language Games for Advanced Natural Language Intelligence

Similar lecture

Chaining Value Functions for Off-Policy Learning

.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

Adversarial Language Games for Advanced Natural Language Intelligence

Similar lecture

Chaining Value Functions for Off-Policy Learning

Downloads