Deep Reinforcement Learning for Ride-sharing Dispatching and Repositioning

In this demo, we will present a simulation-based human-computer interaction of deep reinforcement learning in action on order dispatching and driver repositioning for ride-sharing. Specifically, we will demonstrate through several specially designed domains how we use deep reinforcement learning to train agents (drivers) to have longer optimization horizon and to cooperate to achieve higher objective values collectively.

Teaching AI Agents Ethical Values Using Reinforcement Learning and Policy Orchestration

Autonomous cyber-physical agents play an increasingly large role in our lives. To ensure that they behave in ways aligned with the values of society, we must develop techniques that allow these agents to not only maximize their reward in an environment, but also to learn and follow the implicit constraints of society. We detail a novel approach that uses inverse reinforcement learning to learn a set of unspecified constraints from demonstrations and reinforcement learning to learn to maximize environmental rewards. A contextual bandit-based orchestrator then picks between the two policies: constraint-based and environment reward-based. The contextual bandit orchestrator allows the agent to mix policies in novel ways, taking the best actions from either a reward-maximizing or constrained policy. In addition, the orchestrator is transparent on which policy is being employed at each time step. We test our algorithms using Pac-Man and show that the agent is able to learn to act optimally, act within the demonstrated constraints, and mix these two functions in complex ways.

Risk Assessment for Networked-guarantee Loans Using High-order Graph Attention Representation

Assessing and predicting the default risk of networked-guarantee loans is critical for the commercial banks and financial regulatory authorities. The guarantee relationships between the loan companies are usually modeled as directed networks. Learning the informative low-dimensional representation of the networks is important for the default risk prediction of loan companies, even for the assessment of systematic financial risk level. In this paper, we propose a high-order graph attention representation method (HGAR) to learn the embedding of guarantee networks. Because this financial network is different from other complex networks, such as social, language, or citation networks, we set the binary roles of vertices and define high-order adjacent measures based on financial domain characteristics. We design objective functions in addition to a graph attention layer to capture the importance of nodes. We implement a productive learning strategy and prove that the complexity is near-linear with the number of edges, which could scale to large datasets. Extensive experiments demonstrate the superiority of our model over state-of-the-art method. We also evaluate the model in a real-world loan risk control system, and the results validate the effectiveness of our proposed approaches.

Weak Supervision Enhanced Generative Network for Question Generation

Automatic question generation according to an answer within the given passage is useful for many applications, such as question answering system, dialogue system, etc. Current neural-based methods mostly take two steps which extract several important sentences based on the candidate answer through manual rules or supervised neural networks and then use an encoder-decoder framework to generate questions about these sentences. These approaches still acquire two steps and neglect the semantic relations between the answer and the context of the whole passage which is sometimes necessary for answering the question. To address this problem, we propose the Weakly Supervision Enhanced Generative Network (WeGen) which automatically discovers relevant features of the passage given the answer span in a weakly supervised manner to improve the quality of generated questions. More specifically, we devise a discriminator, Relation Guider, to capture the relations between the passage and the associated answer and then the Multi-Interaction mechanism is deployed to transfer the knowledge dynamically for our question generation system. Experiments show the effectiveness of our method in both automatic evaluations and human evaluations.

Generalized Potential Heuristics for Classical Planning

Generalized planning aims at computing solutions that work for all instances of the same domain. In this paper, we show that several interesting planning domains possess compact generalized heuristics that can guide a greedy search in guaranteed polynomial time to the goal, and which work for any instance of the domain. These heuristics are weighted sums of state features that capture the number of objects satisfying a certain first-order logic property in any given state. These features have a meaningful interpretation and generalize naturally to the whole domain. Additionally, we present an approach based on mixed integer linear programming to compute such heuristics automatically from the observation of small training instances. We develop two variations of the approach that progressively refine the heuristic as new states are encountered. We illustrate the approach empirically on a number of standard domains, where we show that the generated heuristics will correctly generalize to all possible instances.

Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmax

In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN) parallel corpus retrieval task. In all the languages tested, the system achieves P@1 of 86% or higher. We use pairs retrieved by our approach to train NMT models that achieve similar performance to models trained on gold pairs. We explore simple document-level embeddings constructed by averaging our sentence embeddings. On the UN document-level retrieval task, document embeddings achieve around 97% on P@1 for all experimented language pairs. Lastly, we evaluate the proposed model on the BUCC mining task. The learned embeddings with raw cosine similarity scores achieve competitive results compared to current state-of-the-art models, and with a second-stage scorer we achieve a new state-of-the-art level on this task.

Crafting Efficient Neural Graph of Large Entropy

Network pruning is widely applied to deep CNN models due to their heavy computation costs and achieves high performance by keeping important weights while removing the redundancy. Pruning redundant weights directly may hurt global information flow, which suggests that an efficient sparse network should take graph properties into account. Thus, instead of paying more attention to preserving important weight, we focus on the pruned architecture itself. We propose to use graph entropy as the measurement, which shows useful properties to craft high-quality neural graphs and enables us to propose efficient algorithm to construct them as the initial network architecture. Our algorithm can be easily implemented and deployed to different popular CNN models and achieve better trade-offs.

Meta-Interpretive Learning Using HEX-Programs

Meta-Interpretive Learning (MIL) is a recent approach for Inductive Logic Programming (ILP) implemented in Prolog. Alternatively, MIL-problems can be solved by using Answer Set Programming (ASP), which may result in performance gains due to efficient conflict propagation. However, a straightforward MIL-encoding results in a huge size of the ground program and search space. To address these challenges, we encode MIL in the HEX-extension of ASP, which mitigates grounding issues, and we develop novel pruning techniques.

Multi-agent Attentional Activity Recognition

Multi-modality is an important feature of sensor based activity recognition. In this work, we consider two inherent characteristics of human activities, the spatially-temporally varying salience of features and the relations between activities and corresponding body part motions. Based on these, we propose a multi-agent spatial-temporal attention model. The spatial-temporal attention mechanism helps intelligently select informative modalities and their active periods. And the multiple agents in the proposed model represent activities with collective motions across body parts by independently selecting modalities associated with single motions. With a joint recognition goal, the agents share gained information and coordinate their selection policies to learn the optimal recognition model. The experimental results on four real-world datasets demonstrate that the proposed model outperforms the state-of-the-art methods.

Multiple Noisy Label Distribution Propagation for Crowdsourcing

Crowdsourcing services provide a fast, efficient, and cost-effective means of obtaining large labeled data for supervised learning. Ground truth inference, also called label integration, designs proper aggregation strategies to infer the unknown true label of each instance from the multiple noisy label set provided by ordinary crowd workers. However, to the best of our knowledge, nearly all existing label integration methods focus solely on the multiple noisy label set itself of the individual instance while totally ignoring the intercorrelation among multiple noisy label sets of different instances. To solve this problem, a multiple noisy label distribution propagation (MNLDP) method is proposed in this study. MNLDP first transforms the multiple noisy label set of each instance into its multiple noisy label distribution and then propagates its multiple noisy label distribution to its nearest neighbors. Consequently, each instance absorbs a fraction of the multiple noisy label distributions from its nearest neighbors and yet simultaneously maintains a fraction of its own original multiple noisy label distribution. Promising experimental results on simulated and real-world datasets validate the effectiveness of our proposed method.