Relational Gating for ''What If'' Reasoning

This paper addresses the challenge of learning to do procedural reasoning over text to answer "What if..." questions. We propose a novel relational gating network that learns to filter the key entities and relationships and learns contextual and cross representations of both procedure and question for finding the answer. Our relational gating network contains an entity gating module, relation gating module, and contextual interaction module. These modules help in solving the "What if..." reasoning problem. We show that modeling pairwise relationships helps to capture higher-order relations and find the line of reasoning for causes and effects in the procedural descriptions. Our proposed approach achieves the state-of-the-art results on the WIQA dataset.

EpistoNet: An ensemble of Epistocracy-optimized mixture of experts for detecting COVID-19 on chest X-ray images

The Coronavirus has spread across the world and infected millions of people, causing devastating damage to the public health and global economies. To mitigate the impact of the coronavirus a reliable, fast, and accurate diagnostic system should be promptly implemented. In this study, we propose EpistoNet, a decision tree-based ensemble model using two mixtures of discriminative experts to classify COVID-19 lung infection from chest X-ray images. To optimize the architecture and hyper-parameters of the designed neural networks, we employed Epistocracy algorithm, a novel hyper-heuristic evolutionary method. Using 2,500 chest X-ray images consisting of 1,250 COVID-19 and 1,250 non-COVID-19 cases, we left out 500 images for testing and partitioned the remaining 2,000 images into 5 different clusters using K-means clustering algorithm. We trained multiple deep convolutional neural networks on each cluster to help build a mixture of strong discriminative experts from the top-performing models supervised by a gating network. The final ensemble model obtained 95% accuracy on COVID-19 images and 93% accuracy on non-COVID-19. The experimental results show that EpistoNet can accurately, and reliably be used to detect COVID-19 infection in the chest X-ray images, and Epistocracy algorithm can be effectively used to optimize the hyper-parameters of the proposed models.

Memory Augmented Neural Model for Incremental Session-based Recommendation

Increasing concerns with privacy have stimulated interests in Session-based Recommendation (SR) using no personal data other than what is observed in the current browser session. Existing methods are evaluated in static settings which rarely occur in real-world applications. To better address the dynamic nature of SR tasks, we study an incremental SR scenario, where new items and preferences appear continuously. We show that existing neural recommenders can be used in incremental SR scenarios with small incremental updates to alleviate computation overhead and catastrophic forgetting. More importantly, we propose a general framework called Memory Augmented Neural model (MAN). MAN augments a base neural recommender with a continuously queried and updated nonparametric memory, and the predictions from the neural and the memory components are combined through another lightweight gating network. We empirically show that MAN is well-suited for the incremental SR task, and it consistently outperforms state-oft-he-art neural and nonparametric methods. We analyze the results and demonstrate that it is particularly good at incrementally learning preferences on new and infrequent items.

Self-Supervised Mixture-of-Experts by Uncertainty Estimation

Learning related tasks in various domains and transferring exploited knowledge to new situations is a significant challenge in Reinforcement Learning (RL). However, most RL algorithms are data inefficient and fail to generalize in complex environments, limiting their adaptability and applicability in multi-task scenarios. In this paper, we propose SelfSupervised Mixture-of-Experts (SUM), an effective algorithm driven by predictive uncertainty estimation for multitask RL. SUM utilizes a multi-head agent with shared parameters as experts to learn a series of related tasks simultaneously by Deep Deterministic Policy Gradient (DDPG). Each expert is extended by predictive uncertainty estimation on known and unknown states to enhance the Q-value evaluation capacity against overfitting and the overall generalization ability. These enable the agent to capture and diffuse the common knowledge across different tasks improving sample efficiency in each task and the effectiveness of expert scheduling across multiple tasks. Instead of task-specific design as common MoEs, a self-supervised gating network is adopted to determine a potential expert to handle each interaction from unseen environments and calibrated completely by the uncertainty feedback from the experts without explicit supervision. To alleviate the imbalanced expert utilization as the crux of MoE, optimization is accomplished via decayedmasked experience replay, which encourages both diversification and specialization of experts during different periods. We demonstrate that our approach learns faster and achieves better performance by efficient transfer and robust generalization, outperforming several related methods on extended OpenAI Gym’s MuJoCo multi-task environments.

Mixture of Experts with Entropic Regularization for Data Classification

Today, there is growing interest in the automatic classification of a variety of tasks, such as weather forecasting, product recommendations, intrusion detection, and people recognition. “Mixture-of-experts” is a well-known classification technique; it is a probabilistic model consisting of local expert classifiers weighted by a gate network that is typically based on softmax functions, combined with learnable complex patterns in data. In this scheme, one data point is influenced by only one expert; as a result, the training process can be misguided in real datasets for which complex data need to be explained by multiple experts. In this work, we propose a variant of the regular mixture-of-experts model. In the proposed model, the cost classification is penalized by the Shannon entropy of the gating network in order to avoid a “winner-takes-all” output for the gating network. Experiments show the advantage of our approach using several real datasets, with improvements in mean accuracy of 3–6% in some datasets. In future work, we plan to embed feature selection into this model.