Two important tasks at the intersection of knowledge graphs and natural language processing are graph-to-text (G2T) and text-to-graph (T2G) conversion. Due to the difficulty and high cost of data collection, the supervised data available in the two fields are usually on the magnitude of tens of thousands, for example, 18K in the WebNLG dataset, which is far fewer than the millions of data for other tasks such as machine translation. Consequently, deep learning models in these two fields suffer largely from scarce training data. This work presents the first attempt to unsupervised learning of T2G and G2T via cycle training. We present CycleGT, an unsupervised training framework that can bootstrap from fully non-parallel graph and text datasets, iteratively back translate between the two forms, and use a novel pretraining strategy. Experiments on the benchmark WebNLG dataset show that, impressively, our unsupervised model trained on the same amount of data can achieve performance on par with the supervised models. This validates our framework as an effective approach to overcome the data scarcity problem in the fields of G2T and T2G.
Centralized training with decentralized execution has become an important paradigm in multi-agent learning. Though practical, current methods rely on restrictive assumptions to decompose the centralized value function across agents for execution. In this paper, we eliminate this restriction by proposing multi-agent determinantal Q-learning. Our method is established on Q-DPP, an extension of determinantal point process (DPP) with partition-matroid constraint to multi-agent setting. Q-DPP promotes agents to acquire diverse behavioral models; this allows a natural factorization of the joint Q-functions with no need for \emph{a priori} structural constraints on the value function or special network architectures. We demonstrate that Q-DPP generalizes major solutions including VDN, QMIX, and QTRAN on decentralizable cooperative tasks. To efficiently draw samples from Q-DPP, we adopt an existing sample-by-projection sampler with theoretical approximation guarantee. The sampler also benefits exploration by coordinating agents to cover orthogonal directions in the state space during multi-agent training. We evaluate our algorithm on various cooperative benchmarks; its effectiveness has been demonstrated when compared with the state-of-the-art.
Learning a neural response generation model on data synthesized under the adversarial training framework helps to explore more possible responses. However, most of the data synthesized de novo are of low quality due to the vast size of the response space. In this paper, we propose a counterfactual off-policy method to learn on a better synthesis of data. It takes advantage of a real response to infer an alternative that was not taken using a structural casual model. Learning on the counterfactual responses helps to explore the high-reward area of the response space. An empirical study on the DailyDialog dataset shows that our approach significantly outperforms the HRED model as well as the conventional adversarial training approaches.
We tackle a common scenario in imitation learning (IL), where agents try to recover the optimal policy from expert demonstrations without further access to the expert or environment reward signals. The classical inverse reinforcement learning (IRL) solution involves bi-level optimization and is of high computational cost. Recent generative adversarial methods formulate the IL problem as occupancy measure matching, which, however, suffer from the notorious training instability and mode-dropping problems. Inspired by recent progress in energy-based model (EBM), in this paper, we propose a novel IL framework named Energy-Based Imitation Learning (EBIL), solving the IL problem via estimating the expert energy as the surrogate reward function through score matching. EBIL combines the idea of both EBM and occupancy measure matching, which enjoys: (1) high model flexibility for expert policy distribution estimation; (2) efficient computation that avoids the previous alternate training fashion. Though motivated by matching the policy between the expert and the agent, we surprisingly find a non-trivial connection between EBIL and the classic Max-Entropy IRL (MaxEnt IRL) approach, and further show that EBIL can be seen as a simpler and more efficient solution of MaxEnt IRL. Extensive experiments show that EBIL can always achieve comparable performance against state-of-the-art methods with less computation cost.
In this paper, we focus on reducing the labeled data size for sentence learning. We argue that real-time uncertainty sampling of active learning is time-consuming, and delayed uncertainty sampling may lead to the ineffective sampling problem. We propose the adversarial uncertainty sampling in discrete space, in which sentences are mapped into the popular pre-trained language model encoding space. Our proposed approach can work in real-time and is more efficient than traditional uncertainty sampling. Experimental results on five datasets show that our proposed approach outperforms strong baselines and can achieve better uncertainty sampling effectiveness with acceptable running time.
Learning effective feature interactions is crucial for click-through rate (CTR) prediction tasks in recommender systems. In most of the existing deep learning models, feature interactions are either manually designed or simply enumerated. However, enumerating all feature interactions brings large memory and computation cost. Even worse, useless interactions may introduce unnecessary noise and complicate the training process. In this work, we propose a two-stage algorithm called Automatic Feature Interaction Selection (AutoFIS). AutoFIS can automatically identify all the important feature interactions for factorization models with just the computational cost equivalent to training the target model to convergence. In the \emph{search stage}, instead of searching over a discrete set of candidate feature interactions, we relax the choices to be continuous by introducing the architecture parameters. By implementing a regularized optimizer over the architecture parameters, the model can automatically identify and remove the redundant feature interactions during the training process of the model. In the \emph{re-train stage}, we keep the architecture parameters serving as an attention unit to further boost the performance. Offline experiments on three large-scale datasets (two public benchmarks, one private) demonstrate that the proposed AutoFIS can significantly improve various FM based models. AutoFIS has been deployed onto the training platform of Huawei App Store recommendation service, where a 10-day online A/B test demonstrated that AutoFIS improved the DeepFM model by 20.3\% and 20.1\% in terms of CTR and CVR respectively.