While deep learning is a powerful tool for natural language processing (NLP) problems, successful solutions to these problems rely heavily on large amounts of annotated samples. However, manually annotating data is expensive and time-consuming. Active Learning (AL) strategies reduce the need for huge volumes of labeled data by iteratively selecting a small number of examples for manual annotation based on their estimated utility in training the given model. In this paper, we argue that since AL strategies choose examples independently, they may potentially select similar examples, all of which may not contribute significantly to the learning process. Our proposed approach, Active$\mathbf{^2}$ Learning (A$\mathbf{^2}$L), actively adapts to the deep learning model being trained to eliminate further such redundant examples chosen by an AL strategy. We show that A$\mathbf{^2}$L is widely applicable by using it in conjunction with several different AL strategies and NLP tasks. We empirically demonstrate that the proposed approach is further able to reduce the data requirements of state-of-the-art AL strategies by an absolute percentage reduction of $\approx\mathbf{3-25\%}$ on multiple NLP tasks while achieving the same performance with no additional computation overhead.
Hierarchical reinforcement learning approaches learn policies based on hierarchical decision structures. However, training such methods in practice may lead to poor generalization, with either sub-policies executing actions for too few time steps or devolving into a single policy altogether. In our work, we introduce an alternative approach to sequentially learn such skills without using an overarching hierarchical policy, in the context of environments in which an objective of the agent is to prolong the episode for as long as possible, or in other words `stay alive'. We demonstrate the utility of our approach in a simulated 3D navigation environment which we have built. We show that our method outperforms prior methods such as Soft Actor Critic and Soft Option Critic on our environment, as well as the Atari River Raid environment.
The multi-armed bandits' framework is the most common platform to study strategies for sequential decision-making problems. Recently, the notion of fairness has attracted a lot of attention in the machine learning community. One can impose the fairness condition that at any given point of time, even during the learning phase, a poorly performing candidate should not be preferred over a better candidate. This fairness constraint is known to be one of the most stringent and has been studied in the stochastic multi-armed bandits' framework in a stationary setting for which regret bounds have been established. The main aim of this paper is to study this problem in a non-stationary setting. We present a new algorithm called Fair Upper Confidence Bound with Exploration Fair-UCBe algorithm for solving a slowly varying stochastic $k$-armed bandit problem. With this we present two results: (i) Fair-UCBe indeed satisfies the above mentioned fairness condition, and (ii) it achieves a regret bound of $O\left(k^{\frac{3}{2}} T^{1 - \frac{\alpha}{2}} \sqrt{\log T}\right)$, for some suitable $\alpha \in (0, 1)$, where $T$ is the time horizon. This is the first fair algorithm with a sublinear regret bound applicable to non-stationary bandits to the best of our knowledge. We show that the performance of our algorithm in the non-stationary case approaches that of its stationary counterpart as the variation in the environment tends to zero.
Representation learning of textual networks poses a significant challenge as it involves capturing amalgamated information from two modalities: (i) underlying network structure, and (ii) node textual attributes. For this, most existing approaches learn embeddings of text and network structure by enforcing embeddings of connected nodes to be similar. Then for achieving a modality fusion they use the similarities between text embedding of a node with the structure embedding of its connected node and vice versa. This implies that these approaches require edge information for learning embeddings and they cannot learn embeddings of unseen nodes. In this paper we propose an approach that achieves both modality fusion and the capability to learn embeddings of unseen nodes. The main feature of our model is that it uses an adversarial mechanism between text embedding based discriminator, and structure embedding based generator to learn efficient representations. Then for learning embeddings of unseen nodes, we use the supervision provided by the text embedding based discriminator. In addition this, we propose a novel architecture for learning text embedding that can combine both mutual attention and topological attention mechanism, which give more flexible text embeddings. Through extensive experiments on real-world datasets, we demonstrate that our model makes substantial gains over several state-of-the-art benchmarks. In comparison with previous state-of-the-art, it gives up to 7% improvement in performance in predicting links among nodes seen in the training and up to 12% improvement in performance in predicting links involving nodes not seen in training. Further, in the node classification task, it gives up to 2% improvement in performance.
A complex combination of simultaneous supervised-unsupervised learning is believed to be the key to humans performing tasks seamlessly across multiple domains or tasks. This phenomenon of cross-domain learning has been very well studied in domain adaptation literature. Recent domain adaptation works rely on an indirect way of first aligning the source and target domain distributions and then train a classifier on the labeled source domain to classify the target domain. However, this approach has the main drawback that obtaining a near-perfect alignment of the domains in itself might be difficult/impossible (e.g., language domains). To address this, we follow Vapnik's imperative of statistical learning that states any desired problem should be solved in the most direct way rather than solving a more general intermediate task and propose a direct approach to domain adaptation that does not require domain alignment. We propose a model referred Contradistinguisher that learns contrastive features and whose objective is to jointly learn to contradistinguish the unlabeled target domain in an unsupervised way and classify in a supervised way on the source domain. We achieve the state-of-the-art on Office-31 and VisDA-2017 datasets in both single-source and multi-source settings. We also demonstrate that the contradistinguish loss improves the model performance by increasing the shape bias.
A complex combination of simultaneous supervised-unsupervised learning is believed to be the key to humans performing tasks seamlessly across multiple domains or tasks. This phenomenon of cross-domain learning has been very well studied in domain adaptation literature. Recent domain adaptation works rely on an indirect way of first aligning the source and target domain distributions and then train a classifier on the labeled source domain to classify the target domain. However, this approach has the main drawback that obtaining a near-perfect alignment of the domains in itself might be difficult or impossible (e.g., language domains). To address this, we follow Vapnik's idea of statistical learning that states any desired problem should be solved in the most direct way rather than solving a more general intermediate task and propose a direct approach to domain adaptation that does not require domain alignment. We propose a model referred Contradistinguisher that learns contrastive features and whose objective is to jointly learn to contradistinguish the unlabeled target domain in an unsupervised way and classify it in a supervised way on the source domain. We demonstrate the superiority of our approach by achieving state-of-the-art on eleven visual and four language benchmark datasets in both single-source and multi-source domain adaptation settings.
Multi-Agent Reinforcement Learning (MARL) methods find optimal policies for agents that operate in the presence of other learning agents. Central to achieving this is how the agents coordinate. One way to coordinate is by learning to communicate with each other. Can the agents develop a language while learning to perform a common task? In this paper, we formulate and study a MARL problem where cooperative agents are connected to each other via a fixed underlying network. These agents can communicate along the edges of this network by exchanging discrete symbols. However, the semantics of these symbols are not predefined and, during training, the agents are required to develop a language that helps them in accomplishing their goals. We propose a method for training these agents using emergent communication. We demonstrate the applicability of the proposed framework by applying it to the problem of managing traffic controllers, where we achieve state-of-the-art performance as compared to a number of strong baselines. More importantly, we perform a detailed analysis of the emergent communication to show, for instance, that the developed language is grounded and demonstrate its relationship with the underlying network topology. To the best of our knowledge, this is the only work that performs an in depth analysis of emergent communication in a networked MARL setting while being applicable to a broad class of problems.
In this paper we propose a statistical model for dynamically evolving networks, together with a variational inference approach. Our model, which we call Dynamic Latent Attribute Interaction Model (DLAIM), encodes edge dependencies across different time snapshots. It represents nodes via latent attributes and uses attribute interaction matrices to model the presence of edges. Both are allowed to evolve with time, thus allowing us to capture the dynamics of the network. We develop a neural network based variational inference procedure that provides a suitable way to learn the model parameters. The main strengths of DLAIM are: (i) it is flexible as it does not impose strict assumptions on network evolution unlike existing approaches, (ii) it applies to both directed as well as undirected networks, and more importantly, (iii) learned node attributes and interaction matrices may be interpretable and therefore provide insights on the mechanisms behind network evolution. Experiments done on real world networks for the task of link forecasting demonstrate the superior performance of our model as compared to existing approaches.
In most practical contexts network indexed data consists not only of a description about the presence/absence of links, but also attributes and information about the nodes and/or links. Building on success of Stochastic Block Models (SBM) we propose a simple yet powerful generalization of SBM for networks with node attributes. In a standard SBM the rows of latent community membership matrix are sampled from a multinomial. In RB-SBM, our proposed model, these rows are sampled from a Restricted Boltzmann Machine (RBM) that models a joint distribution over observed attributes and latent community membership. This model has the advantage of being simple while combining connectivity and attribute information, and it has very few tuning parameters. Furthermore, we show that inference can be done efficiently in linear time and it can be naturally extended to accommodate, for instance, overlapping communities. We demonstrate the performance of our model on multiple synthetic and real world networks with node attributes where we obtain state-of-the-art results on the task of community detection.