Modeling the data generator as a stochastic policy in reinforcement learning (RL), SeqGAN bypasses the generator differentiation problem by directly performing gradient policy update.
A unified framework takes advantage of both schools of thinking in information retrieval modelling and shows that the generative model learns to fit the relevance distribution over documents via the signals from the discriminative model to achieve a better estimation for document ranking.
IEEE 16th International Conference on Data Mining…
1 November 2016
TLDR
A Product-based Neural Networks (PNN) with an embedding layer to learn a distributed representation of the categorical data, a product layer to capture interactive patterns between interfield categories, and further fully connected layers to explore high-order feature interactions.
This paper proposes a novel Self-Taught Hashing (STH) approach to semantic hashing: it first finds the optimal l-bit binary codes for all documents in the given corpus via unsupervised learning, and then train l classifiers via supervised learning to predict the l- bit code for any query document unseen before.
The Texygen platform could help standardize the research on text generation and improve the reproductivity and reliability of future research work in text generation.
The discriminative net is allowed to leak its own high-level extracted features to the generative net to further help the guidance, and without any supervision, LeakGAN would be able to implicitly learn sentence structures only through the interaction between Manager and Worker.
This paper proposes a new framework toward efficient architecture search by exploring the architecture space based on the current network and reusing its weights, and employs a reinforcement learning agent as the meta-controller, whose action is to grow the network depth or layer width with function-preserving transformations.
This paper proposes two novel models using deep neural networks (DNNs) to automatically learn effective patterns from categorical feature interactions and make predictions of users' ad clicks and demonstrates that their methods work better than major state-of-the-art models.
An efficient document ranking algorithm is derived that generalizes the well-known probability ranking principle by considering both the uncertainty of relevance predictions and correlations between retrieved documents and the benefit of diversification is mathematically quantified.
The mathematical derivation suggests that optimal bidding strategies should try to bid more impressions rather than focus on a small set of high valued impressions because according to the current RTB market data, compared to the higher evaluated impressions, the lower evaluated ones are more cost effective and the chances of winning them are relatively higher.