相关论文: Initialization Matters: Regularizing Manifold-info…

Feed-forward neural networks can be understood as a combination of an intermediate representation and a linear hypothesis. While most previous works aim to diversify the representations, we explore the complementary direction by performing…

We revisit the problem of spectral clustering in multimodal settings, where each data modality is encoded as a graph Laplacian. While classical approaches--including joint diagonalization, spectral co-regularization, and multiview…

Deep neural networks are typically initialized with random weights, with variances chosen to facilitate signal propagation and stable gradients. It is also believed that diversity of features is an important property of these…

Deeply-learned planning methods are often based on learning representations that are optimized for unrelated tasks. For example, they might be trained on reconstructing the environment. These representations are then combined with predictor…

Dropout is a very effective way of regularizing neural networks. Stochastically "dropping out" units with a certain probability discourages over-specific co-adaptations of feature detectors, preventing overfitting and improving network…

State-of-the-art neural networks can be trained to become remarkable solutions to many problems. But while these architectures can express symbolic, perfect solutions, trained models often arrive at approximations instead. We show that the…

Input features play a crucial role in DNN-based recommender systems with thousands of categorical and continuous fields from users, items, contexts, and interactions. Noisy features and inappropriate embedding dimension assignments can…

In recent years significant progress has been made in successfully training recurrent neural networks (RNNs) on sequence learning problems involving long range temporal dependencies. The progress has been made on three fronts: (a)…

The homepage recommendation on most E-commerce applications places items in a hierarchical manner, where different channels display items in different styles. Existing algorithms usually optimize the performance of a single channel. So…

In this work we consider a generalized bilevel optimization framework for solving inverse problems. We introduce fractional Laplacian as a regularizer to improve the reconstruction quality, and compare it with the total variation…

Recurrent neural networks for session-based recommendation have attracted a lot of attention recently because of their promising performance. repeat consumption is a common phenomenon in many recommendation scenarios (e.g., e-commerce,…

Regularization is essential for avoiding over-fitting to training data in network optimization, leading to better generalization of the trained networks. The label noise provides a strong implicit regularization by replacing the target…

Cross-domain recommendation (CDR) has been proven as a promising way to tackle the user cold-start problem, which aims to make recommendations for users in the target domain by transferring the user preference derived from the source…

It is broadly known that deep neural networks are susceptible to being fooled by adversarial examples with perturbations imperceptible by humans. Various defenses have been proposed to improve adversarial robustness, among which adversarial…

Next-basket recommendation (NBR) is prevalent in e-commerce and retail industry. In this scenario, a user purchases a set of items (a basket) at a time. NBR performs sequential modeling and recommendation based on a sequence of baskets. NBR…

In recommender systems, users always choose the favorite items to rate, which leads to data missing not at random and poses a great challenge for unbiased evaluation and learning of prediction models. Currently, the doubly robust (DR)…

Between matrix factorization or Random Walk with Restart (RWR), which method works better for recommender systems? Which method handles explicit or implicit feedback data better? Does additional information help recommendation? Recommender…

The network embedding problem aims to map nodes that are similar to each other to vectors in a Euclidean space that are close to each other. Like centrality analysis (ranking) and community detection, network embedding is in general…

The cold start problem in recommender systems is a long-standing challenge, which requires recommending to new users (items) based on attributes without any historical interaction records. In these recommendation systems, warm users (items)…

In this work, we generalize the ideas of Kaiming initialization to Graph Neural Networks (GNNs) and propose a new scheme (G-Init) that reduces oversmoothing, leading to very good results in node and graph classification tasks. GNNs are…