09,24,2021

News Blog Paper China
Bootstrapping User and Item Representations for One-Class Collaborative Filtering2021-05-13   ${\displaystyle \cong }$
The goal of one-class collaborative filtering (OCCF) is to identify the user-item pairs that are positively-related but have not been interacted yet, where only a small portion of positive user-item interactions (e.g., users' implicit feedback) are observed. For discriminative modeling between positive and negative interactions, most previous work relied on negative sampling to some extent, which refers to considering unobserved user-item pairs as negative, as actual negative ones are unknown. However, the negative sampling scheme has critical limitations because it may choose "positive but unobserved" pairs as negative. This paper proposes a novel OCCF framework, named as BUIR, which does not require negative sampling. To make the representations of positively-related users and items similar to each other while avoiding a collapsed solution, BUIR adopts two distinct encoder networks that learn from each other; the first encoder is trained to predict the output of the second encoder as its target, while the second encoder provides the consistent targets by slowly approximating the first encoder. In addition, BUIR effectively alleviates the data sparsity issue of OCCF, by applying stochastic data augmentation to encoder inputs. Based on the neighborhood information of users and items, BUIR randomly generates the augmented views of each positive interaction each time it encodes, then further trains the model by this self-supervision. Our extensive experiments demonstrate that BUIR consistently and significantly outperforms all baseline methods by a large margin especially for much sparse datasets in which any assumptions about negative interactions are less valid.
 
Future Data Helps Training: Modeling Future Contexts for Session-based Recommendation2020-01-25   ${\displaystyle \cong }$
Session-based recommender systems have attracted much attention recently. To capture the sequential dependencies, existing methods resort either to data augmentation techniques or left-to-right style autoregressive training.Since these methods are aimed to model the sequential nature of user behaviors, they ignore the future data of a target interaction when constructing the prediction model for it. However, we argue that the future interactions after a target interaction, which are also available during training, provide valuable signal on user preference and can be used to enhance the recommendation quality. Properly integrating future data into model training, however, is non-trivial to achieve, since it disobeys machine learning principles and can easily cause data leakage. To this end, we propose a new encoder-decoder framework named Gap-filling based Recommender (GRec), which trains the encoder and decoder by a gap-filling mechanism. Specifically, the encoder takes a partially-complete session sequence (where some items are masked by purpose) as input, and the decoder predicts these masked items conditioned on the encoded representation. We instantiate the general GRec framework using convolutional neural network with sparse kernels, giving consideration to both accuracy and efficiency. We conduct experiments on two real-world datasets covering short-, medium-, and long-range user sessions, showing that GRec significantly outperforms the state-of-the-art sequential recommendation methods. More empirical studies verify the high utility of modeling future contexts under our GRec framework.
 
Learning Dynamic Embeddings from Temporal Interactions2018-12-05   ${\displaystyle \cong }$
Modeling a sequence of interactions between users and items (e.g., products, posts, or courses) is crucial in domains such as e-commerce, social networking, and education to predict future interactions. Representation learning presents an attractive solution to model the dynamic evolution of user and item properties, where each user/item can be embedded in a euclidean space and its evolution can be modeled by dynamic changes in embedding. However, existing embedding methods either generate static embeddings, treat users and items independently, or are not scalable. Here we present JODIE, a coupled recurrent model to jointly learn the dynamic embeddings of users and items from a sequence of user-item interactions. JODIE has three components. First, the update component updates the user and item embedding from each interaction using their previous embeddings with the two mutually-recursive Recurrent Neural Networks. Second, a novel projection component is trained to forecast the embedding of users at any future time. Finally, the prediction component directly predicts the embedding of the item in a future interaction. For models that learn from a sequence of interactions, traditional training data batching cannot be done due to complex user-user dependencies. Therefore, we present a novel batching algorithm called t-Batch that generates time-consistent batches of training data that can run in parallel, giving massive speed-up. We conduct six experiments on two prediction tasks---future interaction prediction and state change prediction---using four real-world datasets. We show that JODIE outperforms six state-of-the-art algorithms in these tasks by up to 22.4%. Moreover, we show that JODIE is highly scalable and up to 9.2x faster than comparable models. As an additional experiment, we illustrate that JODIE can predict student drop-out from courses five interactions in advance.
 
Learning Problem-agnostic Speech Representations from Multiple Self-supervised Tasks2019-04-06   ${\displaystyle \cong }$
Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some recent works, however, have shown that it is possible to derive useful speech representations by employing a self-supervised encoder-discriminator approach. This paper proposes an improved self-supervised method, where a single neural encoder is followed by multiple workers that jointly solve different self-supervised tasks. The needed consensus across different tasks naturally imposes meaningful constraints to the encoder, contributing to discover general representations and to minimize the risk of learning superficial ones. Experiments show that the proposed approach can learn transferable, robust, and problem-agnostic features that carry on relevant information from the speech signal, such as speaker identity, phonemes, and even higher-level features such as emotional cues. In addition, a number of design choices make the encoder easily exportable, facilitating its direct usage or adaptation to different problems.
 
Dynamic Graph Collaborative Filtering2021-01-07   ${\displaystyle \cong }$
Dynamic recommendation is essential for modern recommender systems to provide real-time predictions based on sequential data. In real-world scenarios, the popularity of items and interests of users change over time. Based on this assumption, many previous works focus on interaction sequences and learn evolutionary embeddings of users and items. However, we argue that sequence-based models are not able to capture collaborative information among users and items directly. Here we propose Dynamic Graph Collaborative Filtering (DGCF), a novel framework leveraging dynamic graphs to capture collaborative and sequential relations of both items and users at the same time. We propose three update mechanisms: zero-order 'inheritance', first-order 'propagation', and second-order 'aggregation', to represent the impact on a user or item when a new interaction occurs. Based on them, we update related user and item embeddings simultaneously when interactions occur in turn, and then use the latest embeddings to make recommendations. Extensive experiments conducted on three public datasets show that DGCF significantly outperforms the state-of-the-art dynamic recommendation methods up to 30. Our approach achieves higher performance when the dataset contains less action repetition, indicating the effectiveness of integrating dynamic collaborative information.
 
Machine translation considering context information using Encoder-Decoder model2019-03-30   ${\displaystyle \cong }$
In the task of machine translation, context information is one of the important factor. But considering the context information model dose not proposed. The paper propose a new model which can integrate context information and make translation. In this paper, we create a new model based Encoder Decoder model. When translating current sentence, the model integrates output from preceding encoder with current encoder. The model can consider context information and the result score is higher than existing model.
 
Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks2019-08-03   ${\displaystyle \cong }$
Modeling sequential interactions between users and items/products is crucial in domains such as e-commerce, social networking, and education. Representation learning presents an attractive opportunity to model the dynamic evolution of users and items, where each user/item can be embedded in a Euclidean space and its evolution can be modeled by an embedding trajectory in this space. However, existing dynamic embedding methods generate embeddings only when users take actions and do not explicitly model the future trajectory of the user/item in the embedding space. Here we propose JODIE, a coupled recurrent neural network model that learns the embedding trajectories of users and items. JODIE employs two recurrent neural networks to update the embedding of a user and an item at every interaction. Crucially, JODIE also models the future embedding trajectory of a user/item. To this end, it introduces a novel projection operator that learns to estimate the embedding of the user at any time in the future. These estimated embeddings are then used to predict future user-item interactions. To make the method scalable, we develop a t-Batch algorithm that creates time-consistent batches and leads to 9x faster training. We conduct six experiments to validate JODIE on two prediction tasks---future interaction prediction and state change prediction---using four real-world datasets. We show that JODIE outperforms six state-of-the-art algorithms in these tasks by at least 20% in predicting future interactions and 12% in state change prediction.
 
Dual-embedding based Neural Collaborative Filtering for Recommender Systems2021-02-04   ${\displaystyle \cong }$
Among various recommender techniques, collaborative filtering (CF) is the most successful one. And a key problem in CF is how to represent users and items. Previous works usually represent a user (an item) as a vector of latent factors (aka. \textit{embedding}) and then model the interactions between users and items based on the representations. Despite its effectiveness, we argue that it's insufficient to yield satisfactory embeddings for collaborative filtering. Inspired by the idea of SVD++ that represents users based on themselves and their interacted items, we propose a general collaborative filtering framework named DNCF, short for Dual-embedding based Neural Collaborative Filtering, to utilize historical interactions to enhance the representation. In addition to learning the primitive embedding for a user (an item), we introduce an additional embedding from the perspective of the interacted items (users) to augment the user (item) representation. Extensive experiments on four publicly datasets demonstrated the effectiveness of our proposed DNCF framework by comparing its performance with several traditional matrix factorization models and other state-of-the-art deep learning based recommender models.
 
Solving Cold Start Problem in Recommendation with Attribute Graph Neural Networks2020-01-21   ${\displaystyle \cong }$
Matrix completion is a classic problem underlying recommender systems. It is traditionally tackled with matrix factorization. Recently, deep learning based methods, especially graph neural networks, have made impressive progress on this problem. Despite their effectiveness, existing methods focus on modeling the user-item interaction graph. The inherent drawback of such methods is that their performance is bound to the density of the interactions, which is however usually of high sparsity. More importantly, for a cold start user/item that does not have any interactions, such methods are unable to learn the preference embedding of the user/item since there is no link to this user/item in the graph. In this work, we develop a novel framework Attribute Graph Neural Networks (AGNN) by exploiting the attribute graph rather than the commonly used interaction graph. This leads to the capability of learning embeddings for cold start users/items. Our AGNN can produce the preference embedding for a cold user/item by learning on the distribution of attributes with an extended variational auto-encoder structure. Moreover, we propose a new graph neural network variant, i.e., gated-GNN, to effectively aggregate various attributes of different modalities in a neighborhood. Empirical results on two real-world datasets demonstrate that our model yields significant improvements for cold start recommendations and outperforms or matches state-of-the-arts performance in the warm start scenario.
 
Understanding and Improving Encoder Layer Fusion in Sequence-to-Sequence Learning2020-12-29   ${\displaystyle \cong }$
Encoder layer fusion (EncoderFusion) is a technique to fuse all the encoder layers (instead of the uppermost layer) for sequence-to-sequence (Seq2Seq) models, which has proven effective on various NLP tasks. However, it is still not entirely clear why and when EncoderFusion should work. In this paper, our main contribution is to take a step further in understanding EncoderFusion. Many of previous studies believe that the success of EncoderFusion comes from exploiting surface and syntactic information embedded in lower encoder layers. Unlike them, we find that the encoder embedding layer is more important than other intermediate encoder layers. In addition, the uppermost decoder layer consistently pays more attention to the encoder embedding layer across NLP tasks. Based on this observation, we propose a simple fusion method, SurfaceFusion, by fusing only the encoder embedding layer for the softmax layer. Experimental results show that SurfaceFusion outperforms EncoderFusion on several NLP benchmarks, including machine translation, text summarization, and grammatical error correction. It obtains the state-of-the-art performance on WMT16 Romanian-English and WMT14 English-French translation tasks. Extensive analyses reveal that SurfaceFusion learns more expressive bilingual word embeddings by building a closer relationship between relevant source and target embeddings. The source code will be released.
 
TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain2021-03-17   ${\displaystyle \cong }$
In this paper, we propose a transformer-based architecture, called two-stage transformer neural network (TSTNN) for end-to-end speech denoising in the time domain. The proposed model is composed of an encoder, a two-stage transformer module (TSTM), a masking module and a decoder. The encoder maps input noisy speech into feature representation. The TSTM exploits four stacked two-stage transformer blocks to efficiently extract local and global information from the encoder output stage by stage. The masking module creates a mask which will be multiplied with the encoder output. Finally, the decoder uses the masked encoder feature to reconstruct the enhanced speech. Experimental results on the benchmark dataset show that the TSTNN outperforms most state-of-the-art models in time or frequency domain while having significantly lower model complexity.
 
Contextual Joint Factor Acoustic Embeddings2019-10-16   ${\displaystyle \cong }$
Embedding acoustic information into fixed length representations is of interest for a whole range of applications in speech and audio technology. We propose two novel unsupervised approaches to generate acoustic embeddings by modelling of acoustic context. The first approach is a contextual joint factor synthesis encoder, where the encoder in an encoder/decoder framework is trained to extract joint factors from surrounding audio frames to best generate the target output. The second approach is a contextual joint factor analysis encoder, where the encoder is trained to analyse joint factors from the source signal that correlates best with the neighbouring audio. To evaluate the effectiveness of our approaches compared to prior work, we chose two tasks - phone classification and speaker recognition - and test on different TIMIT data sets. Experimental results show that one of our proposed approaches outperforms phone classification baselines, yielding a classification accuracy of 74.1%. When using additional out-of-domain data for training, an additional 2-3% improvements can be obtained, for both for phone classification and speaker recognition tasks.
 
Interacting Attention-gated Recurrent Networks for Recommendation2017-09-07   ${\displaystyle \cong }$
Capturing the temporal dynamics of user preferences over items is important for recommendation. Existing methods mainly assume that all time steps in user-item interaction history are equally relevant to recommendation, which however does not apply in real-world scenarios where user-item interactions can often happen accidentally. More importantly, they learn user and item dynamics separately, thus failing to capture their joint effects on user-item interactions. To better model user and item dynamics, we present the Interacting Attention-gated Recurrent Network (IARN) which adopts the attention model to measure the relevance of each time step. In particular, we propose a novel attention scheme to learn the attention scores of user and item history in an interacting way, thus to account for the dependencies between user and item dynamics in shaping user-item interactions. By doing so, IARN can selectively memorize different time steps of a user's history when predicting her preferences over different items. Our model can therefore provide meaningful interpretations for recommendation results, which could be further enhanced by auxiliary features. Extensive validation on real-world datasets shows that IARN consistently outperforms state-of-the-art methods.
 
Pairwise Interactive Graph Attention Network for Context-Aware Recommendation2019-11-18   ${\displaystyle \cong }$
Context-aware recommender systems (CARS), which consider rich side information to improve recommendation performance, have caught more and more attention in both academia and industry. How to predict user preferences from diverse contextual features is the core of CARS. Several recent models pay attention to user behaviors and use specifically designed structures to extract adaptive user interests from history behaviors. However, few works take item history interactions into consideration, which leads to the insufficiency of item feature representation and item attraction extraction. From these observations, we model the user-item interaction as a dynamic interaction graph (DIG) and proposed a GNN-based model called Pairwise Interactive Graph Attention Network (PIGAT) to capture dynamic user interests and item attractions simultaneously. PIGAT introduces the attention mechanism to consider the importance of each interacted user/item to both the user and the item, which captures user interests, item attractions and their influence on the recommendation context. Moreover, confidence embeddings are applied to interactions to distinguish the confidence of interactions occurring at different times. Then more expressive user/item representations and adaptive interaction features are generated, which benefits the recommendation performance especially when involving long-tail items. We conduct experiments on three real-world datasets to demonstrate the effectiveness of PIGAT.
 
A Deep Convolutional Auto-Encoder with Pooling - Unpooling Layers in Caffe2017-01-18   ${\displaystyle \cong }$
This paper presents the development of several models of a deep convolutional auto-encoder in the Caffe deep learning framework and their experimental evaluation on the example of MNIST dataset. We have created five models of a convolutional auto-encoder which differ architecturally by the presence or absence of pooling and unpooling layers in the auto-encoder's encoder and decoder parts. Our results show that the developed models provide very good results in dimensionality reduction and unsupervised clustering tasks, and small classification errors when we used the learned internal code as an input of a supervised linear classifier and multi-layer perceptron. The best results were provided by a model where the encoder part contains convolutional and pooling layers, followed by an analogous decoder part with deconvolution and unpooling layers without the use of switch variables in the decoder part. The paper also discusses practical details of the creation of a deep convolutional auto-encoder in the very popular Caffe deep learning framework. We believe that our approach and results presented in this paper could help other researchers to build efficient deep neural network architectures in the future.
 
TwitterMancer: Predicting Interactions on Twitter Accurately2019-04-24   ${\displaystyle \cong }$
This paper investigates the interplay between different types of user interactions on Twitter, with respect to predicting missing or unseen interactions. For example, given a set of retweet interactions between Twitter users, how accurately can we predict reply interactions? Is it more difficult to predict retweet or quote interactions between a pair of accounts? Also, how important is time locality, and which features of interaction patterns are most important to enable accurate prediction of specific Twitter interactions? Our empirical study of Twitter interactions contributes initial answers to these questions. We have crawled an extensive dataset of Greek-speaking Twitter accounts and their follow, quote, retweet, reply interactions over a period of a month. We find we can accurately predict many interactions of Twitter users. Interestingly, the most predictive features vary with the user profiles, and are not the same across all users. For example, for a pair of users that interact with a large number of other Twitter users, we find that certain "higher-dimensional" triads, i.e., triads that involve multiple types of interactions, are very informative, whereas for less active Twitter users, certain in-degrees and out-degrees play a major role. Finally, we provide various other insights on Twitter user behavior. Our code and data are available at https://github.com/twittermancer/. Keywords: Graph mining, machine learning, social media, social networks
 
Feature-based factorized Bilinear Similarity Model for Cold-Start Top-n Item Recommendation2019-04-22   ${\displaystyle \cong }$
Recommending new items to existing users has remained a challenging problem due to absence of user's past preferences for these items. The user personalized non-collaborative methods based on item features can be used to address this item cold-start problem. These methods rely on similarities between the target item and user's previous preferred items. While computing similarities based on item features, these methods overlook the interactions among the features of the items and consider them independently. Modeling interactions among features can be helpful as some features, when considered together, provide a stronger signal on the relevance of an item when compared to case where features are considered independently. To address this important issue, in this work we introduce the Feature-based factorized Bilinear Similarity Model (FBSM), which learns factorized bilinear similarity model for TOP-n recommendation of new items, given the information about items preferred by users in past as well as the features of these items. We carry out extensive empirical evaluations on benchmark datasets, and we find that the proposed FBSM approach improves upon traditional non-collaborative methods in terms of recommendation performance. Moreover, the proposed approach also learns insightful interactions among item features from data, which lead to deep understanding on how these interactions contribute to personalized recommendation.
 
Multi-Layer Softmaxing during Training Neural Machine Translation for Flexible Decoding with Fewer Layers2019-08-28   ${\displaystyle \cong }$
This paper proposes a novel procedure for training an encoder-decoder based deep neural network which compresses NxM models into a single model enabling us to dynamically choose the number of encoder and decoder layers for decoding. Usually, the output of the last layer of the N-layer encoder is fed to the M-layer decoder, and the output of the last decoder layer is used to compute softmax loss. Instead, our method computes a single loss consisting of NxM losses: the softmax loss for the output of each of the M decoder layers derived using the output of each of the N encoder layers. A single model trained by our method can be used for decoding with an arbitrary fewer number of encoder and decoder layers. In practical scenarios, this (a) enables faster decoding with insignificant losses in translation quality and (b) alleviates the need to train NxM models, thereby saving space. We take a case study of neural machine translation and show the advantage and give a cost-benefit analysis of our approach.
 
User Embedding based Neighborhood Aggregation Method for Inductive Recommendation2021-02-15   ${\displaystyle \cong }$
We consider the problem of learning latent features (aka embedding) for users and items in a recommendation setting. Given only a user-item interaction graph, the goal is to recommend items for each user. Traditional approaches employ matrix factorization-based collaborative filtering methods. Recent methods using graph convolutional networks (e.g., LightGCN) achieve state-of-the-art performance. They learn both user and item embedding. One major drawback of most existing methods is that they are not inductive; they do not generalize for users and items unseen during training. Besides, existing network models are quite complex, difficult to train and scale. Motivated by LightGCN, we propose a graph convolutional network modeling approach for collaborative filtering CF-GCN. We solely learn user embedding and derive item embedding using light variant CF-LGCN-U performing neighborhood aggregation, making it scalable due to reduced model complexity. CF-LGCN-U models naturally possess the inductive capability for new items, and we propose a simple solution to generalize for new users. We show how the proposed models are related to LightGCN. As a by-product, we suggest a simple solution to make LightGCN inductive. We perform comprehensive experiments on several benchmark datasets and demonstrate the capabilities of the proposed approach. Experimental results show that similar or better generalization performance is achievable than the state of the art methods in both transductive and inductive settings.
 
Inductive Relational Matrix Completion2020-07-09   ${\displaystyle \cong }$
Data sparsity and cold-start issues emerge as two major bottlenecks for matrix completion in the context of user-item interaction matrix. We propose a novel method that can fundamentally address these issues. The main idea is to partition users into support users, which have many observed interactions (i.e., non-zero entries in the matrix), and query users, which have few observed entries. For support users, we learn their transductive preference embeddings using matrix factorization over their interactions (a relatively dense sub-matrix). For query users, we devise an inductive relational model that learns to estimate the underlying relations between the two groups of users. This allows us to attentively aggregate the preference embeddings of support users in order to compute inductive embeddings for query users. This new method can address the data sparsity issue by generalizing the behavior patterns of warm-start users to others and thus enables the model to also work effectively for cold-start users with no historical interaction. As theoretical insights, we show that a general version of our model does not sacrifice any expressive power on query users compared with transductive matrix factorization under mild conditions. Also, the generalization error on query users is bounded by the numbers of support users and query users' observed interactions. Moreover, extensive experiments on real-world datasets demonstrate that our model outperforms several state-of-the-art methods by achieving significant improvements on MAE and AUC for warm-start, few-shot (sparsity) and zero-shot (cold-start) recommendation.