Search

Predicting protein function is a longstanding challenge that has significant scientific implications. The success of amino acid sequence-based learning methods depends on the relationship between sequence, structure, and function. However, recent advances in AlphaFold have led to highly accurate protein structure data becoming more readily available, prompting a fundamental question:given sufficient experimental and predicted structures, should we use structure-based learning methods instead of sequence-based learning methods for predicting protein function, given the intuition that a protein’s structure has a closer relationship to its function than its amino acid sequence?To answer this question, we explore several key factors that affect function prediction accuracy. Firstly, we learn protein representations using state-of-the-art graph neural networks (GNNs) and compare graph construction(GC) methods at the residue and atomic levels. Secondly, we investigate whether protein structures generated by AlphaFold are as effective as experimental structures for function prediction when protein graphs are used as input. Finally, we compare the accuracy of sequence-only, structure-only, and sequence-structure fusion-based learning methods for predicting protein function. Additionally, we make several observations, provide useful tips, and share code and datasets to encourage further research and enhance reproducibility.

High-throughput DNA sequencing technologies open the gate to tremendous (meta)genomic data from yet-to-be-explored microbial dark matter. However, accurately assigning protein functions to new gene sequences remains challenging. To this end, we developed FunGeneTyper, an expandable deep learning-based framework with models, structured databases and tools for ultra-accurate (>0.99) and fine-grained classification and discovery of antibiotic resistance genes (ARGs) and virulence factor or toxin genes. Specifically, this new framework achieves superior performance in discovering new ARGs from human gut (accuracy: 0.8512; and F1-score: 0.6948), wastewater (0.7273; 0.6072), and soil (0.8269; 0.5445) samples, beating the state-of-the-art bioinformatics tools and protein sequence-based (F1-score: 0.0556-0.5065) and domain-based (F1-score: 0.2630-0.5224) alignment approaches. We empowered the generalized application of the framework by implementing a lightweight, privacy-preserving and plug-and-play neural network module shareable among global developers and users. The FunGeneTyper*is released to promote the monitoring of key functional genes and discovery of precious enzymatic resources from diverse microbiomes.

Accurately predicting the effects of mutations in cancer has the potential to improve existing treatments and identify novel therapeutic targets. In this paper, we evidence for the first time that the large-scale pre-trained protein language models (PPLMs) are zero-shot predictors for twoclinicallyrelevant tasks: identifying diseasecausing mutations and predicting patient survival rate. Then we benchmark a series of state-of-the-art (SOTA) PPLMs on 2279 protein variants across 20 cancer-related genes. Our empirical results show that the PPLMs outperform the SOTA baseline, EVE [1], trained on multiple sequence alignment (MSA) data. We also demonstrate that the evolutionary index score, generated from the PPLM’s softmax layer, is good indicator for both mutation pathogenicity and patient survival rate. Our paper has taken a key step toward the clinical utility of large-scale PPLMs.

Lifelong learning capabilities are crucial for sentiment classifiers to process continuous streams of opinioned information on the Web. However, performing lifelong learning is non-trivial for deep neural networks as continually training of incrementally available information inevitably results in catastrophic forgetting or interference. In this paper, we propose a novel iterative network pruning with uncertainty regularization method for lifelong sentiment classification (IPRLS), which leverages the principles of network pruning and weight regularization. By performing network pruning with uncertainty regularization in an iterative manner, IPRLS can adapta single BERT model to work with continuously arriving data from multiple domains while avoiding catastrophic forgetting and interference. Specifically, we leverage an iterative pruning method to remove redundant parameters in large deep networks so that the freed-up space can then be employed to learn new tasks, tackling the catastrophic forgetting problem. Instead of keeping the old-tasks fixed when learning new tasks, we also use an uncertainty regularization based on the Bayesian online learning framework to constrain the update of old tasks weights in BERT, which enables positive backward transfer, i.e. learning new tasks improves performance on past tasks while protecting old knowledge from being lost. In addition, we propose a task-specific low-dimensional residual function in parallel to each layer of BERT, which makes IPRLS less prone to losing the knowledge saved in the base BERT network when learning a new task. Extensive experiments on 16 popular review corpora demonstrate that the proposed IPRLS method sig-nificantly outperforms the strong baselines for lifelong sentiment classification. For reproducibility, we submit the code and data at:https://github.com/siat-nlp/IPRLS., Comment: Accepted by the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2021

This ability to learn consecutive tasks without forgetting how to perform previously trained problems is essential for developing an online dialogue system. This paper proposes an effective continual learning for the task-oriented dialogue system with iterative network pruning, expanding and masking (TPEM), which preserves performance on previously encountered tasks while accelerating learning progress on subsequent tasks. Specifically, TPEM (i) leverages network pruning to keep the knowledge for old tasks, (ii) adopts network expanding to create free weights for new tasks, and (iii) introduces task-specific network masking to alleviate the negative impact of fixed weights of old tasks on new tasks. We conduct extensive experiments on seven different tasks from three benchmark datasets and show empirically that TPEM leads to significantly improved results over the strong competitors. For reproducibility, we submit the code and data at: https://github.com/siat-nlp/TPEM, Comment: Accepted by The Annual Meeting of the Association for Computational Linguistics (ACL), 2021

Learning user representations is a vital technique toward effective user modeling and personalized recommender systems. Existing approaches often derive an individual set of model parameters for each task by training on separate data. However, the representation of the same user potentially has some commonalities, such as preference and personality, even in different tasks. As such, these separately trained representations could be suboptimal in performance as well as inefficient in terms of parameter sharing. In this paper, we delve on research to continually learn user representations task by task, whereby new tasks are learned while using partial parameters from old ones. A new problem arises since when new tasks are trained, previously learned parameters are very likely to be modified, and as a result, an artificial neural network (ANN)-based model may lose its capacity to serve for well-trained previous tasks forever, this issue is termed catastrophic forgetting. To address this issue, we present \emph{Conure} the first \underline{con}tinual, or lifelong, \underline{u}ser \underline{re}presentation learner -- i.e., learning new tasks over time without forgetting old ones. Specifically, we propose iteratively removing less important weights of old tasks in a deep user representation model, motivated by the fact that neural network models are usually over-parameterized. In this way, we could learn many tasks with a single model by reusing the important weights, and modifying the less important weights to adapt to new tasks. We conduct extensive experiments on two real-world datasets with nine tasks and show that \emph{Conure} largely exceeds the standard model that does not purposely preserve such old "knowledge", and performs competitively or sometimes better than models which are trained either individually for each task or simultaneously by merging all task data.

Inductive transfer learning has had a big impact on computer vision and NLP domains but has not been used in the area of recommender systems. Even though there has been a large body of research on generating recommendations based on modeling user-item interaction sequences, few of them attempt to represent and transfer these models for serving downstream tasks where only limited data exists. In this paper, we delve on the task of effectively learning a single user representation that can be applied to a diversity of tasks, from cross-domain recommendations to user profile predictions. Fine-tuning a large pre-trained network and adapting it to downstream tasks is an effective way to solve such tasks. However, fine-tuning is parameter inefficient considering that an entire model needs to be re-trained for every new task. To overcome this issue, we develop a parameter-efficient transfer learning architecture, termed as PeterRec, which can be configured on-the-fly to various downstream tasks. Specifically, PeterRec allows the pre-trained parameters to remain unaltered during fine-tuning by injecting a series of re-learned neural networks, which are small but as expressive as learning the entire network. We perform extensive experimental ablation to show the effectiveness of the learned user representation in five downstream tasks. Moreover, we show that PeterRec performs efficient transfer learning in multiple domains, where it achieves comparable or sometimes better performance relative to fine-tuning the entire model parameters. Codes and datasets are available at https://github.com/fajieyuan/sigir2020_peterrec.

Deep learning has brought great progress for the sequential recommendation (SR) tasks. With advanced network architectures, sequential recommender models can be stacked with many hidden layers, e.g., up to 100 layers on real-world recommendation datasets. Training such a deep network is difficult because it can be computationally very expensive and takes much longer time, especially in situations where there are tens of billions of user-item interactions. To deal with such a challenge, we present StackRec, a simple, yet very effective and efficient training framework for deep SR models by iterative layer stacking. Specifically, we first offer an important insight that hidden layers/blocks in a well-trained deep SR model have very similar distributions. Enlightened by this, we propose the stacking operation on the pre-trained layers/blocks to transfer knowledge from a shallower model to a deep model, then we perform iterative stacking so as to yield a much deeper but easier-to-train SR model. We validate the performance of StackRec by instantiating it with four state-of-the-art SR models in three practical scenarios with real-world datasets. Extensive experiments show that StackRec achieves not only comparable performance, but also substantial acceleration in training time, compared to SR models that are trained from scratch. Codes are available at https://github.com/wangjiachun0426/StackRec.

Convolutional Neural Networks (CNNs) have been recently introduced in the domain of session-based next item recommendation. An ordered collection of past items the user has interacted with in a session (or sequence) are embedded into a 2-dimensional latent matrix, and treated as an image. The convolution and pooling operations are then applied to the mapped item embeddings. In this paper, we first examine the typical session-based CNN recommender and show that both the generative model and network architecture are suboptimal when modeling long-range dependencies in the item sequence. To address the issues, we introduce a simple, but very effective generative model that is capable of learning high-level representation from both short- and long-range item dependencies. The network architecture of the proposed model is formed of a stack of holed convolutional layers, which can efficiently increase the receptive fields without relying on the pooling operation. Another contribution is the effective use of residual block structure in recommender systems, which can ease the optimization for much deeper networks. The proposed generative model attains state-of-the-art accuracy with less training time in the next item recommendation task. It accordingly can be used as a powerful recommendation baseline to beat in future, especially when there are long sequences of user feedback.

As the core of recommender system, collaborative filtering (CF) models the affinity between a user and an item from historical user-item interactions, such as clicks, purchases, and so on. Benefited from the strong representation power, neural networks have recently revolutionized the recommendation research, setting up a new standard for CF. However, existing neural recommender models do not explicitly consider the correlations among embedding dimensions, making them less effective in modeling the interaction function between users and items. In this work, we emphasize on modeling the correlations among embedding dimensions in neural networks to pursue higher effectiveness for CF. We propose a novel and general neural collaborative filtering framework, namely ConvNCF, which is featured with two designs: 1) applying outer product on user embedding and item embedding to explicitly model the pairwise correlations between embedding dimensions, and 2) employing convolutional neural network above the outer product to learn the high-order correlations among embedding dimensions. To justify our proposal, we present three instantiations of ConvNCF by using different inputs to represent a user and conduct experiments on two real-world datasets. Extensive results verify the utility of modeling embedding dimension correlations with ConvNCF, which outperforms several competitive CF methods., Comment: TOIS Minor

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.

With the prevalence of multimedia content on the Web, developing recommender solutions that can effectively leverage the rich signal in multimedia data is in urgent need. Owing to the success of deep neural networks in representation learning, recent advance on multimedia recommendation has largely focused on exploring deep learning methods to improve the recommendation accuracy. To date, however, there has been little effort to investigate the robustness of multimedia representation and its impact on the performance of multimedia recommendation. In this paper, we shed light on the robustness of multimedia recommender system. Using the state-of-the-art recommendation framework and deep image features, we demonstrate that the overall system is not robust, such that a small (but purposeful) perturbation on the input image will severely decrease the recommendation accuracy. This implies the possible weakness of multimedia recommender system in predicting user preference, and more importantly, the potential of improvement by enhancing its robustness. To this end, we propose a novel solution named Adversarial Multimedia Recommendation (AMR), which can lead to a more robust multimedia recommender model by using adversarial learning. The idea is to train the model to defend an adversary, which adds perturbations to the target image with the purpose of decreasing the model's accuracy. We conduct experiments on two representative multimedia recommendation tasks, namely, image recommendation and visually-aware product recommendation. Extensive results verify the positive effect of adversarial learning and demonstrate the effectiveness of our AMR method. Source codes are available in https://github.com/duxy-me/AMR., TKDE

CBOW (Continuous Bag-Of-Words) is one of the most commonly used techniques to generate word embeddings in various NLP tasks. However, it fails to reach the optimal performance due to uniform involvements of positive words and a simple sampling distribution of negative words. To resolve these issues, we propose OptRank to optimize word ranking and approximate negative sampling for bettering word embedding. Specifically, we first formalize word embedding as a ranking problem. Then, we weigh the positive words by their ranks such that highly ranked words have more importance, and adopt a dynamic sampling strategy to select informative negative words. In addition, an approximation method is designed to efficiently compute word ranks. Empirical experiments show that OptRank consistently outperforms its counterparts on a benchmark dataset with different sampling scales, especially when the sampled subset is small. The code and datasets can be obtained from https://github.com/ouououououou/OptRank.

To cope with ambiguous and/or underspecified queries, search result diversification (SRD) is a key technique that has attracted a lot of attention. This paper focuses on implicit SRD, where the subtopics underlying a query are unknown. Many existing methods appeal to the greedy strategy for generating diversified results. A common practice is using a heuristic criterion for making the locally optimal choice at each round. As a result, it is difficult to know whether the failures are caused by the optimization criterion or the setting of parameters. Different from previous studies, we formulate implicit SRD as a process of selecting and ranking k exemplar documents through integer linear programming (ILP). The key idea is that: for a specific query, we expect to maximize the overall relevance of the k exemplar documents. Meanwhile, we wish to maximize the representativeness of the selected exemplar documents with respect to the non-selected documents. Intuitively, if the selected exemplar documents concisely represent the entire set of documents, the novelty and diversity will naturally arise. Moreover, we propose two approaches ILP4ID (Integer Linear Programming for Implicit SRD) and AP4ID (Affinity Propagation for Implicit SRD) for solving the proposed formulation of implicit SRD. In particular, ILP4ID appeals to the strategy of bound-and-branch and is able to obtain the optimal solution. AP4ID being an approximate method transforms the target problem as a maximum-a-posteriori inference problem, and the message passing algorithm is adopted to find the solution. Furthermore, we investigate the differences and connections between the proposed models and prior models by casting them as different variants of the cluster-based paradigm for implicit SRD. To validate the effectiveness and efficiency of the proposed approaches, we conduct a series of experiments on four benchmark TREC diversity collections. The experimental results demonstrate that: (1) The proposed methods, especially ILP4ID, can achieve substantially improved performance over the state-of-the-art unsupervised methods for implicit SRD. (2) The initial runs, the number of input documents, query types, the ways of computing document similarity, the pre-defined cluster number and the optimization algorithm significantly affect the performance of diversification models. Careful examinations of these factors are highly recommended in the development of implicit SRD methods. Based on the in-depth study of different types of methods for implicit SRD, we provide additional insight into the cluster-based paradigm for implicit SRD. In particular, how the methods relying on greedy strategies impact the performance of implicit SRD, and how a particular diversification model should be fine-tuned.

Community Question Answering (CQA) services, such as Yahoo! Answers and WikiAnswers, have become popular with users as one of the central paradigms for satisfying users' information needs. The task of question retrieval aims to resolve one's query directly by finding the most relevant questions (together with their answers) from an archive of past questions. However, as the text of each question is short, there is usually a lexical gap between the queried question and the past questions. To alleviate this problem, we present a hybrid approach that blends several language modelling techniques for question retrieval, namely, the classic (query-likelihood) language model, the state-of-the-art translation-based language model, and our proposed semantics-based language model. The semantics of each candidate question is given by a probabilistic topic model which makes use of local and global semantic graphs for capturing the hidden interactions among entities (e.g., people, places, and concepts) in question-answer pairs. Experiments on two real-world datasets show that our approach can significantly outperform existing ones.