Multimodal recommendation combines the user historical behaviors with the modal features of items to capture the tangible user preferences, presenting superior performance compared to the conventional ID-based recommender systems. However, existing methods still encounter two key problems in the representation learning of users and items, respectively: (1) the initialization of multimodal user representations is either agnostic to historical behaviors or contaminated by irrelevant modal noise, and (2) the widely used KNN-based item-item graph contains noisy edges with low similarities and lacks audience co-occurrence relationships. To address such issues, we propose MLLMRec, a novel preference reasoning paradigm with graph refinement for multimodal recommendation. Specifically, on the one hand, the item images are first converted into high-quality semantic descriptions using a multimodal large language model (MLLM), thereby bridging the semantic gap between visual and textual modalities. Then, we construct a behavioral description list for each user and feed it into the MLLM to reason about the purified user preference profiles that contain the latent interaction intents. On the other hand, we develop the threshold-controlled denoising and topology-aware enhancement strategies to refine the suboptimal item-item graph, thereby improving the accuracy of item representation learning. Extensive experiments on three publicly available datasets demonstrate that MLLMRec achieves the state-of-the-art performance with an average improvement of 21.48% over the optimal baselines. The source code is provided at https://github.com/Yuzhuo-Dang/MLLMRec.

Dynamic link prediction aims to predict the future links in dynamic graphs. Existing generative dynamic link prediction studies utilize the global degree distribution for mitigating the over-estimation problem, which can model the time-invariant features while neglecting the time-varying features, resulting in capturing inaccurate evolution patterns. However, such time related features are intrinsically coupled, which makes simultaneously and independently modeling both features infeasible. Motivated by these issues, we propose a Time-wise causal debiasing framework (Tide) for generative dynamic link prediction, which does not resort to any extra trainable modules. Instead, to obtain the time-invariant features, we first utilize a time-invariant deconfounded learning mechanism for decoupling the prediction score with the degree distribution. To leverage the time-varying features, we intervene in the model during the inference stage by a predicted future degree distribution, aiming to make the accurate predictions for dynamic graphs. Experiments conducted on four public datasets under both inductive and transductive settings present that our Tide enhanced models can outperform their corresponding vanilla versions by up to 21.42% and 27.73% in terms of NDCG and Jaccard, respectively.

Dynamic link prediction aims to predict the future links on dynamic graphs, which can be applied to wide scenarios such as recommender systems and social networks on the World Wide Web. Existing methods mainly (1) focus on the in-graph learning, which cannot generalize to graphs unobserved during training; or (2) achieve the cross-graph predictions in a many-many mechanism by training on multiple graphs across various domains, which results in a large computational cost. In this paper, we propose a cross-graph dynamic link predictor named CrossDyG, which achieves the cross-graph transferability in a one-many mechanism which trains on one single source graph and test on different target graphs. Specifically, we provide causal and empirical analysis on the structural bias caused by the graph-specific structural characteristics in cross-graph predictions. Then, we conduct deconfounded training to learn the universal network evolution pattern from one single source graph during training. Finally, we apply the causal intervention to leverage the graph-specific structural characteristics of each target graph during inference. Extensive experiments conducted on three benchmark data of dynamic graphs demonstrate that CrossDyG outperforms the state-of-the-art baselines by up to 11.01% and 17.02% in terms of AP and AUC, respectively. In addition, the improvements are especially significant when training on small source graphs.

Dynamic graph link prediction is widely utilized in the complex web of the real world, such as social networks, citation networks, recommendation systems, etc. Recent Transformer-based link prediction methods on dynamic graphs not only fail to model the fine-grained structures such as triangles with the vanilla Transformers in the graph serialization process, but also amplify the imbalanced distribution of graphs because of their over-estimation of high-degree nodes. To tackle these issues, we propose a Topology-aware Transformer on Dynamic Graph (TopDyG) for link prediction, consisting of a topology injected Transformer (Ti-Transformer) and a mutual information learning (Mi-Learning). The Ti-Transformer explores the explicit structure of serialized graphs, capturing the topological features. The Mi-Learning mines the relationship between nodes by modeling the mutual information with a prior knowledge, alleviating the over-estimation of high-degree nodes when applying the Transformer-based models for the dynamic graph link prediction task. Extensive experiments on four public datasets containing both transductive and inductive settings present the superiority of our proposal. In particular, TopDyG presents an improvement of 43.27% and 28.75% against the state-of-the-art baselines in terms of NDCG and Jaccard, respectively. The advantages are especially obvious on the high-density graphs.

Dynamic graph learning on temporal networks aims to understand the continuous evolution pattern of networks, with an important application on forecasting the future temporal network. Existing methods mainly focus on modeling the structural and temporal features, with recent research interest shifting toward considering the structural correlations between nodes through their neighbor co-occurrences. Though satisfactory performance has been achieved, there still remain several limitations: (1) the deviation of investigated scenarios from real-world applications, since most previous researches concentrate on special cases of multigraphs with abundant repeat edges; (2) the insufficient computational efficiency of modeling the structural features, since the existing neighbor co-occurrence scheme fails to consider explicit structural correlations between nodes and suffers from a time-consuming pairwise encoding strategy; (3) the unsatisfying prediction accuracy due to inadequate modeling of temporal features, since each neighbor’s historical temporal features and the temporal domain shifting with network evolving are both neglected. To solve these issues, we first focus on the general scenarios of temporal networks without abundant repeat edges for approaching the actual applications and propose an efficient and effective dynamic graph learning method named LightDyG. Specifically, (1) on the one hand, to increase the computational efficiency, LightDyG decouples the structural correlations between nodes and their individual substructures for fast convergence based on the analysis of existing co-occurrence mechanism, and further designs an incremental strategy for efficient structural encoding; (2) on the other hand, to improve the prediction accuracy, the temporal characteristics are considered by including both the interaction and appearance timestamps of neighbors, and a time-invariant temporal encoding strategy is designed to eliminate the temporal bias introduced by the network evolution. Extensive experiments conducted on four public temporal networks demonstrate that LightDyG outperforms the best baselines by 4.54–11.39% and 6.06–16.24% in terms of AP and AUC on the temporal link prediction tasks, respectively. In addition, LightDyG reduces the time cost for training and test up to 45.91% and 63.94%, respectively, and also achieves a fast convergence speed during training. The implementation of our approach is available in https://github.com/nudtzpan/LightDyG .

Job‐resume matching (JRM) is the core of online recruitment services for predicting the matching degree between a job post and a resume. Most of the existing methods for JRM achieve a promising performance by simplifying this task as a matching between the free‐text attributes in the job post and the resume. However, they neglect the contributions of the semistructured multivariate attributes such as education and salary, which will result in an unsuccessful prediction. To address this issue, we propose a novel approach to comprehensively explore the Internal and EXternal InTeractions for semistructured multivariate attributes in JRM, i.e., InEXIT. In detail, we first encode the key and the value of each attribute as well as its source into the same semantic space. Next, to explore the complex relationships among the multivariate attributes, we propose to hierarchically model the internal interactions among the multivariate attributes inside the job post and the resume, as well as the external interactions between the job post and the resume. In particular, a stepwise fusion mechanism is designed to respectively integrate the key embeddings and the source embeddings into the value embeddings so as to clearly indicate the key and the source of the value. Finally, we employ an aggregation matching layer to predict the matching degree. We quantify the improvements of InEXIT against the competitive baselines on a real‐world dataset, showing a general improvement of 4.28%, 4.10%, and 3.56% over the state‐of‐the‐art baseline in terms of AUC, accuracy, and F1 score, respectively.

Recent research has highlighted the importance of mixed-initiative interactions in conversational search. To enable mixed-initiative interactions, information retrieval systems should be able to ask diverse questions, such as information-seeking, clarification, and open-ended ones. question generation (QG) of open-domain conversational systems aims at enhancing the interactiveness and persistence of human-machine interactions. The task is challenging because of the sparsity of question generation (QG)-specific data in conversations. Current work is limited to single-turn interaction scenarios. We propose a context-enhanced neural question generation (CNQG) model that leverages the conversational context to predict question content and pattern, then perform question decoding. A hierarchical encoder framework is employed to obtain the discourse-level context representation. Based on this, we propose Review and Transit mechanisms to respectively select contextual keywords and predict new topic words to further construct the question content. Conversational context and the predicted question content are used to produce the question pattern, which in turn guides the question decoding process implemented by a recurrent decoder with a joint attention mechanism. To fully utilize the limited QG-specific data to train our question generator, we perform multi-task learning with three auxiliary training objectives, i.e., question pattern prediction, Review , and Transit mechanisms. The required additional labeled data is obtained in a self-supervised way. We also design a weight decaying strategy to adjust the influences of various auxiliary learning tasks. To the best of our acknowledge, we are the first to extend the application of QG to the multi-turn open-domain conversational scenario. Extensive experimental results demonstrate the effectiveness of our proposal and its main components on generating relevant and informative questions, with robust performance for contexts with various lengths.

Event representation targets to model the event-reasoning process as a machine-readable format. Previous studies on event representation mostly concentrate on a sole modeling perspective and have not well investigated the scenario-level knowledge, which can cause information loss. To cope with this dilemma, we propose a unified fine-tuning architecture-based approach ( UniFA-S ) that integrates all levels of trainings, including the scenario-level knowledge. However, another challenge for existing models is the ever-increasing computation overheads, restricting the deployment ability on limited resources devices. Hence, in this article, we aim to compress the cumbersome model UniFA-S into a lighter and easy-to-deploy one without much performance damage. To this end, we propose a sequence-aware knowledge distillation model (SaKD) that employs a dynamic self-distillation on the decouple-compress-couple framework for compressing UniFA-S , which cannot only realize the model compression, but also retain the integrity of individual components. We also design two fitting strategies to address the less-supervised issue at the distillation stage. Comprehensive experiments on representation-and-inference ability-based tasks validate the effectiveness of SaKD. Compared to UniFA-S , SaKD realizes a more portable event representation model at the cost of only 1.0% performance drop in terms of accuracy or Spearman’s correlation, which is far less than other knowledge distillation models.

Session-based recommendation aims to generate recommendations merely based on the ongoing session, which is a challenging task. Previous methods mainly focus on modeling the sequential signals or the transition relations between items in the current session using RNNs or GNNs to identify user’s intent for recommendation. Such models generally ignore the dynamic connections between the local and global item transition patterns, although the global information is taken into consideration by exploiting the global-level pair-wise item transitions. Moreover, existing methods that mainly adopt the cross-entropy loss with softmax generally face a serious over-fitting problem, harming the recommendation accuracy. Thus, in this article, we propose a Graph Co-Attentive Recommendation Machine (GCARM) for session-based recommendation. In detail, we first design a Graph Co-Attention Network (GCAT) to consider the dynamic correlations between the local and global neighbors of each node during the information propagation. Then, the item-level dynamic connections between the output of the local and global graphs are modeled to generate the final item representations. After that, we produce the prediction scores and design a Max Cross-Entropy (MCE) loss to prevent over-fitting. Extensive experiments are conducted on three benchmark datasets, i.e., Diginetica, Gowalla, and Yoochoose. The experimental results show that GCARM can achieve the state-of-the-art performance in terms of Recall and MRR, especially on boosting the ranking of the target item.

Session-based recommendation (SBR) , which mainly relies on a user’s limited interactions with items to generate recommendations, is a widely investigated task. Existing methods often apply RNNs or GNNs to model user’s sequential behavior or transition relationship between items to capture her current preference. For training such models, the supervision signals are merely generated from the sequential interactions inside a session, neglecting the correlations of different sessions, which we argue can provide additional supervisions for learning the item representations. Moreover, previous methods mainly adopt the cross-entropy loss for training, where the user’s ground truth preference distribution towards items is regarded as a one-hot vector of the target item, easily making the network over-confident and leading to a serious overfitting problem. Thus, in this article, we propose a Collaborative Graph Learning (CGL) approach for session-based recommendation. CGL first applies the Gated Graph Neural Networks (GGNNs) to learn item embeddings and then is trained by considering both the main supervision as well as the self-supervision signals simultaneously. The main supervisions are produced by the sequential order while the self-supervisions are derived from the global graph constructed by all sessions. In addition, to prevent overfitting, we propose a Target-aware Label Confusion (TLC) learning method in the main supervised component. Extensive experiments are conducted on three publicly available datasets, i.e., Retailrocket, Diginetica, and Gowalla. The experimental results show that CGL can outperform the state-of-the-art baselines in terms of Recall and MRR.

Event detection classifies unlabeled sentences into event labels, which can benefit numerous applications, including information retrieval, question answering and script learning. One of the major obstacles to event detection in reality is insufficient training data. To deal with the low-resources problem, we investigate few-shot event detection in this paper and propose TaLeM, a novel taxonomy-aware learning model, consisting of two components, i.e., the taxonomy-aware self-supervised learning framework (TaSeLF) and the taxonomy-aware prototypical networks (TaPN). Specifically, TaSeLF mines the taxonomy-aware distance relations to increases the training examples, which alleviates the generalization bottleneck brought by the insufficient data. TaPN introduces the Poincaré embeddings to represent the label taxonomy, and integrates them into a task-adaptive projection networks, which tackles problems of the class centroids distribution and the taxonomy-aware embedding distribution in the vanilla prototypical networks.

This paper provides theoretical and practical implications for the application of agent-based models (ABMs) to address the issue of coevolutionary business-IS alignment. The implications stem from the following arguments: (a) the alignment issue can be modelled by an ABM to describe the features of complex adaptive systems (CAS); (b) the coevolutionary principles of business and IS alignment stipulate individual behaviours and guide organisational order; (c) ABM development and experimentation offer guidance to better explain how organisations control the alignment trajectory with coevolutionary principles. To extend the extant coevolutionary research on alignment, this paper develops an ABM for a hierarchical organisational structure and validates three coevolutionary principles.

Session-based recommendation is a challenging task. Without access to a user's historical user-item interactions, the information available in an ongoing session may be very limited. Previous work on session-based recommendation has considered sequences of items that users have interacted with sequentially. Such item sequences may not fully capture complex transition relationship between items that go beyond inspection order. Thus graph neural network (GNN) based models have been proposed to capture the transition relationship between items. However, GNNs typically propagate information from adjacent items only, thus neglecting information from items without direct connections. Importantly, GNN-based approaches often face serious overfitting problems. We propose Star Graph Neural Networks with Highway Networks (SGNN-HN) for session-based recommendation. The proposed SGNN-HN applies a star graph neural network (SGNN) to model the complex transition relationship between items in an ongoing session. To avoid overfitting, we employ highway networks (HN) to adaptively select embeddings from item representations. Finally, we aggregate the item embeddings generated by the SGNN in an ongoing session to represent a user's final preference for item prediction. Experiments on two public benchmark datasets show that SGNN-HN can outperform state-of-the-art models in terms of [email protected] and [email protected] for session-based recommendation.

Given an occurred event, human can easily predict the next event or reason the preceding event, yet which is difficult for machine to perform such event reasoning. Event representation bridges the connection and targets to model the process of event reasoning as a machine-readable format, which then can support a wide range of applications in information retrieval, e.g., question answering and information extraction. Existing work mainly resorts to a joint training to integrate all levels of training loss in event chains by a simple loss summation, which is easily trapped into a local optimum. In addition, the scenario knowledge in event chains is not well investigated for event representation. In this paper, we propose a unified fine-tuning architecture, incorporated with scenario knowledge for event representation, i.e., UniFA-S, which mainly consists of a unified fine-tuning architecture (UniFA) and a scenario-level variational auto-encoder (S-VAE). In detail, UniFA employs a multi-step fine-tuning to integrate all levels of training and S-VAE applies a stochastic variable to implicitly represent the scenario-level knowledge. We evaluate our proposal from two aspects, i.e., the representation and inference abilities. For the representation ability, our ensemble model UniFA-S can beat state-of-the-art baselines for two similarity tasks. For the inference ability, UniFA-S can outperform the best baseline, achieving 4.1%-8.2% improvements in terms of accuracy for various inference tasks.

Question generation in open-domain dialogue systems is a challenging but less-explored task. It aims to enhance the interactivity and persistence of human-machine interactions. Previous work mainly focuses on question generation in the setting of single-turn dialogues, or investigates it as a data augmentation method for machine comprehension. We propose a Context-augmented Neural Question Generation (CNQG) model that leverages the conversational context to generate questions for promoting interactivity and persistence of multi-turn dialogues. More specifically, we formulate the task of question generation as a two-stage process. First, we employ an encoder-decoder framework to predict a question pattern, which denotes a set of representative interrogatives, and identify the potential topics from the conversational context by employing point-wise mutual information. Then, we generate the question by decoding the concatenation of the current dialogue utterance, the pattern, and the topics with an attention mechanism. To the best of our knowledge, ours is the first work on question generation in multi-turn open-domain dialogue systems. Our experimental results on two publicly available multi-turn conversation datasets show that CNQG outperforms the state-of-the-art baselines in terms of BLEU-1, BLEU-2, Distinct-1 and Distinct-2. In addition, we find that CNQG allows one to efficiently distill useful features from long contexts, and maintain robust effectiveness even for short contexts.

Session-based recommendation is the task of recommending the next item a user might be interested in given partially known session information, e.g., part of a session or recent historical sessions. An effective session-based recommender should be able to exploit a user's evolving preferences, which we assume to be a mixture of her short- and long-term interests. Existing session-based recommendation methods often embed a user's long-term preference into a static representation, which plays a fixed role when dealing with her current short-term interests. This is problematic because long-term preferences may be more or less important for predicting the next conversion depending on the user's short-term interests. We propose a DCN-SR. DCN-SR applies a co-attention network to capture the dynamic interactions between the user's long- and short-term interaction behavior and generates co-dependent representations of the user's long- and short-term interests. For modeling a user's short-term interaction behavior, we design a CGRU network to take actions like "click'', "collect'' and "buy'' into account. Experiments on e-commerce datasets show significant improvements of DCN-SR over state-of-the-art session-based recommendation methods, with improvements of up to 2.58% on the Tmall dataset and 3.08% on the Tianchi dataset in terms of [email protected] [email protected] improvements are 3.78% and 4.05%, respectively. We also investigate the scalability and sensitivity of DCN-SR. The improvements of DCN-SR over state-of-the-art baselines are especially noticeable for short sessions and active users with many historical interactions.

Answer selection focuses on selecting the correct answer for a question. Most previous work on answer selection achieves good performance by employing an RNN, which processes all question and answer sentences with the same feature extractor regardless of the sentence length. These methods often encounter the problem of long-term dependencies. To address this issue, we propose a Length-adaptive Neural Network (LaNN) for answer selection that can auto-select a neural feature extractor according to the length of the input sentence. In particular, we propose a flexible neural structure that applies a BiLSTM-based feature extractor for short sentences and a Transformer-based feature extractor for long sentences. To the best of our knowledge, LaNN is the first neural network structure that can auto-select the feature extraction mechanism based on the input. We quantify the improvements of LaNN against several competitive baselines on the public WikiQA dataset, showing significant improvements over the state-of-the-art.

We propose a Joint Neural Collaborative Filtering (J-NCF) method for recommender systems. The J-NCF model applies a joint neural network that couples deep feature learning and deep interaction modeling with a rating matrix. Deep feature learning extracts feature representations of users and items with a deep learning architecture based on a user-item rating matrix. Deep interaction modeling captures non-linear user-item interactions with a deep neural network using the feature representations generated by the deep feature learning process as input. J-NCF enables the deep feature learning and deep interaction modeling processes to optimize each other through joint training, which leads to improved recommendation performance. In addition, we design a new loss function for optimization that takes both implicit and explicit feedback, point-wise and pair-wise loss into account. Experiments on several real-world datasets show significant improvements of J-NCF over state-of-the-art methods, with improvements of up to 8.24% on the MovieLens 100K dataset, 10.81% on the MovieLens 1M dataset, and 10.21% on the Amazon Movies dataset in terms of HR@10. NDCG@10 improvements are 12.42%, 14.24%, and 15.06%, respectively. We also conduct experiments to evaluate the scalability and sensitivity of J-NCF. Our experiments show that the J-NCF model has a competitive recommendation performance with inactive users and different degrees of data sparsity when compared to state-of-the-art baselines.

In previous work on text summarization, encoder-decoder architectures and attention mechanisms have both been widely used. Attention-based encoder-decoder approaches typically focus on taking the sentences preceding a given sentence in a document into account for document representation, failing to capture the relationships between a sentence and sentences that follow it in a document in the encoder. We propose an attentive encoder-based summarization (AES) model to generate article summaries. AES can generate a rich document representation by considering both the global information of a document and the relationships of sentences in the document. A unidirectional recurrent neural network (RNN) and a bidirectional RNN are considered to construct the encoders, giving rise to unidirectional attentive encoder-based summarization (Uni-AES) and bidirectional attentive encoder-based summarization (Bi-AES), respectively. Our experimental results show that Bi-AES outperforms Uni-AES. We obtain substantial improvements over a relevant start-of-the-art baseline.

Query suggestions help users of a search engine to refine their queries. Previous work on query suggestion has mainly focused on incorporating directly observable features such as query co-occurrence and semantic similarity. The structure of such features is often set manually, as a result of which hidden dependencies between queries and users may be ignored. We propose an AHNQS model that combines a hierarchical structure with a session-level neural network and a user-level neural network to model the short- and long-term search history of a user. An attention mechanism is used to capture user preferences. We quantify the improvements of AHNQS over state-of-the-art RNN-based query suggestion baselines on the AOL query log dataset, with improvements of up to 21.86% and 22.99% in terms of [email protected] and [email protected], respectively, over the state-of-the-art; improvements are especially large for short sessions.

Query suggestions help users refine their queries after they input an initial query. We consider the task of generating query suggestions that are personalized and diversified. We propose a personalized query suggestion diversification model (PQSD), where a user's long-term search behavior is injected into a basic greedy query suggestion diversification model (G-QSD) that considers a user's search context in their current session. Query aspects are identified through clicked documents based on the Open Directory Project (ODP). We quantify the improvement of PQSD over a state-of-the-art baseline using the AOL query log and show that it beats the baseline in terms of metrics used in query suggestion ranking and diversification. The experimental results show that PQSD achieves the best performance when only queries with clicked documents are taken as search context rather than all queries.

A Bloom filter is an effective, space-efficient data structure for concisely representing a set, and supporting approximate membership queries. Traditionally, the Bloom filter and its variants just focus on how to represent a static set and decrease the false positive probability to a sufficiently low level. By investigating mainstream applications based on the Bloom filter, we reveal that dynamic data sets are more common and important than static sets. However, existing variants of the Bloom filter cannot support dynamic data sets well. To address this issue, we propose dynamic Bloom filters to represent dynamic sets, as well as static sets and design necessary item insertion, membership query, item deletion, and filter union algorithms. The dynamic Bloom filter can control the false positive probability at a low level by expanding its capacity as the set cardinality increases. Through comprehensive mathematical analysis, we show that the dynamic Bloom filter uses less expected memory than the Bloom filter when representing dynamic sets with an upper bound on set cardinality, and also that the dynamic Bloom filter is more stable than the Bloom filter due to infrequent reconstruction when addressing dynamic sets without an upper bound on set cardinality. Moreover, the analysis results hold in stand-alone applications, as well as distributed applications.