{"title":"ChiQA","authors":"Bingning Wang, Feiyang Lv, Ting Yao, Jin Ma, Yu Luo, Haijin Liang","doi":"10.1145/3511808.3557258","DOIUrl":"https://doi.org/10.1145/3511808.3557258","url":null,"abstract":"Visual question answering is an important task in both natural language and vision understanding. However, in most of the public visual question answering datasets such as VQA, CLEVR, the questions are human generated that specific to the given image, such as 'What color are her eyes?'. The human generated crowdsourcing questions are relatively simple and sometimes have the bias toward certain entities or attributes [1, 55]. In this paper, we introduce a new question answering dataset based on image-ChiQA. It contains the real-world queries issued by internet users, combined with several related open-domain images. The system should determine whether the image could answer the question or not. Different from previous VQA datasets, the questions are real-world image-independent queries that are more various and unbiased. Compared with previous image-retrieval or image-caption datasets, the ChiQA not only measures the relatedness but also measures the answerability, which demands more fine-grained vision and language reasoning. ChiQA contains more than 40K questions and more than 200K question-images pairs. A three-level 2/1/0 label is assigned to each pair indicating perfect answer, partially answer and irrelevant. Data analysis shows ChiQA requires a deep understanding of both language and vision, including grounding, comparisons, and reading. We evaluate several state-of-the-art visual-language models such as ALBEF, demonstrating that there is still a large room for improvements on ChiQA.","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128475345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yili Wang, Kaixiong Zhou, Rui Miao, Ninghao Liu, X. Wang
{"title":"AdaGCL","authors":"Yili Wang, Kaixiong Zhou, Rui Miao, Ninghao Liu, X. Wang","doi":"10.1145/3511808.3557228","DOIUrl":"https://doi.org/10.1145/3511808.3557228","url":null,"abstract":"Training graph neural networks (GNNs) with good generalizability on large-scale graphs is a challenging problem. Existing methods mainly divide the input graph into multiple subgraphs and train them in different batches to improve training scalability. However, the local batches obtained by such a strategy could contain topological bias compared with the complete graph structure. It has been studied that the topological bias results in more significant gaps between training and testing performances, or worse generalization robustness. A straightforward solution is to utilize contrastive learning, and train node embeddings to be robust and invariant among the augmented imperfect graphs. However, most of the existing work are inefficient by contrasting extensive node pairs at the large-scale graph. With random data augmentation, they may deteriorate the embedding process by transforming well-sampled batches into meaningless graph structures. To bridge the gap between large-scale graph training and contrastive learning, we propose adaptive subgraph contrastive learning (AdaGCL). Given a batch of sampled subgraphs, we propose subgraph-granularity contrastive loss to compare the anchor node with a limited number of subgraphs, which reduces the computation cost. AdaGCL tailors two key components for batch training: (1) Batch-aware view generation to keep the intrinsic individual subgraph structures of batch to learn the informative node embeddings; (2) Batch-aware pair sampling to construct the positive and negative contrasting subgraphs based on anchor node label. Experiments show that AdaGCL can scale up to graphs with millions of nodes, and delivers the consistent improvement than the existing methods on various benchmark datasets. Furthermore, AdaGCL has comparable running time with the state-of-the-art contrastive learning methods that focus on improving efficiency. Finally, ablation studies of the two components of AdaGCL demonstrate their effectiveness to generalize the batch training. The code is in: https://github.com/YL-wang/CIKM_AdaGCL/.","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"191 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114966664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiandong Xie, Yue Cui, Feiteng Huang, Chao Liu, Kai Zheng
{"title":"MARINA","authors":"Jiandong Xie, Yue Cui, Feiteng Huang, Chao Liu, Kai Zheng","doi":"10.1145/3511808.3557386","DOIUrl":"https://doi.org/10.1145/3511808.3557386","url":null,"abstract":"The proliferation of real-time monitoring applications such as Artificial Intelligence for IT Operations (AIOps) and the Internet of Things (IoT) has led to the generation of a vast amount of time-series data. To extract the underlying value of the data, both the industry and the academia are in dire need of efficient and effective methods for time-series analysis. To this end, in this paper, we propose a Multi-layer perceptron (MLP)-attention based multivariate time-series analysis model MARINA. MARINA is designed to simultaneously learn the temporal and spatial correlations among multivariate time-series. Also, the model is versatile in that it is suitable for major time-series analysis tasks such as forecasting and anomaly detection. Through extensive comparisons with the representative multivariate time-series forecasting and anomaly detection algorithms, MARINA is shown to achieve state-of-the-art (SOTA) performance in both forecasting and anomaly detection tasks.","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130470795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"RSD","authors":"Houxing Ren, Jingyuan Wang, Wayne Xin Zhao","doi":"10.1007/3-540-29662-x_2363","DOIUrl":"https://doi.org/10.1007/3-540-29662-x_2363","url":null,"abstract":"","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114956748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Chenglong Ma, Yongli Ren, Pablo Castells, M. Sanderson
{"title":"NEST","authors":"Chenglong Ma, Yongli Ren, Pablo Castells, M. Sanderson","doi":"10.1145/3511808.3557407","DOIUrl":"https://doi.org/10.1145/3511808.3557407","url":null,"abstract":"We outline a simulation-based study of the effect rapid population-scale concept drifts have on Collaborative Filtering (CF) models. We create a framework for analyzing the effects of macro-trends in population dynamics on the behavior of such models. Our framework characterizes population-scale concept drifts in item preferences and provides a lens to understand the influence events, such as a pandemic, have on CF models. Our experimental results show the initial impact on CF performance at the initial stage of such events, followed by an aggravated population herding effect during the event. The herding introduces a popularity bias that may benefit affected users, but which comes at the expense of a normal user experience. We propose an adaptive ensemble method that can effectively apply optimal algorithms to cope with the change brought about by different stages of the event.","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123940310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shuai Guo, Yang Gu, Shijie Wen, Yuan Ma, Yiqiang Chen, Jiwei Wang, Chunyu Hu
{"title":"KiCi","authors":"Shuai Guo, Yang Gu, Shijie Wen, Yuan Ma, Yiqiang Chen, Jiwei Wang, Chunyu Hu","doi":"10.1145/3511808.3557371","DOIUrl":"https://doi.org/10.1145/3511808.3557371","url":null,"abstract":"Wearable-based human activity recognition (HAR) is commonly employed in real-world scenarios such as health monitoring, auxiliary diagnosis, etc. As implementing activity recognition is a daunting challenge in an open dynamic environment, incremental learning has become a common method to adapt to variable behavior patterns of users and create dynamic modeling in activity recognition. However, catastrophic forgetting is a significant challenge with incremental learning. This is contrary to our expectations of identifying new activity classes while remembering existing ones. To address this problem, we propose a knowledge importance-based class incremental learning method called KiCi and construct an incremental learning model based on the framework of self-iterative knowledge distillation for dynamic activity recognition. To eliminate the prediction bias of the teacher model on the old knowledge, we utilize the trained weights of previous incremental steps generated by the teacher model as the prior knowledge to obtain knowledge importance. Then use it to make the student model have a reasonable trade-off between old and new knowledge and mitigate catastrophic forgetting by avoiding negative transfer. We conduct extensive experiments on four public HAR datasets and our method consistently outperforms the existing state-of-the-art methods by a large margin.","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"249 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130556678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"GCWSNet","authors":"Ping Li, Weijie Zhao","doi":"10.1145/3511808.3557332","DOIUrl":"https://doi.org/10.1145/3511808.3557332","url":null,"abstract":"We propose using \"powered generalized min-max'' (pGMM) hashed (linearized) via the \"generalized consistent weighted sampling'' (GCWS) for training (deep) neural networks (hence the name \"GCWSNet''). The pGMM and several related kernels were proposed in 2017. We demonstrate that pGMM hashed by GCWS provide a numerically stable scheme for applying power transformation on the original data, regardless of the magnitude of p and the data. Our experiments show that GCWSNet often improves the accuracy. It is also evident that GCWSNet converges substantially faster, reaching reasonable accuracy with merely one epoch of the training process. This property is much desired because many applications, such as advertisement click-through rate (CTR) prediction models, or data streams (i.e., data seen only once), often train just one epoch. Another beneficial side effect is that the computations of the first layer of the neural networks become additions instead of multiplications because the input data become binary and highly sparse. Empirical comparisons with (normalized) random Fourier features (NRFF) are provided. We also propose to reduce the model size of GCWSNet by count-sketch and develop the theory for analyzing the impact of using count-sketch on the accuracy of GCWS. Our analysis shows that an \"8-bit'' strategy should provide the good trade-off between accuracy and model size. There are other ways to take advantage of GCWS. For example, one can apply GCWS on the last layer to boost the accuracy of trained deep neural nets.","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124773978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Taeri Kim, Yeon-Chang Lee, Kijung Shin, Sang-Wook Kim
{"title":"MARIO","authors":"Taeri Kim, Yeon-Chang Lee, Kijung Shin, Sang-Wook Kim","doi":"10.1145/3511808.3557387","DOIUrl":"https://doi.org/10.1145/3511808.3557387","url":null,"abstract":"We address the multimedia recommendation problem, which utilizes items' multimodal features, such as visual and textual modalities, in addition to interaction information. While a number of existing multimedia recommender systems have been developed for this problem, we point out that none of these methods individually capture the influence of each modality at the interaction level. More importantly, we experimentally observe that the learning procedures of existing works fail to preserve the intrinsic modality-specific properties of items. To address above limitations, we propose an accurate multimedia recommendation framework, named MARIO, based on modality-aware attention and modality-preserving decoders. MARIO predicts users' preferences by considering the individual influence of each modality on each interaction while obtaining item embeddings that preserve the intrinsic modality-specific properties. The experiments on four real-life datasets demonstrate that MARIO consistently and significantly outperforms seven competitors in terms of the recommendation accuracy: MARIO yields up to 14.61% higher accuracy, compared to the best competitor.","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115075406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shuncheng Liu, Xu Chen, Ziniu Wu, Liwei Deng, Han Su, Kai Zheng
{"title":"HeGA","authors":"Shuncheng Liu, Xu Chen, Ziniu Wu, Liwei Deng, Han Su, Kai Zheng","doi":"10.1145/3511808.3557345","DOIUrl":"https://doi.org/10.1145/3511808.3557345","url":null,"abstract":"Trajectory prediction enables the fast and accurate response of autonomous driving navigation in complex and dense traffics. In this paper, we present a novel trajectory prediction network called Heterogeneous Graph Aggregation (HeGA) for high-density heterogeneous traffic, where the traffic agents of various categories interact densely with each other. To predict the trajectory of a target agent, HeGA first automatically selects neighbors that interact with it by our proposed adaptive neighbor selector, and then aggregates their interactions based on a novel two-phase aggregation transformer block. At last, the historical residual connection LSTM enhances the historical information awareness and decodes the spatial coordinates as the prediction results. Extensive experiments on real data demonstrate that the proposed network significantly outperforms the existing state-of-the-art competitors by over 27% on average displacement error (ADE) and over 31% on final displacement error (FDE). We also deploy HeGA in a state-of-the-art framework for autonomous driving, demonstrating its superior applicability based on three simulated environments with different densities and complexities.","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122512100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wu Meihan, Li Li, Chang Tao, Eric Rigall, Wang Xiaodong, Xu Cheng-Zhong
{"title":"FedCDR","authors":"Wu Meihan, Li Li, Chang Tao, Eric Rigall, Wang Xiaodong, Xu Cheng-Zhong","doi":"10.1145/3511808.3557320","DOIUrl":"https://doi.org/10.1145/3511808.3557320","url":null,"abstract":"The cold-start problem, faced when providing recommendations to newly joined users with no historical interaction record existing in the platform, is one of the most critical problems that negatively impact the performance of a recommendation system. Fortunately, cross-domain recommendation~(CDR) is a promising approach for solving this problem, which can exploit the knowledge of these users from source domains to provide recommendations in the target domain. However, this method requires that the central server has the interaction behaviour data in both domains of all the users, which prevents users from participating due to privacy issues. In this work, we propose FedCDR, a federated learning based cross-domain recommendation system that effectively trains the recommendation model while keeping users' raw data and private user-specific parameters located on their own devices. Unlike existing CDR models, a personal module and a transfer module are designed to adapt to the extremely heterogeneous data on the participating devices. Specifically, the personal module extracts private user features for each user, while the transfer module is responsible for transferring the knowledge between the two domains. Moreover, in order to provide personalized recommendations with less storage and communication costs while effectively protecting privacy, we design a personalized update strategy for each client and a personalized aggregation strategy for the server. In addition, we conduct comprehensive experiments on the representative Amazon 5-cores datasets for three popular rating prediction tasks to evaluate the effectiveness of FedCDR. The results show that FedCDR outperforms the state-of-the-art methods in mean absolute error (MAE) and root mean squared error (RMSE). For example, in task Movie&Music, FedCDR can effectively improve the performance up to 65.83% and 55.45% on MAE and RMSE, respectively, when the new users are in the movie domain.","PeriodicalId":441107,"journal":{"name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","volume":"310 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123148088","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}