Yan Fu

Weilian Song, Jieliang Luo, Dale Zhao et al.

This paper proposes an assistive system for architects that converts a large-scale point cloud into a standardized digital representation of a building for Building Information Modeling (BIM) applications. The process is known as Scan-to-BIM, which requires many hours of manual work even for a single building floor by a professional architect. Given its challenging nature, the paper focuses on helping architects on the Scan-to-BIM process, instead of replacing them. Concretely, we propose an assistive Scan-to-BIM system that takes the raw sensor data and edit history (including the current BIM model), then auto-regressively predicts a sequence of model editing operations as APIs of a professional BIM software (i.e., Autodesk Revit). The paper also presents the first building-scale Scan2BIM dataset that contains a sequence of model editing operations as the APIs of Autodesk Revit. The dataset contains 89 hours of Scan2BIM modeling processes by professional architects over 16 scenes, spanning over 35,000 m^2. We report our system's reconstruction quality with standard metrics, and we introduce a novel metric that measures how natural the order of reconstructed operations is. A simple modification to the reconstruction module helps improve performance, and our method is far superior to two other baselines in the order metric. We will release data, code, and models at a-scan2bim.github.io.

Guanlin Liu, Anand Ramachandran, Tanmay Gangwani et al.

Knowledge distillation is used, in generative language modeling, to train a smaller student model using the help of a larger teacher model, resulting in improved capabilities for the student model. In this paper, we formulate a more general framework for knowledge distillation where the student learns from the teacher during training, and also learns to ask for the teacher's help at test-time following rules specifying test-time restrictions. Towards this, we first formulate knowledge distillation as an entropy-regularized value optimization problem. Adopting Path Consistency Learning to solve this, leads to a new knowledge distillation algorithm using on-policy and off-policy demonstrations. We extend this using constrained reinforcement learning to a framework that incorporates the use of the teacher model as a test-time reference, within constraints. In this situation, akin to a human learner, the model needs to learn not only the learning material, but also the relative difficulty of different sections to prioritize for seeking teacher help. We examine the efficacy of our method through experiments in translation and summarization tasks, observing trends in accuracy and teacher use, noting that our approach unlocks operating points not available to the popular Speculative Decoding approach.

Yingying Sun, Jun A, Zhiwei Liu et al.

Artificial intelligence (AI) is transforming scientific research, including proteomics. Advances in mass spectrometry (MS)-based proteomics data quality, diversity, and scale, combined with groundbreaking AI techniques, are unlocking new challenges and opportunities in biological discovery. Here, we highlight key areas where AI is driving innovation, from data analysis to new biological insights. These include developing an AI-friendly ecosystem for proteomics data generation, sharing, and analysis; improving peptide and protein identification and quantification; characterizing protein-protein interactions and protein complexes; advancing spatial and perturbation proteomics; integrating multi-omics data; and ultimately enabling AI-empowered virtual cells.

Ai Chen, Yuxu Lu, Dong Yang et al.

Salient object detection (SOD) plays a critical role in Intelligent Imaging, facilitating the detection and segmentation of key visual elements in an image. However, adverse imaging conditions such as haze during the day, low light, and haze at night severely degrade image quality and hinder reliable object detection in real-world scenarios. To address these challenges, we propose a multi-knowledge-oriented nighttime haze imaging enhancer (MKoIE), which integrates three tasks: daytime dehazing, low-light enhancement, and nighttime dehazing. The MKoIE incorporates two key innovative components: First, the network employs a task-oriented node learning mechanism to handle three specific degradation types: day-time haze, low light, and night-time haze conditions, with an embedded self-attention module enhancing its performance in nighttime imaging. In addition, multi-receptive field enhancement module that efficiently extracts multi-scale features through three parallel depthwise separable convolution branches with different dilation rates, capturing comprehensive spatial information with minimal computational overhead to meet the requirements of real-time imaging deployment. To ensure optimal image reconstruction quality and visual characteristics, we suggest a hybrid loss function. Extensive experiments on different types of weather/imaging conditions illustrate that MKoIE surpasses existing methods, enhancing the reliability, accuracy, and operational efficiency of intelligent imaging.

Kuan-Chieh Wang, Yan Fu, Ke Li et al.

Given the ubiquity of deep neural networks, it is important that these models do not reveal information about sensitive data that they have been trained on. In model inversion attacks, a malicious user attempts to recover the private dataset used to train a supervised neural network. A successful model inversion attack should generate realistic and diverse samples that accurately describe each of the classes in the private dataset. In this work, we provide a probabilistic interpretation of model inversion attacks, and formulate a variational objective that accounts for both diversity and accuracy. In order to optimize this variational objective, we choose a variational family defined in the code space of a deep generative model, trained on a public auxiliary dataset that shares some structural similarity with the target dataset. Empirically, our method substantially improves performance in terms of target attack accuracy, sample realism, and diversity on datasets of faces and chest X-ray images.

Enyu Yu, Duanbing Chen, Yan Fu et al.

Because of its wide application, critical nodes identification has become an important research topic at the micro level of network science. Influence maximization is one of the main problems in critical nodes mining and is usually handled with heuristics. In this paper, a deep graph learning framework IMGNN is proposed and the corresponding training sample generation scheme is designed. The framework takes centralities of nodes in a network as input and the probability that nodes in the optimal initial spreaders as output. By training on a large number of small synthetic networks, IMGNN is more efficient than human-based heuristics in minimizing the size of initial spreaders under the fixed infection scale. The experimental results on one synthetic and five real networks show that, compared with traditional non-iterative node ranking algorithms, IMGNN has the smallest proportion of initial spreaders under different infection probabilities when the final infection scale is fixed. And the reordered version of IMGNN outperforms all the latest critical nodes mining algorithms.

Zhouyang Xie, Yan Fu, Shengzhao Tian et al.

Channel pruning is a promising technique to compress the parameters of deep convolutional neural networks(DCNN) and to speed up the inference. This paper aims to address the long-standing inefficiency of channel pruning. Most channel pruning methods recover the prediction accuracy by re-training the pruned model from the remaining parameters or random initialization. This re-training process is heavily dependent on the sufficiency of computational resources, training data, and human interference(tuning the training strategy). In this paper, a highly efficient pruning method is proposed to significantly reduce the cost of pruning DCNN. The main contributions of our method include: 1) pruning compensation, a fast and data-efficient substitute of re-training to minimize the post-pruning reconstruction loss of features, 2) compensation-aware pruning(CaP), a novel pruning algorithm to remove redundant or less-weighted channels by minimizing the loss of information, and 3) binary structural search with step constraint to minimize human interference. On benchmarks including CIFAR-10/100 and ImageNet, our method shows competitive pruning performance among the state-of-the-art retraining-based pruning methods and, more importantly, reduces the processing time by 95% and data usage by 90%.

En-Yu Yu, Yan Fu, Jun-Lin Zhou et al.

Many real-world systems can be expressed in temporal networks with nodes playing far different roles in structure and function and edges representing the relationships between nodes. Identifying critical nodes can help us control the spread of public opinions or epidemics, predict leading figures in academia, conduct advertisements for various commodities, and so on. However, it is rather difficult to identify critical nodes because the network structure changes over time in temporal networks. In this paper, considering the sequence topological information of temporal networks, a novel and effective learning framework based on the combination of special GCNs and RNNs is proposed to identify nodes with the best spreading ability. The effectiveness of the approach is evaluated by weighted Susceptible-Infected-Recovered model. Experimental results on four real-world temporal networks demonstrate that the proposed method outperforms both traditional and deep learning benchmark methods in terms of the Kendall $τ$ coefficient and top $k$ hit rate.

Faez Ahmed, Yaxin Cui, Yan Fu et al.

Graph Neural Networks have revolutionized many machine learning tasks in recent years, ranging from drug discovery, recommendation systems, image classification, social network analysis to natural language understanding. This paper shows their efficacy in modeling relationships between products and making predictions for unseen product networks. By representing products as nodes and their relationships as edges of a graph, we show how an inductive graph neural network approach, named GraphSAGE, can efficiently learn continuous representations for nodes and edges. These representations also capture product feature information such as price, brand, or engineering attributes. They are combined with a classification model for predicting the existence of the relationship between products. Using a case study of the Chinese car market, we find that our method yields double the prediction performance compared to an Exponential Random Graph Model-based method for predicting the co-consideration relationship between cars. While a vanilla GraphSAGE requires a partial network to make predictions, we introduce an `adjacency prediction model' to circumvent this limitation. This enables us to predict product relationships when no neighborhood information is known. Finally, we demonstrate how a permutation-based interpretability analysis can provide insights on how design attributes impact the predictions of relationships between products. This work provides a systematic method to predict the relationships between products in many different markets.

Fei Yuan, Linjun Shou, Jian Pei et al.

In natural language processing (NLP) tasks, slow inference speed and huge footprints in GPU usage remain the bottleneck of applying pre-trained deep models in production. As a popular method for model compression, knowledge distillation transfers knowledge from one or multiple large (teacher) models to a small (student) model. When multiple teacher models are available in distillation, the state-of-the-art methods assign a fixed weight to a teacher model in the whole distillation. Furthermore, most of the existing methods allocate an equal weight to every teacher model. In this paper, we observe that, due to the complexity of training examples and the differences in student model capability, learning differentially from teacher models can lead to better performance of student models distilled. We systematically develop a reinforced method to dynamically assign weights to teacher models for different training instances and optimize the performance of student model. Our extensive experimental results on several NLP tasks clearly verify the feasibility and effectiveness of our approach.

Po Li, Lei Li, Yan Fu et al.

In this paper, we introduce Cross-modal Alignment with mixture experts Neural Network (CameNN) recommendation model for intral-city retail industry, which aims to provide fresh foods and groceries retailing within 5 hours delivery service arising for the outbreak of Coronavirus disease (COVID-19) pandemic around the world. We propose CameNN, which is a multi-task model with three tasks including Image to Text Alignment (ITA) task, Text to Image Alignment (TIA) task and CVR prediction task. We use pre-trained BERT to generate the text embedding and pre-trained InceptionV4 to generate image patch embedding (each image is split into small patches with the same pixels and treat each patch as an image token). Softmax gating networks follow to learn the weight of each transformer expert output and choose only a subset of experts conditioned on the input. Then transformer encoder is applied as the share-bottom layer to learn all input features' shared interaction. Next, mixture of transformer experts (MoE) layer is implemented to model different aspects of tasks. At top of the MoE layer, we deploy a transformer layer for each task as task tower to learn task-specific information. On the real word intra-city dataset, experiments demonstrate CameNN outperform baselines and achieve significant improvements on the image and text representation. In practice, we applied CameNN on CVR prediction in our intra-city recommender system which is one of the leading intra-city platforms operated in China.

Ya-Hui An, Muthu Kumar Chandresekaran, Min-Yen Kan et al.

New learning resources are created and minted in Massive Open Online Courses every week -- new videos, quizzes, assessments and discussion threads are deployed and interacted with -- in the era of on-demand online learning. However, these resources are often artificially siloed between platforms and artificial web application models. Facilitating the linking between such resources facilitates learning and multimodal understanding, bettering learners' experience. We create a framework for MOOC Uniform Identifier for Resources (MUIR). MUIR enables applications to refer and link to such resources in a cross-platform way, allowing the easy minting of identifiers to MOOC resources, akin to #hashtags. We demonstrate the feasibility of this approach to the automatic identification, linking and resolution -- a task known as Wikification -- of learning resources mentioned on MOOC discussion forums, from a harvested collection of 100K+ resources. Our Wikification system achieves a high initial rate of 54.6% successful resolutions on key resource mentions found in discussion forums, demonstrating the utility of the MUIR framework. Our analysis on this new problem shows that context is a key factor in determining the correct resolution of such mentions.

Fei Yuan, Linjun Shou, Xuanyu Bai et al.

Multilingual pre-trained models could leverage the training data from a rich source language (such as English) to improve performance on low resource languages. However, the transfer quality for multilingual Machine Reading Comprehension (MRC) is significantly worse than sentence classification tasks mainly due to the requirement of MRC to detect the word level answer boundary. In this paper, we propose two auxiliary tasks in the fine-tuning stage to create additional phrase boundary supervision: (1) A mixed MRC task, which translates the question or passage to other languages and builds cross-lingual question-passage pairs; (2) A language-agnostic knowledge masking task by leveraging knowledge phrases mined from web. Besides, extensive experiments on two cross-lingual MRC datasets show the effectiveness of our proposed approach.

Ya-Hui An, Liangming Pan, Min-Yen Kan et al.

In discussions hosted on discussion forums for MOOCs, references to online learning resources are often of central importance. They contextualize the discussion, anchoring the discussion participants' presentation of the issues and their understanding. However they are usually mentioned in free text, without appropriate hyperlinking to their associated resource. Automated learning resource mention hyperlinking and categorization will facilitate discussion and searching within MOOC forums, and also benefit the contextualization of such resources across disparate views. We propose the novel problem of learning resource mention identification in MOOC forums. As this is a novel task with no publicly available data, we first contribute a large-scale labeled dataset, dubbed the Forum Resource Mention (FoRM) dataset, to facilitate our current research and future research on this task. We then formulate this task as a sequence tagging problem and investigate solution architectures to address the problem. Importantly, we identify two major challenges that hinder the application of sequence tagging models to the task: (1) the diversity of resource mention expression, and (2) long-range contextual dependencies. We address these challenges by incorporating character-level and thread context information into a LSTM-CRF model. First, we incorporate a character encoder to address the out-of-vocabulary problem caused by the diversity of mention expressions. Second, to address the context dependency challenge, we encode thread contexts using an RNN-based context encoder, and apply the attention mechanism to selectively leverage useful context information during sequence tagging. Experiments on FoRM show that the proposed method improves the baseline deep sequence tagging models notably, significantly bettering performance on instances that exemplify the two challenges.

Ya-Hui An, Qiang Dong, Chong-Jing Sun et al.

In last decades, diversity and accuracy have been regarded as two important measures in evaluating a recommendation model. However, a clear concern is that a model focusing excessively on one measure will put the other one at risk, thus it is not easy to greatly improve diversity and accuracy simultaneously. In this paper, we propose to enhance the Resource-Allocation (RA) similarity in resource transfer equations of diffusion-like models, by giving a tunable exponent to the RA similarity, and traversing the value of the exponent to achieve the optimal recommendation results. In this way, we can increase the recommendation scores (allocated resource) of many unpopular objects. Experiments on three benchmark data sets, MovieLens, Netflix, and RateYourMusic show that the modified models can yield remarkable performance improvement compared with the original ones.

Da-Cheng Nie, Ya-Hui An, Qiang Dong et al.

Recent decade has witnessed the increasing popularity of recommender systems, which help users acquire relevant commodities and services from overwhelming resources on Internet. Some simple physical diffusion processes have been used to design effective recommendation algorithms for user-object bipartite networks, typically mass diffusion (MD) and heat conduction (HC) algorithms which have different advantages respectively on accuracy and diversity. In this paper, we investigate the effect of weight assignment in the hybrid of MD and HC, and find that a new hybrid algorithm of MD and HC with balanced weights will achieve the optimal recommendation results, we name it balanced diffusion (BD) algorithm. Numerical experiments on three benchmark data sets, MovieLens, Netflix and RateYourMusic (RYM), show that the performance of BD algorithm outperforms the existing diffusion-based methods on the three important recommendation metrics, accuracy, diversity and novelty. Specifically, it can not only provide accurately recommendation results, but also yield higher diversity and novelty in recommendations by accurately recommending unpopular objects.

Chongjing Sun, Philip S. Yu, Xiangnan Kong et al.

Publishing social network data for research purposes has raised serious concerns for individual privacy. There exist many privacy-preserving works that can deal with different attack models. In this paper, we introduce a novel privacy attack model and refer it as a mutual friend attack. In this model, the adversary can re-identify a pair of friends by using their number of mutual friends. To address this issue, we propose a new anonymity concept, called k-NMF anonymity, i.e., k-anonymity on the number of mutual friends, which ensures that there exist at least k-1 other friend pairs in the graph that share the same number of mutual friends. We devise algorithms to achieve the k-NMF anonymity while preserving the original vertex set in the sense that we allow the occasional addition but no deletion of vertices. Further we give an algorithm to ensure the k-degree anonymity in addition to the k-NMF anonymity. The experimental results on real-word datasets demonstrate that our approach can preserve the privacy and utility of social networks effectively against mutual friend attacks.