Visual emergence is the phenomenon in which the visual system obtains a holistic perception after grouping and reorganizing local signals. The picture Dalmatian dog is known for its use in explaining visual emergence. This type of image, which consists of a set of discrete black speckles, is called an emerging image. Although Gestalt theory summarizes perceptual organization into several principles, it remains ambiguous how these principles affect the perception of emerging images. This study, therefore, designed three psychological experiments to explore the factors that influence the perception of emerging images. In the first, we found that the density of speckles in the local area and the arrangements of some key speckles played a key role in the perception of an emerging case. We set parameters in the algorithm to characterize these two factors. We then automatically generated emerging-test images through the algorithm and verified their effectiveness in two subsequent experiments.


Important Clues that Facilitate Visual Emergence: Three Psychological Experiments

Coupled dynamical systems, especially those comprised of hysteretic elements, possess remarkable behavioral similarities to some aspects of neural activity in living systems. While some features of this similarity have been explored, the results have not yet been leveraged to improve machine learning techniques or artificial neural networks. In this work, a dynamical system of coupled overdamped bistable elements subject to a noise floor assists in information transfer. With the noise allowing the system elements to switch randomly between their stable states, the system response is quantified via a steady state probability distribution. A simple five element realization of this network is used to produce the analog equivalent of an XOR gate, an “XOR transform”, through the proper choice of coupling coefficients and controllable external biases. The demonstration of the XOR transform indicates the ability of the system to synthesize more general functions, a necessary prerequisite for machine learning and computing applications. Finally, a silicon implementation is proposed and simulated using a verified process model that could be fabricated to generate a working analog computing system.

Noise Driven Coupled Dynamic Systems–Towards Low Power Pattern Recognition and Machine Learning

Recommender systems now consume large-scale data and play a significant role in improving user experience. Graph Neural Networks (GNNs) have emerged as one of the most effective recommender system models because they model the rich relational information. The ever-growing volume of data can make training GNNs prohibitively expensive. To address this, previous attempts propose to train the GNN models incrementally as new data blocks arrive. 
Feature and structure knowledge distillation techniques have been explored to allow the GNN model to train in a fast incremental fashion while alleviating the catastrophic forgetting problem. 
However, fully preserving the historical information for all users is sub-optimal since it fails to take into account the dynamics of each user's change of preferences. 
For the users whose interests shift substantially, retaining too much of the old knowledge can overly constrain the model, preventing it from quickly adapting to the users’ novel interests. 
In contrast, for users who have static preferences, model performance can benefit greatly from preserving as much of the user's long-term preferences as possible.
In this work, we propose a novel training strategy that adaptively learns personalized imitation weights for each user to balance the contribution from the recent data and the amount of knowledge to be distilled from previous time periods.
We demonstrate the effectiveness of learning imitation weights via a comparison on five diverse datasets for three state-of-art structure distillation-based recommender systems. The performance shows consistent improvement over competitive incremental learning techniques. We make our code available \url{https://anonymous.4open.science/r/SAIL-PIW-22BD}.

Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems

Cross-domain recommendation (CDR) aims to alleviate the data sparsity by transferring knowledge from an informative source domain to the target domain, which inevitably proposes the stern challenges to data privacy and transferability during the transfer process. A small amount of recent CDR works have investigated the privacy protection, while they still suffer from satisfying practical requirements (e.g., limited privacy-preserving ability) and preventing the potential risk of negative transfer. To address above challenging problems, we propose a novel and unified privacy-preserving federated framework for dual-target CDR, namely P2FCDR. We design P2FCDR as peer-to-peer federated network architecture to ensure the local data storage and privacy protection of business partners. Specifically, for the special knowledge transfer process in CDR under federated settings, we initialize an optimizable orthogonal mapping matrix to learn the embedding transformation across domains and adopt the local differential privacy technique on the transformed embedding before exchanging across domains, which provides the more reliable privacy protection. Furthermore, we exploit the similarity between in-domain and cross-domain embedding, and develop a gated selecting vector to refine the information fusion for more accurate dual-transfer. Extensive experiments on three real-world datasets demonstrate that P2FCDR significantly outperforms the state-of-the-art methods and effectively protects data privacy.

Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation

In recommender systems, a common problem is the presence of various biases in the collected data, which deteriorates the generalization ability of the recommendation models and leads to inaccurate predictions. Doubly robust (DR) learning has been studied in many tasks in RS, with the advantage that unbiased learning can be achieved when either a single imputation or a single propensity model is accurate. In this paper, we propose a multiple robust (MR) estimator that can take the advantage of multiple candidate imputation and propensity models to achieve unbiasedness. Specifically, the MR estimator is unbiased when any of the imputation or propensity models, or a linear combination of these models is accurate. Theoretical analysis shows that the proposed MR is an enhanced version of DR when only having a single imputation and propensity model, and has a smaller bias. Inspired by the generalization error bound of MR, we further propose a novel multiple robust learning approach with stabilization. We conduct extensive experiments on real-world and semi-synthetic datasets, which demonstrates the superiority of the proposed approach over state-of-the-art methods.

Multiple Robust Learning for Recommendation

Since Rendle and Krichene argued that commonly used sampling-based evaluation metrics are ``inconsistent'' with respect to the global metrics (even in expectation), there have been a few studies on the sampling-based recommender system evaluation. Existing methods try either mapping the sampling-based metrics to their global counterparts or more generally, learning the empirical rank distribution to estimate the top-$K$ metrics. 
However, despite existing efforts, there is still a lack of rigorous theoretical understanding of the proposed metric estimators, and the basic item sampling also suffers from the ``blind spot'' issue, i.e., estimation accuracy to recover the top-$K$ metrics when $K$ is small can still be rather substantial. 
In this paper, we provide an in-depth investigation into these problems and make two innovative contributions. First, we propose a new item-sampling estimator that explicitly optimizes the error with respect to the ground truth, and theoretically highlight its subtle difference against prior work. Second, we propose a new adaptive sampling method which aims to deal with the ``blind spot'' problem and also demonstrate the
expectation-maximization (EM) algorithm can be generalized for such a setting. 
Our experimental results confirm our statistical analysis and the superiority of the proposed works. 
This study helps lay the theoretical foundation for adopting item sampling metrics for recommendation evaluation, and provides strong evidence towards making item sampling a powerful and reliable tool for recommendation evaluation.

Towards Reliable Item Sampling for Recommendation Evaluation

As we all know, multi-view data is more expressive than single-view data and multi-label annotation enjoys richer supervision information than single-label, which makes multi-view multi-label learning widely applicable for various pattern recognition tasks. In this complex representation learning problem, three main challenges can be characterized as follows: i) How to learn consistent representations of samples across all views? ii) How to exploit and utilize category correlations of multi-label to guide inference? iii) How to avoid the negative impact resulting from the incompleteness of views or labels? To cope with these problems, we propose a general multi-view multi-label learning framework named label-guided masked view- and category-aware transformers in this paper. First, we design two transformer-style based modules for cross-view features aggregation and multi-label classification, respectively. The former aggregates information from different views in the process of extracting view-specific features, and the latter learns subcategory embedding to improve classification performance. Second, considering the imbalance of expressive power among views, an adaptively weighted view fusion module is proposed to obtain view-consistent embedding features. Third, we impose a label manifold constraint in sample-level representation learning to maximize the utilization of supervised information. Last but not least, all the modules are designed under the premise of incomplete views and labels, which makes our method adaptable to arbitrary multi-view and multi-label data. Extensive experiments on five datasets confirm that our method has clear advantages over other state-of-the-art methods.

Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers

Multi-view Comprehensive Representation Learning (MCRL) aims to synthesize information from multiple views to learn comprehensive representations of data items. Prevalent deep MCRL methods typically concatenate synergistic view-specific representations or average aligned view-specific representations in the fusion stage. However, the performance of synergistic fusion methods inevitably degenerate or even fail when partial views are missing in real-world applications; the aligned based fusion methods usually cannot fully exploit the complementarity of multi-view data. To eliminate all these drawbacks, in this work we present a Progressive Deep Multi-view Fusion (PDMF) method. Considering the multi-view comprehensive representation should contain complete information and the view-specific data contain partial information, we deem that it is unstable to directly learn the mapping from partial information to complete information. Hence, PDMF employs a progressive learning strategy, which contains the pre-training and fine-tuning stages. In the pre-training stage, PDMF decodes the auxiliary comprehensive representation to the view-specific data. It also captures the consistency and complementarity by learning the relations between the dimensions of the auxiliary comprehensive representation and all views. In the fine-tuning stage, PDMF learns the mapping from the original data to the comprehensive representation with the help of the auxiliary comprehensive representation and relations. Experiments conducted on a synthetic toy dataset and 4 real-world datasets show that PDMF outperforms state-of-the-art baseline methods. The code is released at https://github.com/winterant/PDMF.

Progressive Deep Multi-view Comprehensive Representation Learning

Video event extraction aims to detect salient events from a video and identify the arguments for each event as well as their semantic roles. Existing methods focus on capturing the overall visual scene of each frame, ignoring fine-grained argument-level information. Inspired by the definition of events as changes of  states, we propose a novel framework to detect video events by tracking the changes in the visual states of all involved arguments, which are expected to provide the most informative evidence for the extraction of video events. In order to capture the visual state changes of arguments, we decompose them into changes in pixels within objects, displacements of objects, and interactions among multiple arguments. We further propose Object State Embedding, Object Motion-aware Embedding and Argument Interaction Embedding to encode and track these changes respectively. Experiments on various video event extraction tasks demonstrate significant improvements compared to state-of-the-art models. In particular, on verb classification, we achieve 3.49% absolute gains (19.53% relative gains) in F1@5 on Video Situation Recognition.

Video Event Extraction via Tracking Visual States of Arguments

The problem of document structure reconstruction refers to converting digital or scanned documents into corresponding semantic structures. Most existing works mainly focus on splitting the boundary of each element in a single document page, neglecting the reconstruction of semantic structure in multi-page documents. This paper introduces hierarchical reconstruction of document structures as a novel task suitable for NLP and CV fields. To better evaluate the system performance on the new task, we built a large-scale dataset named HRDoc, which consists of 2,500 multi-page documents with nearly 2 million semantic units. Every document in HRDoc has line-level annotations including categories and relations obtained from rule-based extractors and human annotators. Moreover, we proposed an encoder-decoder-based hierarchical document structure parsing system (DSPS) to tackle this problem. By adopting a multi-modal bidirectional encoder and a structure-aware GRU decoder with soft-mask operation, the DSPS model surpass the baseline method by a large margin. All scripts and datasets will be made publicly available at https://github.com/jfma-USTC/HRDoc.

HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures

Hiding information in text documents has been a hot topic recently, with the most typical schemes of utilizing fonts. By constructing several fonts with similar appearances, information can be effectively represented and embedded in documents. However, due to the unstructured characteristic, font vectors are more difficult to synthesize than font images. Existing methods mainly use handcrafted features to design the fonts manually, which is time-consuming and labor-intensive. Moreover, due to the diversity of fonts, handcrafted features are not generalizable to different fonts. Besides, in practice, since documents might be distorted through transmission, ensuring extractability under distortions is also an important requirement. Therefore, three requirements are imposed on vector font generation in this domain: automaticity, generalizability, and robustness. However, none of the existing methods can satisfy these requirements well and simultaneously.
To satisfy the above requirements, we propose AutoStegaFont, an automatic vector font synthesis scheme for hiding information in documents. Specifically, we design a two-stage and dual-modality learning framework. In the first stage, we jointly train an encoder and a decoder to invisibly encode the font images with different information. To ensure robustness, we target designing a noise layer to work with the encoder and decoder during training. In the second stage, we employ a differentiable rasterizer to establish a connection between the image and the vector modality. Then, we design an optimization algorithm to convey the information from the encoded image to the corresponding vector. Thus the encoded font vectors can be automatically generated. Extensive experiments demonstrate the superior performance of our scheme in automatically synthesizing vector fonts for hiding information in documents, with robustness to distortions caused by low-resolution screenshots, printing, and photography. Besides, the proposed framework has better generalizability to fonts with diverse styles and languages.

AutoStegaFont: Synthesizing Vector Fonts for Hiding Information in Documents

From the observation that users reading news tend to not click outdated news, we propose the notion of 'lifetime' of news, with two hypotheses: (i) news has a shorter lifetime, compared to other types of items such as movies or e-commerce products; (ii) news only competes with other news whose lifetimes have not ended, and which has an overlapping lifetime (i.e., limited competitions). By further developing the characteristics of the lifetime of news, then we prenset a novel approach for news recommendation, namely, Lifetime-Aware News reCommEndeR System (LANCER) that carefully exploits the lifetime of news during training and recommendation. Using real-world news datasets (e.g., Adressa and MIND), we successfully demonstrate that state-of-the-art news recommendation models can get significantly benefited by integrating the notion of lifetime and LANCER, by up to about 40% increases in recommendation accuracy.

Underline digital video library

Important Clues that Facilitate Visual Emergence: Three Psychological Experiments

Noise Driven Coupled Dynamic Systems–Towards Low Power Pattern Recognition and Machine Learning

Structure Aware Incremental Learning with Personalized Imitation Weights for Recommender Systems

Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation

Multiple Robust Learning for Recommendation

Towards Reliable Item Sampling for Recommendation Evaluation

Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers

Progressive Deep Multi-view Comprehensive Representation Learning

Video Event Extraction via Tracking Visual States of Arguments

HRDoc: Dataset and Baseline Method Toward Hierarchical Reconstruction of Document Structures

AutoStegaFont: Synthesizing Vector Fonts for Hiding Information in Documents

LANCER: A Lifetime-Aware News Recommender System

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES