Search

In skeletal-based action recognition, Graph Convolutional Networks (GCNs) based methods face limitations due to their complexity and high energy consumption. Spiking Neural Networks (SNNs) have gained attention in recent years for their low energy consumption, but existing methods combining GCNs and SNNs fail to fully utilize the temporal characteristics of skeletal sequences, leading to increased storage and computational costs. To address this issue, we propose a Signal-SGN(Spiking Graph Convolutional Network), which leverages the temporal dimension of skeletal sequences as the spiking timestep and treats features as discrete stochastic signals. The core of the network consists of a 1D Spiking Graph Convolutional Network (1D-SGN) and a Frequency Spiking Convolutional Network (FSN). The SGN performs graph convolution on single frames and incorporates spiking network characteristics to capture inter-frame temporal relationships, while the FSN uses Fast Fourier Transform (FFT) and complex convolution to extract temporal-frequency features. We also introduce a multi-scale wavelet transform feature fusion module(MWTF) to capture spectral features of temporal signals, enhancing the model's classification capability. We propose a pluggable temporal-frequency spatial semantic feature extraction module(TFSM) to enhance the model's ability to distinguish features without increasing inference-phase consumption. Our numerous experiments on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets demonstrate that the proposed models not only surpass existing SNN-based methods in accuracy but also reduce computational and storage costs during training. Furthermore, they achieve competitive accuracy compared to corresponding GCN-based methods, which is quite remarkable.

Click-through rate (CTR) prediction tasks play a pivotal role in real-world applications, particularly in recommendation systems and online advertising. A significant research branch in this domain focuses on user behavior modeling. Current research predominantly centers on modeling co-occurrence relationships between the target item and items previously interacted with by users in their historical data. However, this focus neglects the intricate modeling of user behavior patterns. In reality, the abundance of user interaction records encompasses diverse behavior patterns, indicative of a spectrum of habitual paradigms. These patterns harbor substantial potential to significantly enhance CTR prediction performance. To harness the informational potential within user behavior patterns, we extend Target Attention (TA) to Target Pattern Attention (TPA) to model pattern-level dependencies. Furthermore, three critical challenges demand attention: the inclusion of unrelated items within behavior patterns, data sparsity in behavior patterns, and computational complexity arising from numerous patterns. To address these challenges, we introduce the Deep Pattern Network (DPN), designed to comprehensively leverage information from user behavior patterns. DPN efficiently retrieves target-related user behavior patterns using a target-aware attention mechanism. Additionally, it contributes to refining user behavior patterns through a pre-training paradigm based on self-supervised learning while promoting dependency learning within sparse patterns. Our comprehensive experiments, conducted across three public datasets, substantiate the superior performance and broad compatibility of DPN., Comment: 12 pages, 10 figures, accepted by SIGIR2024

We present Tencent's ads recommendation system and examine the challenges and practices of learning appropriate recommendation representations. Our study begins by showcasing our approaches to preserving prior knowledge when encoding features of diverse types into embedding representations. We specifically address sequence features, numeric features, and pre-trained embedding features. Subsequently, we delve into two crucial challenges related to feature representation: the dimensional collapse of embeddings and the interest entanglement across different tasks or scenarios. We propose several practical approaches to address these challenges that result in robust and disentangled recommendation representations. We then explore several training techniques to facilitate model optimization, reduce bias, and enhance exploration. Additionally, we introduce three analysis tools that enable us to study feature correlation, dimensional collapse, and interest entanglement. This work builds upon the continuous efforts of Tencent's ads recommendation team over the past decade. It summarizes general design principles and presents a series of readily applicable solutions and analysis tools. The reported performance is based on our online advertising platform, which handles hundreds of billions of requests daily and serves millions of ads to billions of users.

For a long time, due to the high heterogeneity in structure and semantics among various spatiotemporal modal data, the joint interpretation of multimodal spatiotemporal data has been an extremely challenging problem. The primary challenge resides in striking a trade-off between the cohesion and autonomy of diverse modalities, and this trade-off exhibits a progressively nonlinear nature as the number of modalities expands. We introduce the Language as Reference Framework (LaRF), a fundamental principle for constructing a multimodal unified model, aiming to strike a trade-off between the cohesion and autonomy among different modalities. We propose a multimodal spatiotemporal general artificial intelligence model, called AllSpark. Our model integrates thirteen different modalities into a unified framework, including 1D (text, code), 2D (RGB, infrared, SAR, multispectral, hyperspectral, tables, graphs, trajectory, oblique photography), and 3D (point clouds, videos) modalities. To achieve modal cohesion, AllSpark uniformly maps diverse modal features to the language modality. In addition, we design modality-specific prompts to guide multi-modal large language models in accurately perceiving multimodal data. To maintain modality autonomy, AllSpark introduces modality-specific encoders to extract the tokens of various spatiotemporal modalities. And modal bridge is employed to achieve dimensional projection from each modality to the language modality. Finally, observing a gap between the model's interpretation and downstream tasks, we designed task heads to enhance the model's generalization capability on specific downstream tasks. Experiments indicate that AllSpark achieves competitive accuracy in modalities such as RGB and trajectory compared to state-of-the-art models., Comment: 49 pages, 16 tables, 3 figures

Multi-domain learning (MDL) aims to train a model with minimal average risk across multiple overlapping but non-identical domains. To tackle the challenges of dataset bias and domain domination, numerous MDL approaches have been proposed from the perspectives of seeking commonalities by aligning distributions to reduce domain gap or reserving differences by implementing domain-specific towers, gates, and even experts. MDL models are becoming more and more complex with sophisticated network architectures or loss functions, introducing extra parameters and enlarging computation costs. In this paper, we propose a frustratingly easy and hyperparameter-free multi-domain learning method named Decoupled Training (D-Train). D-Train is a tri-phase general-to-specific training strategy that first pre-trains on all domains to warm up a root model, then post-trains on each domain by splitting into multi-heads, and finally fine-tunes the heads by fixing the backbone, enabling decouple training to achieve domain independence. Despite its extraordinary simplicity and efficiency, D-Train performs remarkably well in extensive evaluations of various datasets from standard benchmarks to applications of satellite imagery and recommender systems.

Localizing root causes for multi-dimensional data is critical to ensure online service systems' reliability. When a fault occurs, only the measure values within specific attribute combinations are abnormal. Such attribute combinations are substantial clues to the underlying root causes and thus are called root causes of multidimensional data. This paper proposes a generic and robust root cause localization approach for multi-dimensional data, PSqueeze. We propose a generic property of root cause for multi-dimensional data, generalized ripple effect (GRE). Based on it, we propose a novel probabilistic cluster method and a robust heuristic search method. Moreover, we identify the importance of determining external root causes and propose an effective method for the first time in literature. Our experiments on two real-world datasets with 5400 faults show that the F1-score of PSqueeze outperforms baselines by 32.89%, while the localization time is around 10 seconds across all cases. The F1-score in determining external root causes of PSqueeze achieves 0.90. Furthermore, case studies in several production systems demonstrate that PSqueeze is helpful to fault diagnosis in the real world., Comment: Accepted by Journal of Systems and Software at May 4 2023

In Click-through rate (CTR) prediction models, a user's interest is usually represented as a fixed-length vector based on her history behaviors. Recently, several methods are proposed to learn an attentive weight for each user behavior and conduct weighted sum pooling. However, these methods only manually select several fields from the target item side as the query to interact with the behaviors, neglecting the other target item fields, as well as user and context fields. Directly including all these fields in the attention may introduce noise and deteriorate the performance. In this paper, we propose a novel model named AutoAttention, which includes all item/user/context side fields as the query, and assigns a learnable weight for each field pair between behavior fields and query fields. Pruning on these field pairs via these learnable weights lead to automatic field pair selection, so as to identify and remove noisy field pairs. Though including more fields, the computation cost of AutoAttention is still low due to using a simple attention function and field pair selection. Extensive experiments on the public dataset and Tencent's production dataset demonstrate the effectiveness of the proposed approach., Comment: Accepted by ICDM 2022

Binary transition metal nitride with a graphene-like structure and strong magnetic properties is rare. Based on the first-principles calculations, we design two kinds of $M$N$_4$ ($M$ =transition metal) monolayers, which are transition metal nitrides with a planar structure, made up of $M$N$_4$ units aligned in the rhombic and square patterns. The two structural lattices have robust stability and good compatibility with different metal atoms, and the underlying mechanism is the combination of $sp^2$ hybridization, coordinate bond, and $\pi$ conjugation. With the metal atom changing from V, Cr, Mn, Fe to Co, the total charge of $M$N$_4$ system increases by one electron in turn, which results in continuous adjustability of the electronic and magnetic properties. The planar ligand field is another feature of the two $M$N$_4$ lattices, which brings about the special splitting of five suborbitals of 3$d$ metal atom and gives rise to strong magnetism. Moreover, room-temperature ferromagnetism in square-CoN$_4$ monolayer with the Curie temperatures of 321 K is determined by solving the Heisenberg model combined with Monte Carlo method.

MnSn monolayer synthesized recently is a novel two-dimensional ferromagnetic material with a hexagonal lattice, in which three Mn atom come together to form a trimer, making it remarkably different from other magnetic two-dimensional materials. Most impressively, there happens a sharp increase of Curie temperature from 54 K to 225 K when the number of layers increase from 1 to 3. However, no quantitative explanation is reported in previous studies. Herein, by means of first-principle calculations method and Monte carlo method, we demonstrate that strong interlayer ferromagnetic coupling is the essential role in enhancing its critical temperature, which act as a magnetic field to stabilize the ferromagnetism in the MnSn multilayers.

Single-atom-thick two-dimensional materials such as graphene usually have a hexagonal lattice while the square-planar lattice is uncommon in the family of two-dimensional materials. Here, we demonstrate that single-atom-thick transition metal nitride CrN$_4$ monolayer is a stable free-standing layer with a square-planar network. The stability of square-planar geometry is ascribed to the combination of N=N double bond, Cr-N coordination bond, and $\pi$-d conjugation, in which the double $\pi$-d conjugation is rarely reported in previous studies. This mechanism is entirely different from that of the reported two-dimensional materials, leading to lower formation energy and more robust stability compared to the synthesized g-C$_3$N$_4$ monolayer. On the other hand, CrN$_4$ layer has a ferromagnetic ground state, in which the ferromagnetic coupling between two Cr atoms is mediated by electrons of the half-filled large $\pi$ orbitals from $\pi$-d conjugation. The high-temperature ferromagnetism in CrN$_4$ monolayer is confirmed by solving the Heisenberg model with Monte Carlo method., Comment: https://link.aps.org/doi/10.1103/PhysRevB.106.125421

Magnetic two-dimensional materials have potential application in next-generation electronic devices and have stimulated extensive interest in condensed matter physics and material fields. However, how to realize high-temperature ferromagnetism in two-dimensional materials remains a great challenge in physics. Herein, we propose an effective approach that the dimerization of magnetic ions in two-dimensional materials can enhance the exchange coupling and stabilize the ferromagnetism. Manganese carbonitride Mn$_2$N$_6$C$_6$ with a planar monolayer structure is taken as an example to clarify the method, in which two Mn atoms are gathered together to form a ferromagnetic dimer of Mn atoms and further these dimers are coupled together to form the overall ferromagnetism of the two-dimensional material. In Mn$_2$N$_6$C$_6$ monolayer, the near-room-temperature ferromagnetism with the Curie temperature of 272.3 K is determined by solving Heisenberg model using Monte Carlo simulations method., Comment: Journal of Physical Chemistry C Cite This: https://doi.org/10.1021/acs.jpcc.2c02593

Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e.g, click, purchase) are treated as individual tasks and jointly trained with a unified model. Our key observation is that the prediction results of each task may contain task-specific knowledge about user's fine-grained preference towards items. While such knowledge could be transferred to benefit other tasks, it is being overlooked under the current MTL paradigm. This paper, instead, proposes a Cross-Task Knowledge Distillation framework that attempts to leverage prediction results of one task as supervised signals to teach another task. However, integrating MTL and KD in a proper manner is non-trivial due to several challenges including task conflicts, inconsistent magnitude and requirement of synchronous optimization. As countermeasures, we 1) introduce auxiliary tasks with quadruplet loss functions to capture cross-task fine-grained ranking information and avoid task conflicts, 2) design a calibrated distillation approach to align and distill knowledge from auxiliary tasks, and 3) propose a novel error correction mechanism to enable and facilitate synchronous training of teacher and student models. Comprehensive experiments are conducted to verify the effectiveness of our framework in real-world datasets., Comment: in AAAI 2022

The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days. It is hard to design an appropriate online learning system under these non-identical delay for different types of ads and users. In this paper, we propose to tackle the delayed feedback problem in online advertising by "Following the Prophet" (FTP for short). The key insight is that, if the feedback came instantly for all the logged samples, we could get a model without delayed feedback, namely the "prophet". Although the prophet cannot be obtained during online learning, we show that we could predict the prophet's predictions by an aggregation policy on top of a set of multi-task predictions, where each task captures the feedback patterns of different periods. We propose the objective and optimization approach for the policy, and use the logged data to imitate the prophet. Extensive experiments on three real-world advertising datasets show that our method outperforms the previous state-of-the-art baselines., Comment: In Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR '21), July 11--15, 2021, Virtual Event, Canada. ACM, New York, NY, USA, 5 pages. https://doi.org/10.1145/3404835.3463045