Methods › Sequential › Time Series Modules › Temporal Distribution Matching

Temporal Distribution Matching

1 paper tagged archive 2025-07-28

Introduced by Yuntao Du et al. in AdaRNN: Adaptive Learning and Forecasting of Time Series

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Temporal Distribution Matching, or TDM, is a module used in the AdaRNN architecture to match the distributions of the discovered periods to build a time series prediction model ℳ Given the learned time periods, the TDM module is designed to learn the common knowledge shared by different periods via matching their distributions. Thus, the learned model ℳ is expected to generalize well on unseen test data compared with the methods which only rely on local or statistical information.

Within the context of AdaRNN, Temporal Distribution Matching aims to adaptively match the distributions between the RNN cells of two periods while capturing the temporal dependencies. TDM introduces the importance vector α ∈ℝ^(V̂) to learn the relative importance of V hidden states inside the RNN, where all the hidden states are weighted with a normalized α. Note that for each pair of periods, there is an α, and we omit the subscript if there is no confusion. In this way, we can dynamically reduce the distribution divergence of cross-periods.

Given a period-pair (𝒟ᵢ, 𝒟ⱼ), the loss of temporal distribution matching is formulated as:

ℒ_(t d m)(𝒟ᵢ, 𝒟ⱼ ; θ)=∑ₜ₌₁ⱽ α_(i, j)ᵗ d(hᵢᵗ, hⱼᵗ ; θ)

where α_(i, j)ᵗ denotes the distribution importance between the periods 𝒟ᵢ and 𝒟ⱼ at state t.

All the hidden states of the RNN can be easily computed by following the standard RNN computation. Denote by δ(·) the computation of a next hidden state based on a previous state. The state computation can be formulated as

hᵢᵗ=δ(xᵢᵗ, hᵢᵗ⁻¹)

The final objective of temporal distribution matching (one RNN layer) is:

ℒ(θ, α)=ℒ_(pred)(θ)+λ2/(K(K-1)) ∑_(i, j)^(i ≠j) ℒ_(t d m)(𝒟ᵢ, 𝒟ⱼ ; θ, α)

where λ is a trade-off hyper-parameter. Note that in the second term, we compute the average of the distribution distances of all pairwise periods. For computation, we take a mini-batch of 𝒟ᵢ and 𝒟ⱼ to perform forward operation in RNN layers and concatenate all hidden features. Then, we can perform TDM using the above equation.

PaperSource

In Syntology for a different name, 'Distribution Matching', about another paper, arXiv:2106.00320: repository known, no verified implementation (declared_code; repositories: 1 listed of 1 in the graph, strongest link: official). The lookup matched a different name in Syntology's graph, 'Distribution Matching' (resolution: token_match); this answer is about that name. About another paper: this answer is about arXiv:2106.00320, while the archive credits arXiv:2108.04443.

Code Syntology holds under other names, as the lookup lists them (code_nearby); not a complete list, and none of them is this method.

Origin paper of this answer, arXiv:2106.00320 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

What each level means, quoted from Syntology's server card: V0 “imports”; V1 “executes against a synthesized fixture and returns a value of the recorded type”; V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)”; V3 “paper-derived property tests pass on both of those same two generations.” The card adds: “No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results.” A level quoted in two parts is one definition the card writes as two clauses joined by a double hyphen, each clause quoted on its own (how these levels are quoted).

Papers archive 2025-07-28

archive papers tagged: 1 · with a code link: 1 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran: none of the 1 tagged papers has a Syntology run on record

Page 1 of 1: paper 1 of 1, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Activity Recognition1
Financial Analysis1
Human Activity Recognition1
Time Series1
Time Series Analysis1

Usage over time archive 2025-07-28

Papers per year tagged with Temporal Distribution Matching: 2021 to 2021, peak 1 1 0 2021: 1 paper 2021
Papers per year the archive tags with this method, by the paper's archive date (1 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Time Series Modules

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections